CVPR 2018 追蹤之論文綱要（修正于2020.08.28）

• 講在前面
• 論文目錄

講在前面

• 論壇很多博客都對論文做了總結和分類，但就醫學領域而言，對這些論文的篩選信息顯然需要更加精細的把控，所以自己對這979篇的論文做一個大致從名稱上的篩選，希望能找到些能解決當前問題的答案。
• 論文鏈接建議直接Google論文名，比去各種論文或頂會網站找不知道快捷多少。
• 下面皆為機器翻譯以方便我第一次篩選，我會慢慢修正，但現在請結合。有興趣的可以問我要處理這些論文并自動翻譯的腳本。
• Respect！

---

論文目錄

論文概要

1.2D_3D Pose Estimation and Action Recognition Using Multitask Deep Learning 使用多任務深度學習的2D_3D姿勢估計和動作識別
2.3D Human Pose Estimation in the Wild by Adversarial Learning 通過對抗性學習在野外進行3D人體姿勢估計
3.3D Human Sensing, Action and Emotion Recognition in Robot Assisted Therapy of Children With Autism 孤獨癥兒童機器人輔助治療中的3D人體感應，動作和情感識別
4.3D Object Detection With Latent Support Surfaces 具有潛在支撐面的3D對象檢測
5.3D Pose Estimation and 3D Model Retrieval for Objects in the Wild 野外物體的3D姿勢估計和3D模型檢索
6.3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-Compare 3D-RCNN：通過渲染和比較重建實例級3D對象
7.3D Registration of Curves and Surfaces Using Local Differential Information 使用局部微分信息進行曲線和曲面的3D配準
8.3D Semantic Segmentation With Submanifold Sparse Convolutional Networks 子流形稀疏卷積網絡的3D語義分割
9.3D Semantic Trajectory Reconstruction From 3D Pixel Continuum 從3D像素連續體重建3D語義軌跡
10.4DFAB: A Large Scale 4D Database for Facial Expression Analysis and Biometric Applications 4DFAB：用于面部表情分析和生物識別應用程序的大規模4D數據庫
11.4D Human Body Correspondences From Panoramic Depth Maps 全景深度圖的4D人體對應
12.A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping A2-RL：用于圖像裁剪的美學意識增強學習
13.A Bi-Directional Message Passing Model for Salient Object Detection 顯著目標檢測的雙向消息傳遞模型
14.A Biresolution Spectral Framework for Product Quantization 用于產品量化的雙分辨率光譜框架
15.A Causal And-Or Graph Model for Visibility Fluent Reasoning in Tracking Interacting Objects 交互對象跟蹤中可視性推理的因果圖模型
16.Accurate and Diverse Sampling of Sequences Based on a “Best of Many” Sample Objective 基于“多個最佳”樣本目標的序列的準確多樣采樣
17.A Certifiably Globally Optimal Solution to the Non-Minimal Relative Pose Problem 非最小相對姿勢問題的可證明的全局最優解
18.A Closer Look at Spatiotemporal Convolutions for Action Recognition 近距離觀察時空卷積的動作識別
19.A Common Framework for Interactive Texture Transfer 交互式紋理傳輸的通用框架
20.A Constrained Deep Neural Network for Ordinal Regression 序數回歸的約束深度神經網絡
21.Action Sets: Weakly Supervised Action Segmentation Without Ordering Constraints 動作集：沒有順序約束的弱監督動作細分
22.Active Fixation Control to Predict Saccade Sequences 主動注視控制可預測掃視序列
23.Actor and Action Video Segmentation From a Sentence 句子中的演員和動作視頻分割
24.Actor and Observer: Joint Modeling of First and Third-Person Videos 演員和觀察員：第一人稱和第三人稱視頻的聯合建模
25.AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation AdaDepth：用于深度估計的無監督內容一致適應
26.A Deeper Look at Power Normalizations 深入了解功率歸一化
27.Adversarial Complementary Learning for Weakly Supervised Object Localization 弱監督對象定位的對抗互補學習
28.Adversarial Data Programming: Using GANs to Relax the Bottleneck of Curated Labeled Data 對抗性數據編程：使用GAN緩解標簽化數據的瓶頸
29.Adversarial Feature Augmentation for Unsupervised Domain Adaptation 無監督域自適應的對抗特征增強
30.Adversarially Learned One-Class Classifier for Novelty Detection 對抗性學習的一類分類器，用于新穎性檢測
31.Adversarially Occluded Samples for Person Re-Identification 對抗性樣本用于人員重新識別
32.A Face-to-Face Neural Conversation Model 面對面的神經對話模型
33.A Fast Resection-Intersection Method for the Known Rotation Problem 已知旋轉問題的快速后方交集方法
34.A Generative Adversarial Approach for Zero-Shot Learning From Noisy Texts 一種從嘈雜文本中零接觸學習的生成對抗方法
35.A Hierarchical Generative Model for Eye Image Synthesis and Eye Gaze Estimation 眼睛圖像合成和眼睛注視估計的分層生成模型
36.A High-Quality Denoising Dataset for Smartphone Cameras 用于智能手機相機的高質量降噪數據集
37.A Hybrid l1-l0 Layer Decomposition Model for Tone Mapping 用于色調映射的混合l1-l0層分解模型
38.Aligning Infinite-Dimensional Covariance Matrices in Reproducing Kernel Hilbert Spaces for Domain Adaptation 對齊域希爾伯特希爾伯特空間中的無限維協方差矩陣的對齊
39.Alive Caricature From 2D to 3D 從2D到3D的生動漫畫
40.A Low Power, High Throughput, Fully Event-Based Stereo System 低功耗，高吞吐量，完全基于事件的立體聲系統
41.Alternating-Stereo VINS: Observability Analysis and Performance Evaluation 交替立體VINS：可觀察性分析和性能評估
42.A Memory Network Approach for Story-Based Temporal Summarization of 360deg Videos 基于故事的360deg視頻時間摘要的記憶網絡方法
43.A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point Clouds 點云中二次元的類型不可知檢測的極簡方法
44.AMNet: Memorability Estimation With Attention AMNet：具有記憶力的評估
45.Analysis of Hand Segmentation in the Wild 野外手部分割分析
46.Analytical Modeling of Vanishing Points and Curves in Catadioptric Cameras 折反射相機中消失點和曲線的解析模型
47.Analytic Expressions for Probabilistic Moments of PL-DNN With Gaussian Input 高斯輸入的PL-DNN概率矩的解析表達式
48.Analyzing Filters Toward Efficient ConvNet 分析面向高效ConvNet的過濾器
49.An Analysis of Scale Invariance in Object Detection SNIP 目標檢測SNIP中尺度不變性的分析
50.Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation 卷積網絡中無監督生物醫學分割的解剖先驗

論文概要

51.An Efficient and Provable Approach for Mixture Proportion Estimation Using Linear Independence Assumption 使用線性獨立假設的混合比例估計的一種有效且可行的方法
52.An End-to-End TextSpotter With Explicit Alignment and Attention 具有明確對齊和注意力的端到端TextSpotter
53.A Network Architecture for Point Cloud Classification via Automatic Depth Images Generation 通過自動深度圖像生成進行點云分類的網絡架構
54.A Neural Multi-Sequence Alignment TeCHnique (NeuMATCH) 神經多序列比對技術（NeuMATCH）
55.Anticipating Traffic Accidents With Adaptive Loss and Large-Scale Incident DB 利用自適應丟失和大規模事件數據庫預測交通事故
56.An Unsupervised Learning Model for Deformable Medical Image Registration 可變形醫學圖像配準的無監督學習模型
57.AON: Towards Arbitrarily-Oriented Text Recognition AON：面向任意方向的文本識別
58.A Papier-Mache Approach to Learning 3D Surface Generation 學習3D曲面生成的Papier-Mache方法
59.A Perceptual Measure for Deep Single Image Camera Calibration 深度單像相機校準的感官測量
60.Aperture Supervision for Monocular Depth Estimation 用于單眼深度估計的光圈監控
61.A PID Controller Approach for Stochastic Optimization of Deep Networks 用于深度網絡隨機優化的PID控制器方法
62.A Pose-Sensitive Embedding for Person Re-Identification With Expanded Cross Neighborhood Re-Ranking 具有擴展的跨鄰域重新排列的姿勢重新識別的姿勢識別嵌入
63.Appearance-and-Relation Networks for Video Classification 視頻分類的外觀和關系網絡
64.A Prior-Less Method for Multi-Face Tracking in Unconstrained Videos 無約束視頻中多面跟蹤的一種先驗減少方法
65.Arbitrary Style Transfer With Deep Feature Reshuffle 任意樣式轉移，具有深層功能重組
66.A Revised Underwater Image Formation Model 修訂后的水下成像模型
67.Are You Talking to Me? Reasoned Visual Dialog Generation Through Adversarial Learning 你在跟我講話嗎？通過對抗學習進行合理的視覺對話生成
68.A Robust Method for Strong Rolling Shutter Effects Correction Using Lines With Automatic Feature Selection 一種具有自動特征選擇線的強力滾動快門效果校正的魯棒方法
69.Art of Singular Vectors and Universal Adversarial Perturbations 奇異向量和普遍對抗性攝動的藝術
70.Attend and Interact: Higher-Order Object Interactions for Video Understanding 參加和交互：用于視頻理解的高階對象交互
71.Attentional ShapeContextNet for Point Cloud Recognition 注意ShapeContextNet用于點云識別
72.Attention-Aware Compositional Network for Person Re-Identification 用于人員重新識別的注意感知組成網絡
73.Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification 注意力集群：基于純粹注意力的視頻分類局部特征集成
74.Attentive Fashion Grammar Network for Fashion Landmark Detection and Clothing Category Classification 專注于時尚地標檢測和服裝類別分類的時尚語法網絡
75.Attentive Generative Adversarial Network for Raindrop Removal From a Single Image 細心的生成對抗網絡，用于從單個圖像中去除雨滴
76.AttnGAN: Fine-Grained Text to Image Generation With Attentional Generative Adversarial Networks AttnGAN：細化文本到帶有注意生成對抗網絡的圖像生成
77.A Twofold Siamese Network for Real-Time Object Tracking 用于實時對象跟蹤的雙重連體網絡
78.A Two-Step Disentanglement Method 兩步解纏法
79.Audio to Body Dynamics 音頻到人體動力學
80.Augmented Skeleton Space Transfer for Depth-Based Hand Pose Estimation 基于深度的手部姿勢估計的增強骨架空間傳遞
81.Augmenting Crowd-Sourced 3D Reconstructions Using Semantic Detections 使用語義檢測增強人群源3D重建
82.A Unifying Contrast Maximization Framework for Event Cameras, With Applications to Motion, Depth, and Optical Flow Estimation 用于事件攝像機的統一對比度最大化框架，應用于運動，深度和光流估計
83.Automatic 3D Indoor Scene Modeling From Single Panorama 從單個全景圖進行自動3D室內場景建模
84.AVA: A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions AVA：時空局部原子視覺動作的視頻數據集
85.A Variational U-Net for Conditional Appearance and Shape Generation 用于條件外觀和形狀生成的變體U-網
86.Avatar-Net: Multi-Scale Zero-Shot Style Transfer by Feature Decoration Avatar-Net：通過特征裝飾進行多尺度零射擊樣式轉移
87.A Weighted Sparse Sampling and Smoothing Frame Transition Approach for Semantic Fast-Forward First-Person Videos 語義快進第一人稱視頻的加權稀疏采樣和平滑幀過渡方法
88.Baseline Desensitizing in Translation Averaging 平均翻譯中的基線脫敏
89.Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions 在不斷變化的條件下對6DOF戶外視覺本地化進行基準測試
90.Between-Class Learning for Image Classification 課間學習進行圖像分類
91.Beyond Grobner Bases: Basis Selection for Minimal Solvers Grobner基礎之外：最小求解器的基礎選擇
92.Beyond Holistic Object Recognition: Enriching Image Understanding With Part States 超越整體物體識別：利用零件狀態豐富圖像理解
93.Beyond the Pixel-Wise Loss for Topology-Aware Delineation 超越像素明智的拓撲描述
94.Beyond Trade-Off: Accelerate FCN-Based Face Detector With Higher Accuracy 權衡之外：高精度加速基于FCN的人臉檢測器
95.Bidirectional Attentive Fusion With Context Gating for Dense Video Captioning 具有上下文門控功能的雙向注意力融合，用于密集視頻字幕
96.Bidirectional Retrieval Made Simple 雙向檢索變得簡單
97.Bilateral Ordinal Relevance Multi-Instance Regression for Facial Action Unit Intensity Estimation 雙邊序貫相關性多實例回歸用于面部動作單位強度估計
98.Blazingly Fast Video Object Segmentation With Pixel-Wise Metric Learning 像素明智的度量學習，實現了驚人的快速視頻對象分割
99.Blind Predicting Similar Quality Map for Image Quality Assessment 盲預測相似質量圖進行圖像質量評估
100.BlockDrop: Dynamic Inference Paths in Residual Networks BlockDrop：殘差網絡中的動態推理路徑

論文概要

101.Boosting Adversarial Attacks With Momentum 用動量來增強對抗性攻擊
102.Boosting Domain Adaptation by Discovering Latent Domains 通過發現潛在域來促進域適應
103.Boosting Self-Supervised Learning via Knowledge Transfer 通過知識轉移促進自我監督學習
104.Bootstrapping the Performance of Webly Supervised Semantic Segmentation 引導Webly監督的語義分割的性能
105.Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering 自下而上和自上而下的注意力，用于圖像字幕和視覺問題解答
106.Boundary Flow: A Siamese Network That Predicts Boundary Motion Without Training on Motion 邊界流：無需運動訓練就可以預測邊界運動的暹羅網絡
107.BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning BPGrad：通過分支和修剪在深度學習中實現全球最優
108.Burst Denoising With Kernel Prediction Networks 內核預測網絡進行突發去噪
109.Camera Pose Estimation With Unknown Principal Point 主點未知的相機姿態估計
110.Camera Style Adaptation for Person Re-Identification 用于重新識別人的相機樣式適應
111.Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet? 時空3D CNN是否可以追溯2D CNN和ImageNet的歷史？
112.CarFusion: Combining Point Tracking and Part Detection for Dynamic 3D Reconstruction of Vehicles CarFusion：結合點跟蹤和零件檢測用于車輛的動態3D重構
113.CartoonGAN: Generative Adversarial Networks for Photo Cartoonization CartoonGAN：用于照片卡通化的生成對抗網絡
114.Cascaded Pyramid Network for Multi-Person Pose Estimation 用于多人姿勢估計的級聯金字塔網絡
115.Cascade R-CNN: Delving Into High Quality Object Detection 級聯R-CNN：深入研究高質量目標檢測
116.Categorizing Concepts With Basic Level for Vision-to-Language 將基本概念歸類為視覺到語言
117.CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation CBMV：用于視差估計的合并雙向匹配量
118.Classification-Driven Dynamic Image Enhancement 分類驅動的動態圖像增強
119.Classifier Learning With Prior Probabilities for Facial Action Unit Recognition 具有面部動作單元識別先驗概率的分類器學習
120.ClcNet: Improving the Efficiency of Convolutional Neural Network Using Channel Local Convolutions ClcNet：使用通道局部卷積提高卷積神經網絡的效率
121.CleanNet: Transfer Learning for Scalable Image Classifier Training With Label Noise CleanNet：帶標簽噪聲的可擴展圖像分類器培訓的轉移學習
122.CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition 清除：一鍵式一類圖像識別的累積學習
123.Clinical Skin Lesion Diagnosis Using Representations Inspired by Dermatologist Criteria 使用皮膚科醫生標準啟發的表征進行臨床皮膚病變診斷
124.CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization CLIP-Q：通過并行修剪量化進行深度網絡壓縮學習
125.ClusterNet: Detecting Small Objects in Large Scenes by Exploiting Spatio-Temporal Information ClusterNet：通過利用時空信息檢測大型場景中的小物體
126.CNN Based Learning Using Reflection and Retinex Models for Intrinsic Image Decomposition 基于CNN的使用反射和Retinex模型進行內在圖像分解的學習
127.CNN Driven Sparse Multi-Level B-Spline Image Registration CNN驅動的稀疏多級B樣條圖像配準
128.CNN in MRF: Video Object Segmentation via Inference in a CNN-Based Higher-Order Spatio-Temporal MRF MRF中的CNN：在基于CNN的高階時空MRF中通過推理進行視頻對象分割
129.COCO-Stuff: Thing and Stuff Classes in Context COCO-Stuff：上下文中的事物和事物類
130.CodeSLAM – Learning a Compact, Optimisable Representation for Dense Visual SLAM CodeSLAM-學習密集Visual SLAM的緊湊，可優化表示形式
131.Coding Kendall’s Shape Trajectories for 3D Action Recognition 編碼Kendall的形狀軌跡以進行3D動作識別
132.Collaborative and Adversarial Network for Unsupervised Domain Adaptation 無監督域自適應的協作和對抗網絡
133.Compare and Contrast: Learning Prominent Visual Differences 比較和對比：學習明顯的視覺差異
134.Compassionately Conservative Balanced Cuts for Image Segmentation 慷慨保守的平衡切割用于圖像分割
135.Compressed Video Action Recognition 壓縮視頻動作識別
136.CondenseNet: An Efficient DenseNet Using Learned Group Convolutions CondenseNet：使用學習的組卷積的高效DenseNet
137.Conditional Generative Adversarial Network for Structured Domain Adaptation 結構化領域適應的條件生成對抗網絡
138.Conditional Image-to-Image Translation 有條件的圖像到圖像翻譯
139.Conditional Probability Models for Deep Image Compression 深度圖像壓縮的條件概率模型
140.Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in Images 將像素連接到隱私和實用程序：自動刪除圖像中的私人信息
141.Consensus Maximization for Semantic Region Correspondences 語義區域對應的共識最大化
142.Content-Sensitive Supervoxels via Uniform Tessellations on Video Manifolds 通過視頻流形上的統一鑲嵌來對內容敏感的超級體素
143.Context-Aware Deep Feature Compression for High-Speed Visual Tracking 用于高速視覺跟蹤的上下文感知深度特征壓縮
144.Context-Aware Synthesis for Video Frame Interpolation 視頻幀插值的上下文感知綜合
145.Context Contrasted Feature and Gated Multi-Scale Aggregation for Scene Segmentation 用于場景分割的上下文對比特征和門控多尺度聚合
146.Context Embedding Networks 上下文嵌入網絡
147.Context Encoding for Semantic Segmentation 用于語義分割的上下文編碼
148.Continuous Relaxation of MAP Inference: A Nonconvex Perspective MAP推理的連續松弛：非凸視角
149.Controllable Video Generation With Sparse Trajectories 具有稀疏軌跡的可控視頻生成
150.Convolutional Image Captioning 卷積圖像字幕

論文概要

151.Convolutional Neural Networks With Alternately Updated Clique 具有交替更新的派系的卷積神經網絡
152.Convolutional Sequence to Sequence Model for Human Dynamics 卷積序列到人類動力學序列模型
153.Correlation Tracking via Joint Discrimination and Reliability Learning 通過聯合鑒別和可靠性學習進行關聯跟蹤
154.CosFace: Large Margin Cosine Loss for Deep Face Recognition CosFace：用于識別深臉的大余弦余弦損失
155.Coupled End-to-End Transfer Learning With Generalized Fisher Information 端到端遷移學習與廣義Fisher信息相結合
156.Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning 通過深度強化學習制作用于圖像還原的工具鏈
157.Creating Capsule Wardrobes From Fashion Images 從時尚形象創建膠囊衣柜
158.Cross-Dataset Adaptation for Visual Question Answering 跨數據集自適應以解決視覺問題
159.Cross-Domain Self-Supervised Multi-Task Feature Learning Using Synthetic Imagery 使用合成影像的跨域自我監督多任務特征學習
160.Cross-Domain Weakly-Supervised Object Detection Through Progressive Domain Adaptation 通過漸進域自適應進行跨域弱監督對象檢測
161.Cross-Modal Deep Variational Hand Pose Estimation 跨模態深度變化手姿勢估計
162.Cross-View Image Synthesis Using Conditional GANs 使用條件GAN的跨視圖圖像合成
163.Crowd Counting via Adversarial Cross-Scale Consistency Pursuit 通過對抗性跨尺度一致性追求進行人群計數
164.Crowd Counting With Deep Negative Correlation Learning 深度負相關學習的人群計數
165.CRRN: Multi-Scale Guided Concurrent Reflection Removal Network CRRN：多尺度引導并發反射去除網絡
166.CSGNet: Neural Shape Parser for Constructive Solid Geometry CSGNet：用于構造實體幾何的神經形狀解析器
167.CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes CSRNet：擴展卷積神經網絡，用于了解高度擁擠的場景
168.Cube Padding for Weakly-Supervised Saliency Prediction in 360deg Videos 360度視頻中弱監督顯著性預測的多維數據集填充
169.Curve Reconstruction via the Global Statistics of Natural Curves 通過自然曲線的整體統計量重建曲線
170.Customized Image Narrative Generation via Interactive Visual Question Generation and Answering 通過交互式視覺問題生成和回答定制的圖像敘事生成
171.CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization CVM-Net：用于基于圖像的地對空地理定位的跨視圖匹配網絡
172.DA-GAN: Instance-Level Image Translation by Deep Attention Generative Adversarial Networks DA-GAN：深度注意生成對抗網絡的實例級圖像翻譯
173.Data Distillation: Towards Omni-Supervised Learning 數據提煉：走向全監督學習
174.DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks DeblurGAN：使用條件對抗網絡進行盲運動去模糊
175.DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation DecideNet：通過注意力指導的檢測和密度估計計算不同的密度人群
176.Decorrelated Batch Normalization 裝飾相關的批次標準化
177.Decoupled Networks 解耦網絡
178.Deep Adversarial Metric Learning 深度對抗度量學習
179.Deep Adversarial Subspace Clustering 深度對抗子空間聚類
180.Deep Back-Projection Networks for Super-Resolution 深度背投網絡可實現超高分辨率
181.Deep Cauchy Hashing for Hamming Space Retrieval 深層柯西散列用于漢明空間檢索
182.Deep Cocktail Network: Multi-Source Unsupervised Domain Adaptation With Category Shift 深度雞尾酒網絡：具有類別轉移的多源無監督域自適應
183.Deep Cost-Sensitive and Order-Preserving Feature Learning for Cross-Population Age Estimation 用于跨人口年齡估計的深度成本敏感和順序保留特征學習
184.Deep Cross-Media Knowledge Transfer 深度跨媒體知識轉移
185.Deep Density Clustering of Unconstrained Faces 無約束面孔的深度密度聚類
186.Deep Depth Completion of a Single RGB-D Image 單個RGB-D圖像的深度完成
187.Deep Diffeomorphic Transformer Networks 深微形變壓器網絡
188.Deep End-to-End Time-of-Flight Imaging 深度端到端飛行時間成像
189.Deep Extreme Cut: From Extreme Points to Object Segmentation 深度極限切割：從極限點到對象分割
190.Deep Face Detector Adaptation Without Negative Transfer or Catastrophic Forgetting 無需負遷移或災難性遺忘的深臉檢測器自適應
191.Deep Group-Shuffling Random Walk for Person Re-Identification 用于人員重新識別的深度群混洗隨機游走
192.Deep Hashing via Discrepancy Minimization 通過差異最小化進行深度哈希
193.Deep Image Prior 深度圖像先驗
194.Deep Layer Aggregation 深層聚合
195.Deep Learning of Graph Matching 圖匹配的深度學習
196.Deep Learning Under Privileged Information Using Heteroscedastic Dropout 使用異方差輟學在特權信息下進行深度學習
197.Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-Scale Lesion Database 在野外的深部病變圖：關系學習和在大量大型病變數據庫中的重要放射圖像發現的組織
198.Deeply Learned Filter Response Functions for Hyperspectral Reconstruction 深度學習的濾波器響應函數，用于高光譜重建
199.Deep Marching Cubes: Learning Explicit Surface Representations 深入進行中的立方體：學習明確的表面表示
200.Deep Material-Aware Cross-Spectral Stereo Matching 深度材料感知跨譜立體匹配

論文概要

201.Deep Mutual Learning 深度相互學習
202.DeepMVS: Learning Multi-View Stereopsis DeepMVS：學習多視圖立體視覺
203.Deep Ordinal Regression Network for Monocular Depth Estimation 用于單眼深度估計的深度序數回歸網絡
204.Deep Parametric Continuous Convolutional Neural Networks 深參量連續卷積神經網絡
205.Deep Photo Enhancer: Unpaired Learning for Image Enhancement From Photographs With GANs 深度照片增強器：使用GAN從照片中進行成對學習的圖像增強
206.Deep Progressive Reinforcement Learning for Skeleton-Based Action Recognition 基于骨骼的動作識別的深度漸進強化學習
207.Deep Regression Forests for Age Estimation 深回歸森林的年齡估算
208.Deep Reinforcement Learning of Region Proposal Networks for Object Detection 用于對象檢測的區域提議網絡的深度強化學習
209.Deep Semantic Face Deblurring 深層語義去模糊
210.Deep Sparse Coding for Invariant Multimodal Halle Berry Neurons 不變多模態哈莉·貝瑞神經元的深度稀疏編碼
211.Deep Spatial Feature Reconstruction for Partial Person Re-Identification: Alignment-Free Approach 用于部分人員重新識別的深度空間特征重建：無路線方法
212.Deep Spatio-Temporal Random Fields for Efficient Video Segmentation 深度時空隨機場，用于有效的視頻分割
213.Deep Texture Manifold for Ground Terrain Recognition 用于地面地形識別的深紋理流形
214.Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective 深度無監督的顯著性檢測：多重噪聲標記
215.Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation 深度視頻超分辨率網絡，使用動態上采樣濾波器，無需顯式運動補償
216.DeepVoting: A Robust and Explainable Deep Network for Semantic Part Detection Under Partial Occlusion DeepVoting：在部分遮擋下用于語義部分檢測的強大且可解釋的深度網絡
217.Defense Against Adversarial Attacks Using High-Level Representation Guided Denoiser 使用高級表示制導的降噪器防御對抗攻擊
218.Defense Against Universal Adversarial Perturbations 防御普遍的對抗性干擾
219.Deflecting Adversarial Attacks With Pixel Deflection 通過像素偏轉來對抗對手的攻擊
220.Defocus Blur Detection via Multi-Stream Bottom-Top-Bottom Fully Convolutional Network 通過多流底部-頂部-底部完全卷積網絡進行散焦模糊檢測
221.Deformable GANs for Pose-Based Human Image Generation 用于基于姿勢的人體圖像生成的可變形GAN
222.Deformable Shape Completion With Graph Convolutional Autoencoders 圖卷積自動編碼器的可變形形狀完成
223.Deformation Aware Image Compression 變形感知圖像壓縮
224.DeLS-3D: Deep Localization and Segmentation With a 3D Semantic Map DeLS-3D：具有3D語義圖的深度定位和細分
225.Demo2Vec: Reasoning Object Affordances From Online Videos Demo2Vec：從在線視頻中推理出對象客流
226.Dense 3D Regression for Hand Pose Estimation 手勢姿勢估計的密集3D回歸
227.DenseASPP for Semantic Segmentation in Street Scenes DenseASPP用于街道場景中的語義分割
228.Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation 用于單遍語義分割的密集解碼器快捷方式連接
229.Densely Connected Pyramid Dehazing Network 密集連接的金字塔除霧網絡
230.DensePose: Dense Human Pose Estimation in the Wild DensePose：野外的密集人體姿勢估計
231.Density Adaptive Point Set Registration 密度自適應點集配準
232.Density-Aware Single Image De-Raining Using a Multi-Stream Dense Network 使用多流密集網絡的密度感知單圖像降噪
233.Depth and Transient Imaging With Compressive SPAD Array Cameras 壓縮SPAD陣列攝像機的深度和瞬態成像
234.Depth-Aware Stereo Video Retargeting 深度感知立體聲視頻重定向
235.Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals 基于深度的3D手勢估計：從當前成就到未來目標
236.Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation 分離和適應：學習跨域解纏結的深度表示
237.Detail-Preserving Pooling in Deep Networks 深度網絡中保留細節的池
238.Detect-and-Track: Efficient Pose Estimation in Videos 檢測并跟蹤：視頻中的有效姿勢估計
239.Detect Globally, Refine Locally: A Novel Approach to Saliency Detection 全局檢測，局部優化：顯著性檢測的新方法
240.Detecting and Recognizing Human-Object Interactions 檢測和識別人與物體的相互作用
241.Differential Attention for Visual Question Answering 視覺問答中的注意差異
242.Dimensionality’s Blessing: Clustering Images by Underlying Distribution 維數的祝福：通過基礎分布將圖像聚類
243.Direction-Aware Spatial Context Features for Shadow Detection 用于陰影檢測的方向感知空間上下文功能
244.Direct Shape Regression Networks for End-to-End Face Alignment 直接形狀回歸網絡用于端對端的面對齊
245.Discovering Point Lights With Intensity Distance Fields 發現具有強度距離場的點光源
246.Discrete-Continuous ADMM for Transductive Inference in Higher-Order MRFs 離散連續ADMM用于高階MRF中的轉導推理
247.Discriminability Objective for Training Descriptive Captions 訓練描述性字幕的可分辨性目標
248.Discriminative Learning of Latent Features for Zero-Shot Recognition 零射擊識別的潛在特征的判別學習
249.Disentangled Person Image Generation 糾纏人圖像生成
250.Disentangling 3D Pose in a Dendritic CNN for Unconstrained 2D Face Alignment 解開樹枝狀CNN中的3D姿勢以實現不受約束的2D面部對齊

論文概要

251.Disentangling Factors of Variation by Mixing Them 通過混合將變量分解開來
252.Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognition 解開3D人臉形狀的特征以進行聯合人臉重建和識別
253.Disentangling Structure and Aesthetics for Style-Aware Image Completion 解開結構和美學的風格感知圖像完成
254.Distort-and-Recover: Color Enhancement Using Deep Reinforcement Learning 失真與恢復：使用深度強化學習增強色彩
255.Distributable Consistent Multi-Object Matching 可分配一致的多對象匹配
256.DiverseNet: When One Right Answer Is Not Enough DiverseNet：當一個正確的答案還不夠時
257.Diversity Regularized Spatiotemporal Attention for Video-Based Person Re-Identification 基于視頻的人員重新識別的多樣性正則化時空注意
258.Divide and Conquer for Full-Resolution Light Field Deblurring 分立制勝，實現全分辨率光場去模糊
259.Divide and Grow: Capturing Huge Diversity in Crowd Images With Incrementally Growing CNN 分而成長：隨著CNN的不斷增長，捕捉人群圖像中的巨大多樣性
260.Document Enhancement Using Visibility Detection 使用可見性檢測增強文檔
261.DocUNet: Document Image Unwarping via a Stacked U-Net DocUNet：文檔圖像通過堆疊的U-Net變形
262.Domain Adaptive Faster R-CNN for Object Detection in the Wild 用于野外目標檢測的域自適應快速R-CNN
263.Domain Generalization With Adversarial Feature Learning 具有對抗性特征學習的領域概括
264.Don’t Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering 不要只是假設；外觀和答案：克服視覺提問的先驗
265.DOTA: A Large-Scale Dataset for Object Detection in Aerial Images DOTA：用于航空圖像中目標檢測的大規模數據集
266.DoubleFusion: Real-Time Capture of Human Performances With Inner Body Shapes From a Single Depth Sensor DoubleFusion：通過單個深度傳感器實時捕獲具有人體形狀的人體表演
267.DS*: Tighter Lifting-Free Convex Relaxations for Quadratic Matching Problems *DS ：針對二次匹配問題的更緊的免提凸松弛
268.Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-Identification 用于基于上下文感知特征序列的人員重新識別的雙注意匹配網絡
269.Dual Skipping Networks 雙跳網
270.Duplex Generative Adversarial Network for Unsupervised Domain Adaptation 用于無監督域自適應的雙工生成對抗網絡
271.DVQA: Understanding Data Visualizations via Question Answering DVQA：通過問答理解數據可視化
272.Dynamic Feature Learning for Partial Face Recognition 動態特征學習用于部分人臉識別
273.Dynamic Few-Shot Visual Learning Without Forgetting 無需忘記的動態少量視覺學習
274.Dynamic Graph Generation Network: Generating Relational Knowledge From Diagrams 動態圖生成網絡：從圖生成關系知識
275.Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks 使用空間變異遞歸神經網絡進行動態場景去模糊
276.Dynamic-Structured Semantic Propagation Network 動態結構的語義傳播網絡
277.Dynamic Video Segmentation Network 動態視頻分割網絡
278.Dynamic Zoom-In Network for Fast Object Detection in Large Images 動態放大網絡，可快速檢測大圖像中的物體
279.Easy Identification From Better Constraints: Multi-Shot Person Re-Identification From Reference Constraints 從更好的約束中輕松識別：從參考約束中進行多次連發人員重新識別
280.Edit Probability for Scene Text Recognition 編輯場景文本識別的概率
281.Efficient and Deep Person Re-Identification Using Multi-Level Similarity 使用多級相似性進行有效的深度人員重新識別
282.Efficient Diverse Ensemble for Discriminative Co-Tracking 高效的多元化集合體，可進行區分式協同跟蹤
283.Efficient Interactive Annotation of Segmentation Datasets With Polygon-RNN++ 使用Polygon-RNN ++的分段數據集的高效交互式注釋
284.Efficient Large-Scale Approximate Nearest Neighbor Search on OpenCL FPGA 在OpenCL FPGA上進行高效的大規模近似最近鄰居搜索
285.Efficient Optimization for Rank-Based Loss Functions 基于等級的損失函數的有效優化
286.Efficient Parametrization of Multi-Domain Deep Neural Networks 多域深度神經網絡的高效參數化
287.Efficient, Sparse Representation of Manifold Distance Matrices for Classical Scaling 流形距離矩陣的有效，稀疏表示
288.Efficient Subpixel Refinement With Symbolic Linear Predictors 使用符號線性預測器進行有效的亞像素細化
289.Efficient Video Object Segmentation via Network Modulation 通過網絡調制進行有效的視頻對象分割
290.Egocentric Activity Recognition on a Budget 預算中的自我中心活動識別
291.Egocentric Basketball Motion Planning From a Single First-Person Image 從單個第一人稱圖像進行以自我為中心的籃球運動計劃
292.Eliminating Background-Bias for Robust Person Re-Identification 消除背景偏見，進行穩健的人員重新識別
293.Embodied Question Answering 具體問題解答
294.Emotional Attention: A Study of Image Sentiment and Visual Attention 情緒注意：圖像情感和視覺注意的研究
295.Empirical Study of the Topology and Geometry of Deep Networks 深度網絡拓撲和幾何的實證研究
296.Encoding Crowd Interaction With Deep Neural Network for Pedestrian Trajectory Prediction 用深度神經網絡編碼人群交互作用以預測行人軌跡
297.End-to-End Convolutional Semantic Embeddings 端到端卷積語義嵌入
298.End-to-End Deep Kronecker-Product Matching for Person Re-Identification 端到端深度Kronecker產品匹配以重新識別人
299.End-to-End Dense Video Captioning With Masked Transformer 帶屏蔽變壓器的端到端密集視頻字幕
300.End-to-End Flow Correlation Tracking With Spatial-Temporal Attention 時空注意的端到端流相關跟蹤

論文概要

301.End-to-End Learning of Keypoint Detector and Descriptor for Pose Invariant 3D Matching 姿勢不變3D匹配的關鍵點檢測器和描述符的端到端學習
302.End-to-End Learning of Motion Representation for Video Understanding 端到端學習運動表示以了解視頻
303.End-to-End Recovery of Human Shape and Pose 人體形狀和姿勢的端到端恢復
304.End-to-End Weakly-Supervised Semantic Alignment 端到端弱監督的語義對齊
305.Enhancing the Spatial Resolution of Stereo Images Using a Parallax Prior 使用視差先驗增強立體圖像的空間分辨率
306.Environment Upgrade Reinforcement Learning for Non-Differentiable Multi-Stage Pipelines 不可分多階段管道的環境升級強化學習
307.EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth From Light Field Images EPINET：一種全卷積神經網絡，使用對極幾何學從光場圖像中提取深度
308.Erase or Fill? Deep Joint Recurrent Rain Removal and Reconstruction in Videos 擦除還是填充？視頻中的深層關節經常性除雨和重建
309.Estimation of Camera Locations in Highly Corrupted Scenarios: All About That Base, No Shape Trouble 高度損壞的場景中攝像機位置的估計：關于該基準的所有信息，沒有形狀問題
310.Event-Based Vision Meets Deep Learning on Steering Prediction for Self-Driving Cars 基于事件的愿景與無人駕駛汽車轉向預測的深度學習相遇
311.Every Smile Is Unique: Landmark-Guided Diverse Smile Generation 每個微笑都是獨一無二的：具有地標性的多樣化微笑產生
312.Excitation Backprop for RNNs RNN的激勵反向傳播
313.Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks 低位深度神經網絡的明確的丟失錯誤感知量化
314.Exploiting Transitivity for Learning Person Re-Identification Models on a Budget 在預算中利用可傳遞性學習人的重新識別模型
315.Exploit the Unknown Gradually: One-Shot Video-Based Person Re-Identification by Stepwise Learning 逐步利用未知：通過逐步學習對基于視頻的一擊式人員進行重新識別
316.Exploring Disentangled Feature Representation Beyond Face Identification 探索超越人臉識別的非糾纏特征表示
317.Extreme 3D Face Reconstruction: Seeing Through Occlusions 極端3D面部重建：透視遮擋
318.Eye In-Painting With Exemplar Generative Adversarial Networks 使用示例性生成對抗網絡進行眼睛內畫
319.Face Aging With Identity-Preserved Conditional Generative Adversarial Networks 保留身份的條件生成對抗網絡的面孔老化
320.FaceID-GAN: Learning a Symmetry Three-Player GAN for Identity-Preserving Face Synthesis FaceID-GAN：學習對稱三層GAN來保持身份的人臉合成
321.Facelet-Bank for Fast Portrait Manipulation Facelet-Bank用于快速人像操作
322.Facial Expression Recognition by De-Expression Residue Learning 去表達殘基學習的面部表情識別
323.Factoring Shape, Pose, and Layout From the 2D Image of a 3D Scene 從3D場景的2D圖像分解形狀，姿勢和布局
324.Fast and Accurate Online Video Object Segmentation via Tracking Parts 通過跟蹤部件快速，準確地在線分割視頻對象
325.Fast and Accurate Single Image Super-Resolution via Information Distillation Network 通過信息蒸餾網絡實現快速，準確的單圖像超分辨率
326.Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting With a Single Convolutional Net 速度與激情：使用單個卷積網絡進行實時端到端3D檢測，跟蹤和運動預測
327.Fast and Robust Estimation for Unit-Norm Constrained Linear Fitting Problems 單位范數約束線性擬合問題的快速魯棒估計
328.Fast End-to-End Trainable Guided Filter 快速的端到端可訓練導引濾波器
329.Fast Monte-Carlo Localization on Aerial Vehicles Using Approximate Continuous Belief Representations 使用近似連續信念表示法對飛行器進行快速蒙特卡洛定位
330.Fast Spectral Ranking for Similarity Search 相似搜索的快速光譜排名
331.Fast Video Object Segmentation by Reference-Guided Mask Propagation 通過參考引導的遮罩傳播進行快速視頻對象分割
332.FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis FeaStNet：用于3D形狀分析的基于特征的圖卷積
333.Feature Generating Networks for Zero-Shot Learning 零發學習的特征生成網絡
334.Feature Mapping for Learning Fast and Accurate 3D Pose Inference From Synthetic Images 從合成圖像中快速，準確地學習3D姿勢推斷的特征映射
335.Feature Quantization for Defending Against Distortion of Images 防止圖像失真的特征量化
336.Feature Selective Networks for Object Detection 用于目標檢測的特征選擇網絡
337.Features for Multi-Target Multi-Camera Tracking and Re-Identification 多目標多攝像機跟蹤和重新識別功能
338.Feature Space Transfer for Data Augmentation 特征空間傳輸以增強數據
339.Feature Super-Resolution: Make Machine See More Clearly 功能超高分辨率：使機器更加清晰
340.Feedback-Prop: Convolutional Neural Network Inference Under Partial Evidence 反饋支持：部分證據下的卷積神經網絡推理
341.Few-Shot Image Recognition by Predicting Parameters From Activations 通過預測激活參數來進行少量圖像識別
342.FFNet: Video Fast-Forwarding via Reinforcement Learning FFNet：通過強化學習進行視頻快速轉發
343.Fight Ill-Posedness With Ill-Posedness: Single-Shot Variational Depth Super-Resolution From Shading 與病態對抗病態：陰影的單發變化深度超級分辨率
344.Finding Beans in Burgers: Deep Semantic-Visual Embedding With Localization 在漢堡中尋找豆子：具有本地化功能的深度語義視覺嵌入
345.Finding “It”: Weakly-Supervised Reference-Aware Visual Grounding in Instructional Videos 找到“它”：教學視頻中受弱監督的參考感知的視覺基礎
346.Finding Tiny Faces in the Wild With Generative Adversarial Network 利用生成對抗網絡在野外尋找小臉
347.Fine-Grained Video Captioning for Sports Narrative 體育敘事的細粒度視頻字幕
348.First-Person Hand Action Benchmark With RGB-D Videos and 3D Hand Pose Annotations 具有RGB-D視頻和3D手勢注釋的第一人稱手勢基準
349.Five-Point Fundamental Matrix Estimation for Uncalibrated Cameras 未校準相機的五點基本矩陣估計
350.FlipDial: A Generative Model for Two-Way Visual Dialogue FlipDial：雙向視覺對話的生成模型

論文概要

351.Flow Guided Recurrent Neural Encoder for Video Salient Object Detection 流導向的遞歸神經編碼器，用于視頻顯著目標檢測
352.Focal Visual-Text Attention for Visual Question Answering 視覺問題解答的焦點視覺文本注意
353.Focus Manipulation Detection via Photometric Histogram Analysis 通過光度直方圖分析進行焦點操縱檢測
354.FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation FoldingNet：通過深層網格變形的點云自動編碼器
355.Fooling Vision and Language Models Despite Localization and Attention Mechanism 盡管存在本地化和注意力機制，但仍會愚弄視覺和語言模型
356.FOTS: Fast Oriented Text Spotting With a Unified Network FOTS：使用統一網絡快速定位文本
357.Frame-Recurrent Video Super-Resolution 幀循環視頻超分辨率
358.Free Supervision From Video Games 電子游戲免費監督
359.From Lifestyle Vlogs to Everyday Interactions 從生活時尚博客到日常互動
360.From Source to Target and Back: Symmetric Bi-Directional Adaptive GAN 從源到目標再到目標：對稱雙向自適應GAN
361.Frustum PointNets for 3D Object Detection From RGB-D Data 用于從RGB-D數據進行3D對象檢測的Frustum PointNets
362.FSRNet: End-to-End Learning Face Super-Resolution With Facial Priors FSRNet：具有面部先驗的端到端學習面孔超分辨率
363.Fully Convolutional Adaptation Networks for Semantic Segmentation 用于語義分割的全卷積自適應網絡
364.Functional Map of the World 世界功能地圖
365.Fusing Crowd Density Maps and Visual Object Trackers for People Tracking in Crowd Scenes 融合人群密度圖和視覺對象跟蹤器以在人群場景中進行人跟蹤
366.Future Frame Prediction for Anomaly Detection - A New Baseline 異常檢測的未來幀預測-新基準
367.Future Person Localization in First-Person Videos 第一人稱視頻中的未來人本地化
368.GAGAN: Geometry-Aware Generative Adversarial Networks GAGAN：幾何感知生成對抗網絡
369.GANerated Hands for Real-Time 3D Hand Tracking From Monocular RGB 用于單眼RGB的實時3D手跟蹤的分層手
370.Gated Fusion Network for Single Image Dehazing 門控融合網絡用于單圖像去霧
371.Gaze Prediction in Dynamic 360deg Immersive Videos 動態360度沉浸式視頻中的注視預測
372.Generalized Zero-Shot Learning via Synthesized Examples 通過綜合實例進行廣義零槍學習
373.Generate to Adapt: Aligning Domains Using Generative Adversarial Networks 生成以適應：使用生成對抗網絡調整域
374.Generating a Fusion Image: One’s Identity and Another’s Shape 生成融合圖像：一個人的身份和另一個人的形狀
375.Generating Synthetic X-Ray Images of a Person From the Surface Geometry 從表面幾何形狀生成人的合成X射線圖像
376.Generative Adversarial Image Synthesis With Decision Tree Latent Controller 決策樹潛在控制器的對抗式生成圖像綜合
377.Generative Adversarial Learning Towards Fast Weakly Supervised Detection 生成對抗性學習，實現快速弱監督檢測
378.Generative Adversarial Perturbations 生成對抗性擾動
379.Generative Image Inpainting With Contextual Attention 具有上下文注意的生成圖像修復
380.Generative Modeling Using the Sliced Wasserstein Distance 使用切片Wasserstein距離進行生成建模
381.Geometric Multi-Model Fitting With a Convex Relaxation Algorithm 凸松弛算法進行幾何多模型擬合
382.Geometric Robustness of Deep Networks: Analysis and Improvement 深度網絡的幾何魯棒性：分析和改進
383.Geometry Aware Constrained Optimization Techniques for Deep Learning 深度學習的幾何感知約束優化技術
384.Geometry-Aware Deep Network for Single-Image Novel View Synthesis 用于單圖像新穎視圖合成的幾何感知深度網絡
385.Geometry-Aware Learning of Maps for Camera Localization 用于相機定位的地圖的幾何感知學習
386.Geometry-Aware Network for Non-Rigid Shape Prediction From a Single View 從單個視圖進行非剛性形狀預測的幾何感知網絡
387.Geometry-Aware Scene Text Detection With Instance Transformation Network 具有實例轉換網絡的幾何感知場景文本檢測
388.Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning 幾何指導的卷積神經網絡用于自指導視頻表示學習
389.GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation GeoNet：用于聯合深度和表面法線估計的幾何神經網絡
390.GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose GeoNet：密集深度，光流和相機姿勢的無監督學習
391.Gesture Recognition: Focus on the Hands 手勢識別：專注于手
392.Gibson Env: Real-World Perception for Embodied Agents 吉布森環境（Gibson Env）：現實世界對特工的看法
393.Glimpse Clouds: Human Activity Recognition From Unstructured Feature Points 瞥見云：來自非結構化特征點的人類活動識別
394.Globally Optimal Inlier Set Maximization for Atlanta Frame Estimation 亞特蘭大幀估計的全局最優Inlier集最大化
395.Global Versus Localized Generative Adversarial Nets 全球與本地化生成對抗網
396.Going From Image to Video Saliency: Augmenting Image Salience With Dynamic Attentional Push 從圖像到視頻顯著性：通過動態注意力推送來增強圖像顯著性
397.Good View Hunting: Learning Photo Composition From Dense View Pairs 良好的視野狩獵：從密集的視野對中學習照片構圖
398.GraphBit: Bitwise Interaction Mining via Deep Reinforcement Learning GraphBit：通過深度強化學習進行按位交互挖掘
399.Graph-Cut RANSAC 圖切RANSAC
400.Grounding Referring Expressions in Images by Variational Context 通過變體上下文使圖像中的指稱表達接地

論文概要

401.GroupCap: Group-Based Image Captioning With Structured Relevance and Diversity Constraints GroupCap：具有結構相關性和多樣性約束的基于組的圖像字幕
402.Group Consistent Similarity Learning via Deep CRF for Person Re-Identification 通過深度CRF進行群體一致性相似性學習以進行人員重新識別
403.Guided Proofreading of Automatic Segmentations for Connectomics Connectomics自動細分的指導性校對
404.Guide Me: Interacting With Deep Networks 指導我：與深度網絡互動
405.GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition GVCNN：用于3D形狀識別的組視圖卷積神經網絡
406.Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learning 幻覺IQA：通過對抗學習進行無參考圖像質量評估
407.Hand PointNet: 3D Hand Pose Estimation Using Point Sets Hand PointNet：使用點集的3D手姿估計
408.Harmonious Attention Network for Person Re-Identification 重新識別人的和諧注意網絡
409.HashGAN: Deep Learning to Hash With Pair Conditional Wasserstein GAN HashGAN：深度學習與有條件的Wasserstein GAN配對
410.Hashing as Tie-Aware Learning to Rank 散列為領帶感知學習排名
411.HATS: Histograms of Averaged Time Surfaces for Robust Event-Based Object Classification HATS：魯棒的基于事件的對象分類的平均時間表面直方圖
412.Hierarchical Novelty Detection for Visual Object Recognition 視覺對象識別的層次新穎性檢測
413.Hierarchical Recurrent Attention Networks for Structured Online Maps 結構化在線地圖的分層遞歸注意網絡
414.High-Order Tensor Regularization With Application to Attribute Ranking 高階張量正則化及其在屬性排序中的應用
415.High Performance Visual Tracking With Siamese Region Proposal Network 連體區域提案網絡的高性能視覺跟蹤
416.High-Resolution Image Synthesis and Semantic Manipulation With Conditional GANs 有條件GAN的高分辨率圖像合成和語義處理
417.High-Speed Tracking With Multi-Kernel Correlation Filters 利用多核相關濾波器進行高速跟蹤
418.HSA-RNN: Hierarchical Structure-Adaptive RNN for Video Summarization HSA-RNN：用于視頻匯總的分層結構自適應RNN
419.Human Appearance Transfer 人的外觀轉移
420.Human-Centric Indoor Scene Synthesis Using Stochastic Grammar 基于隨機語法的以人為中心的室內場景合成
421.Human Pose Estimation With Parsing Induced Learner 解析誘導學習者的人體姿勢估計
422.Human Semantic Parsing for Person Re-Identification 用于人員重新識別的人類語義解析
423.Hybrid Camera Pose Estimation 混合相機姿勢估計
424.HydraNets: Specialized Dynamic Architectures for Efficient Inference HydraNets：高效推理的專用動態架構
425.Hyperparameter Optimization for Tracking With Continuous Deep Q-Learning 連續深度Q學習的超參數優化跟蹤
426.ICE-BA: Incremental, Consistent and Efficient Bundle Adjustment for Visual-Inertial SLAM ICE-BA：視覺慣性SLAM的增量，一致和高效的捆綁包調整
427.Illuminant Spectra-Based Source Separation Using Flash Photography 使用閃光燈攝影的基于光譜的光源分離
428.Im2Flow: Motion Hallucination From Static Images for Action Recognition Im2Flow：從靜態圖像進行動作幻覺以進行動作識別
429.Im2Pano3D: Extrapolating 360deg Structure and Semantics Beyond the Field of View Im2Pano3D：超越視野，外推360度結構和語義
430.Im2Struct: Recovering 3D Shape Structure From a Single RGB Image Im2Struct：從單個RGB圖像中恢復3D形狀結構
431.Image Blind Denoising With Generative Adversarial Network Based Noise Modeling 基于生成對抗網絡的噪聲建模的圖像盲去噪
432.Image Collection Pop-Up: 3D Reconstruction and Clustering of Rigid and Non-Rigid Categories 圖像集合彈出窗口：剛性和非剛性類別的3D重構和聚類
433.Image Correction via Deep Reciprocating HDR Transformation 通過深度往復HDR變換進行圖像校正
434.Image Generation From Scene Graphs 從場景圖生成圖像
435.Image-Image Domain Adaptation With Preserved Self-Similarity and Domain-Dissimilarity for Person Re-Identification 保留人的自我相似性和域相似性的圖像-圖像域自適應
436.Image Restoration by Estimating Frequency Distribution of Local Patches 通過估計局部補丁的頻率分布來恢復圖像
437.Image Super-Resolution via Dual-State Recurrent Networks 通過雙狀態循環網絡實現圖像超分辨率
438.Image to Image Translation for Domain Adaptation 圖像到圖像翻譯以進行域自適應
439.Importance Weighted Adversarial Nets for Partial Domain Adaptation 局部域自適應的重要性加權對抗網
440.Improved Fusion of Visual and Language Representations by Dense Symmetric Co-Attention for Visual Question Answering 密集的對稱共同注意對視覺問題的回答，改善了視覺和語言表示的融合
441.Improved Lossy Image Compression With Priming and Spatially Adaptive Bit Rates for Recurrent Networks 面向遞歸網絡的具有啟動和空間自適應位速率的改進的有損圖像壓縮
442.Improvements to Context Based Self-Supervised Learning 基于上下文的自我監督學習的改進
443.Improving Color Reproduction Accuracy on Cameras 提高相機的色彩還原精度
444.Improving Landmark Localization With Semi-Supervised Learning 通過半監督學習改善地標本地化
445.Improving Object Localization With Fitness NMS and Bounded IoU Loss 使用Fitness NMS和有限的IoU損失改善對象定位
446.Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors 改善單階段行人探測器的遮擋和硬負處理
447.Independently Recurrent Neural Network (IndRNN): Building a Longer and Deeper RNN 獨立循環神經網絡（IndRNN）：構建更長更深的RNN
448.Indoor RGB-D Compass From a Single Line and Plane 單線和平面的室內RGB-D指南針
449.Inference in Higher Order MRF-MAP Problems With Small and Large Cliques 帶有小集團的高階MRF-MAP問題的推論
450.Inferring Light Fields From Shadows 從陰影推斷光場

論文概要

451.Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis 推理語義布局以實現文本到圖像的分層合成
452.Inferring Shared Attention in Social Scene Videos 推斷社交場景視頻中的共享注意力
453.InLoc: Indoor Visual Localization With Dense Matching and View Synthesis InLoc：具有密集匹配和視圖綜合的室內視覺本地化
454.In-Place Activated BatchNorm for Memory-Optimized Training of DNNs 就地激活的BatchNorm，用于DNN的內存優化訓練
455.Instance Embedding Transfer to Unsupervised Video Object Segmentation 實例嵌入轉移到無監督視頻對象分割
456.Interactive Image Segmentation With Latent Diversity 具有潛在多樣性的交互式圖像分割
457.Interleaved Structured Sparse Convolutional Neural Networks 交錯結構的稀疏卷積神經網絡
458.Interpretable Convolutional Neural Networks 可解釋的卷積神經網絡
459.Interpretable Video Captioning via Trajectory Structured Localization 通過軌跡結構化本地化可解釋的視頻字幕
460.Interpret Neural Networks by Identifying Critical Data Routing Paths 通過識別關鍵數據路由路徑來解釋神經網絡
461.Intrinsic Image Transformation via Scale Space Decomposition 通過尺度空間分解的本征圖像變換
462.Inverse Composition Discriminative Optimization for Point Cloud Registration 點云配準的逆組合判別優化
463.InverseFaceNet: Deep Monocular Inverse Face Rendering InverseFaceNet：深單目反面渲染
464.IQA: Visual Question Answering in Interactive Environments IQA：交互環境中的視覺問題解答
465.ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing ISTA-Net：基于可解釋性優化的深度網絡，用于圖像壓縮傳感
466.Iterative Learning With Open-Set Noisy Labels 開放式嘈雜標簽的迭代學習
467.Iterative Visual Reasoning Beyond Convolutions 超越卷積的迭代視覺推理
468.IVQA: Inverse Visual Question Answering IVQA：逆向視覺問答
469.Jerk-Aware Video Acceleration Magnification 挺舉感知視頻加速倍率
470.Joint Cuts and Matching of Partitions in One Graph 一幅圖中的聯合切割和分區匹配
471.Jointly Localizing and Describing Events for Dense Video Captioning 聯合本地化和描述用于密集視頻字幕的事件
472.Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation 聯合優化數據增強和網絡培訓：人體姿勢估計中的對抗性數據增強
473.Joint Optimization Framework for Learning With Noisy Labels 帶有噪音標簽的聯合優化學習框架
474.Joint Pose and Expression Modeling for Facial Expression Recognition 面部表情識別的聯合姿勢和表情建模
475.Kernelized Subspace Pooling for Deep Local Descriptors 深度本地描述符的內核化子空間池
476.KIPPI: KInetic Polygonal Partitioning of Images KIPPI：圖像的運動多邊形分割
477.Knowledge Aided Consistency for Weakly Supervised Phrase Grounding 弱監督短語接地的知識輔助一致性
478.Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Faces 用于面部反照的標簽去噪對抗網絡（LDAN）
479.LAMV: Learning to Align and Match Videos With Kernelized Temporal Layers LAMV：學習將視頻與內核時間層對齊和匹配
480.Language-Based Image Editing With Recurrent Attentive Models 基于循環注意力模型的基于語言的圖像編輯
481.Large-Scale Distance Metric Learning With Uncertainty 不確定性的大規模遠程度量學習
482.Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning 大規模細粒度分類和特定領域轉移學習
483.Large-Scale Point Cloud Semantic Segmentation With Superpoint Graphs 超點圖的大規模點云語義分割
484.Latent RANSAC 潛在的RANSAC
485.LayoutNet: Reconstructing the 3D Room Layout From a Single RGB Image LayoutNet：從單個RGB圖像重建3D房間布局
486.LDMNet: Low Dimensional Manifold Regularized Neural Networks LDMNet：低維流形正則化神經網絡
487.Lean Multiclass Crowdsourcing 精益多類眾包
488.Learned Shape-Tailored Descriptors for Segmentation 習得的形狀定制描述符用于細分
489.Learning 3D Shape Completion From Laser Scan Data With Weak Supervision 通過弱監督從激光掃描數據中學習3D形狀完成
490.Learning a Complete Image Indexing Pipeline 學習完整的圖像索引管道
491.Learning a Discriminative Feature Network for Semantic Segmentation 學習用于語義分割的判別特征網絡
492.Learning a Discriminative Filter Bank Within a CNN for Fine-Grained Recognition 學習CNN中的判別式濾波器組以進行細粒度識別
493.Learning a Discriminative Prior for Blind Image Deblurring 學習判別先驗盲圖像去模糊
494.Learning and Using the Arrow of Time 學習和使用時間之箭
495.Learning Answer Embeddings for Visual Question Answering 學習視覺視覺答案的答案嵌入
496.Learning a Single Convolutional Super-Resolution Network for Multiple Degradations 學習單個卷積超分辨率網絡以進行多次降級
497.Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking 學習注意力：殘余注意力連體網絡，用于高性能在線視覺跟蹤
498.Learning Attribute Representations With Localization for Flexible Fashion Search 通過本地化學習屬性表示以實現靈活的時尚搜索
499.Learning by Asking Questions 提問學習
500.Learning Compact Recurrent Neural Networks With Block-Term Tensor Decomposition 通過塊期張量分解學習緊湊型遞歸神經網絡

論文概要

501.Learning Compositional Visual Concepts With Mutual Consistency 相互一致地學習構圖視覺概念
502.Learning Compressible 360deg Video Isomers 學習可壓縮的360deg視頻異構體
503.“Learning-Compression” Algorithms for Neural Net Pruning 神經網絡修剪的“學習-壓縮”算法
504.Learning Convolutional Networks for Content-Weighted Image Compression 學習卷積網絡進行內容加權圖像壓縮
505.Learning Deep Descriptors With Scale-Aware Triplet Networks 使用可感知規模的三重態網絡學習深度描述符
506.Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision 學習深度模型進行面部反欺騙：二進制或輔助監督
507.Learning Deep Sketch Abstraction 學習深度素描抽象
508.Learning Deep Structured Active Contours End-to-End 端到端學習深度結構化活動輪廓
509.Learning Depth From Monocular Videos Using Direct Methods 使用直接方法從單眼視頻中學習深度
510.Learning Descriptor Networks for 3D Shape Synthesis and Analysis 用于3D形狀合成和分析的學習描述符網絡
511.Learning Distributions of Shape Trajectories From Longitudinal Datasets: A Hierarchical Model on a Manifold of Diffeomorphisms 從縱向數據集學習形狀軌跡的分布：Diffeomorphisms流形的層次模型。
512.Learning Dual Convolutional Neural Networks for Low-Level Vision 學習雙卷積神經網絡以實現低視力
513.Learning Face Age Progression: A Pyramid Architecture of GANs 學習面部年齡發展：GAN的金字塔體系結構
514.Learning Facial Action Units From Web Images With Scalable Weakly Supervised Clustering 通過可擴展的弱監督聚類從Web圖像中學習面部動作單元
515.Learning for Disparity Estimation Through Feature Constancy 通過特征恒定學習差異估計
516.Learning From Millions of 3D Scans for Large-Scale 3D Face Recognition 從數百萬的3D掃描中學習以進行大規模3D人臉識別
517.Learning From Noisy Web Data With Category-Level Supervision 通過類別級監督從嘈雜的Web數據中學習
518.Learning From Synthetic Data: Addressing Domain Shift for Semantic Segmentation 從合成數據中學習：解決語義語義分割的域移位
519.Learning Generative ConvNets via Multi-Grid Modeling and Sampling 通過多網格建模和采樣學習生成式ConvNet
520.Learning Globally Optimized Object Detector via Policy Gradient 通過策略梯度學習全局優化的對象檢測器
521.Learning Intelligent Dialogs for Bounding Box Annotation 學習邊界框注釋的智能對話框
522.Learning Intrinsic Image Decomposition From Watching the World 從觀看世界中學習內在的圖像分解
523.Learning Latent Super-Events to Detect Multiple Activities in Videos 學習潛在的超級事件以檢測視頻中的多個活動
524.Learning Less Is More - 6D Camera Localization via 3D Surface Regression 學會少即是多-通過3D表面回歸實現6D相機本地化
525.Learning Markov Clustering Networks for Scene Text Detection 學習用于場景文本檢測的馬爾可夫聚類網絡
526.Learning Monocular 3D Human Pose Estimation From Multi-View Images 從多視圖圖像中學習單眼3D人類姿勢估計
527.Learning Multi-Instance Enriched Image Representations via Non-Greedy Ratio Maximization of the l1-Norm Distances 通過l1-Norm距離的非貪心比最大化學習多實例富集圖像表示
528.Learning Patch Reconstructability for Accelerating Multi-View Stereo 學習補丁可重構性，以加速多視圖立體聲
529.Learning Pixel-Level Semantic Affinity With Image-Level Supervision for Weakly Supervised Semantic Segmentation 通過圖像級監督學習像素級語義親和度以實現弱監督語義分割
530.Learning Pose Specific Representations by Predicting Different Views 通過預測不同的觀點來學習姿勢特定表示
531.Learning Rich Features for Image Manipulation Detection 學習豐富的圖像操縱檢測功能
532.Learning Semantic Concepts and Order for Image and Sentence Matching 學習語義概念和圖像和句子匹配的順序
533.Learning Spatial-Aware Regressions for Visual Tracking 學習用于視覺跟蹤的空間感知回歸
534.Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking 學習時空正則化相關濾波器以進行視覺跟蹤
535.Learning Steerable Filters for Rotation Equivariant CNNs 學習旋轉等變CNN的可控濾波器
536.Learning Strict Identity Mappings in Deep Residual Networks 在深度殘差網絡中學習嚴格的身份映射
537.Learning Structure and Strength of CNN Filters for Small Sample Size Training 小樣本量訓練的CNN濾波器的學習結構和強度
538.Learning Superpixels With Segmentation-Aware Affinity Loss 通過分段感知的親和力損失學習超像素
539.Learning Time_Memory-Efficient Deep Architectures With Budgeted Super Networks 通過預算的超級網絡學習時間_內存高效的深度架構
540.Learning to Act Properly: Predicting and Explaining Affordances From Images 學習正確采取行動：預測和解釋圖像中的負擔
541.Learning to Adapt Structured Output Space for Semantic Segmentation 學習適應結構化輸出空間進行語義分割
542.Learning to Compare: Relation Network for Few-Shot Learning 學習比較：很少學習的關系網絡
543.Learning to Detect Features in Texture Images 學習檢測紋理圖像中的特征
544.Learning to Estimate 3D Human Pose and Shape From a Single Color Image 學習從單色圖像估計3D人類姿勢和形狀
545.Learning to Evaluate Image Captioning 學習評估圖像字幕
546.Learning to Extract a Video Sequence From a Single Motion-Blurred Image 學習從單個運動模糊圖像中提取視頻序列
547.Learning to Find Good Correspondences 學習尋找良好的對應關系
548.Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks 學習使用多階段動態生成對抗網絡生成延時視頻
549.Learning to Localize Sound Source in Visual Scenes 學習在視覺場景中定位聲源
550.Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Tasks 學習環顧四周：智能探索未知任務未知的環境

論文概要

551.Learning to Parse Wireframes in Images of Man-Made Environments 學習解析人造環境圖像中的線框
552.Learning to Promote Saliency Detectors 學習促進顯著性檢測器
553.Learning to See in the Dark 學習在黑暗中看
554.Learning to Segment Every Thing 學會分割一切
555.Learning to Sketch With Shortcut Cycle Consistency 學習以快捷的周期一致性進行素描
556.Learning to Understand Image Blur 學習理解圖像模糊
557.Learning Transferable Architectures for Scalable Image Recognition 學習可擴展的體系結構以實現可擴展的圖像識別
558.Learning Visual Knowledge Memory Networks for Visual Question Answering 學習視覺知識記憶網絡以進行視覺問答
559.Left-Right Comparative Recurrent Model for Stereo Matching 立體聲匹配的左右比較遞歸模型
560.LEGO: Learning Edge With Geometry All at Once by Watching Videos 樂高：通過觀看視頻一次學習幾何的優勢
561.Leveraging Unlabeled Data for Crowd Counting by Learning to Rank 通過學習排名利用未標記的數據進行人群計數
562.LiDAR-Video Driving Dataset: Learning Driving Policies Effectively LiDAR視頻駕駛數據集：有效學習駕駛策略
563.Light Field Intrinsics With a Deep Encoder-Decoder Network 具有深層編碼器-解碼器網絡的光場本征
564.Lightweight Probabilistic Deep Networks 輕型概率深度網絡
565.LIME: Live Intrinsic Material Estimation LIME：實時內在材料估計
566.Link and Code: Fast Indexing With Graphs and Compact Regression Codes 鏈接和代碼：使用圖形和緊湊回歸代碼進行快速索引
567.Lions and Tigers and Bears: Capturing Non-Rigid, 3D, Articulated Shape From Images 獅子和老虎與熊：從圖像中捕獲非剛性，3D，關節形狀
568.LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation LiteFlowNet：用于光流估計的輕量級卷積神經網絡
569.Local and Global Optimization Techniques in Graph-Based Clustering 基于圖的聚類中的局部和全局優化技術
570.Local Descriptors Optimized for Average Precision 優化本地描述符以實現平均精度
571.Logo Synthesis and Manipulation With Clustered Generative Adversarial Networks 聚類生成對抗網絡的徽標合成和操縱
572.Long-Term On-Board Prediction of People in Traffic Scenes Under Uncertainty 不確定情況下交通場景中人員的長期車載預測
573.Look at Boundary: A Boundary-Aware Face Alignment Algorithm 看邊界：邊界感知的人臉對齊算法
574.Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval With Generative Models 外觀，想象和匹配：使用生成模型改進文本視覺跨模態檢索
575.Lose the Views: Limited Angle CT Reconstruction via Implicit Sinogram Completion 失去視野：通過隱式Singram完成有限角度CT重建
576.Low-Latency Video Semantic Segmentation 低延遲視頻語義分割
577.Low-Shot Learning From Imaginary Data 虛幻數據的低速學習
578.Low-Shot Learning With Imprinted Weights 帶有權重的低速學習
579.Low-Shot Learning With Large-Scale Diffusion 大規模擴散的低射學習
580.LSTM Pose Machines LSTM姿勢機
581.M3: Multimodal Memory Modelling for Video Captioning M3：用于視頻字幕的多模式內存建模
582.Making Convolutional Networks Recurrent for Visual Sequence Learning 使卷積網絡循環進行視覺序列學習
583.Manifold Learning in Quotient Spaces 商空間中的流形學習
584.MapNet: An Allocentric Spatial Memory for Mapping Environments MapNet：映射環境的同心圓空間內存
585.Mask-Guided Contrastive Attention Model for Person Re-Identification 面罩引導的對比注意模型用于人員重新識別
586.MaskLab: Instance Segmentation by Refining Object Detection With Semantic and Direction Features MaskLab：通過語義和方向特征完善對象檢測來實現實例分割
587.Matching Adversarial Networks 匹配的對抗網絡
588.Matching Pixels Using Co-Occurrence Statistics 使用共現統計匹配像素
589.Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layers Matryoshka Networks：通過嵌套形狀層預測3D幾何
590.MAttNet: Modular Attention Network for Referring Expression Comprehension MAttNet：用于引用表達理解的模塊化注意網絡
591.Maximum Classifier Discrepancy for Unsupervised Domain Adaptation 無監督域自適應的最大分類器差異
592.Mean-Variance Loss for Deep Age Estimation From a Face 從臉部進行深度估計的均值方差損失
593.MegaDepth: Learning Single-View Depth Prediction From Internet Photos MegaDepth：從互聯網照片中學習單視圖深度預測
594.MegDet: A Large Mini-Batch Object Detector MegDet：大型小批量物體檢測器
595.Memory Based Online Learning of Deep Representations From Video Streams 基于內存的視頻流深度表示在線學習
596.Memory Matching Networks for One-Shot Image Recognition 一鍵式圖像識別的內存匹配網絡
597.Mesoscopic Facial Geometry Inference Using Deep Neural Networks 使用深層神經網絡的介觀面部幾何推理
598.MiCT: Mixed 3D_2D Convolutional Tube for Human Action Recognition MiCT：用于人類動作識別的混合3D_2D卷積管
599.Min-Entropy Latent Model for Weakly Supervised Object Detection 弱熵目標檢測的最小熵潛模型
600.Mining on Manifolds: Metric Learning Without Labels 流形上的挖掘：無標簽的公制學習

論文概要

601.Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling 基于核相關和圖池的挖掘點云局部結構
602.Missing Slice Recovery for Tensors Using a Low-Rank Model in Embedded Space 在嵌入式空間中使用低秩模型進行張量缺失切片恢復
603.Mix and Match Networks: Encoder-Decoder Alignment for Zero-Pair Image Translation 混合和匹配網絡：零對圖像轉換的編碼器-解碼器對準
604.MobileNetV2: Inverted Residuals and Linear Bottlenecks MobileNetV2：殘差和線性瓶頸
605.Mobile Video Object Detection With Temporally-Aware Feature Maps 具有臨時感知特征圖的移動視頻對象檢測
606.MoCoGAN: Decomposing Motion and Content for Video Generation MoCoGAN：分解運動和內容以生成視頻
607.Modeling Facial Geometry Using Compositional VAEs 使用合成VAE對面部幾何建模
608.Modifying Non-Local Variations Across Multiple Views 跨多個視圖修改非局部變化
609.Modulated Convolutional Networks 調制卷積網絡
610.MoNet: Deep Motion Exploitation for Video Object Segmentation MoNet：用于視頻對象分割的深度運動開發
611.MoNet: Moments Embedding Network MoNet：時刻嵌入網絡
612.Monocular 3D Pose and Shape Estimation of Multiple People in Natural Scenes - The Importance of Multiple Scene Constraints 自然場景中多人的單眼3D姿勢和形狀估計-多場景約束的重要性
613.Monocular Relative Depth Perception With Web Stereo Data Supervision Web立體聲數據監控的單眼相對深度感知
614.MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks MorphNet：深度網絡的快速，簡單的資源受限結構學習
615.Motion-Appearance Co-Memory Networks for Video Question Answering 運動外觀協同存儲網絡，用于視頻問答
616.Motion-Guided Cascaded Refinement Network for Video Object Segmentation 運動引導級聯細化網絡的視頻對象分割
617.Motion Segmentation by Exploiting Complementary Geometric Models 利用互補幾何模型進行運動分割
618.MovieGraphs: Towards Understanding Human-Centric Situations From Videos MovieGraphs：通過視頻了解以人為中心的情況
619.Multi-Agent Diverse Generative Adversarial Networks 多智能體多元化生成對抗網絡
620.Multi-Cell Detection and Classification Using a Generative Convolutional Model 使用生成卷積模型進行多細胞檢測和分類
621.Multi-Content GAN for Few-Shot Font Style Transfer 多內容GAN，可進行少量字體轉換
622.Multi-Cue Correlation Filters for Robust Visual Tracking 多線索相關濾波器可實現強大的視覺跟蹤
623.Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning 基于弱監督學習的多標簽分類，目標檢測和語義分割的多證據過濾與融合
624.Multi-Frame Quality Enhancement for Compressed Video 壓縮視頻的多幀質量增強
625.Multi-Image Semantic Matching by Mining Consistent Features 挖掘一致特征的多圖像語義匹配
626.Multi-Label Zero-Shot Learning With Structured Knowledge Graphs 具有結構化知識圖的多標簽零射擊學習
627.Multi-Level Factorisation Net for Person Re-Identification 用于人員重新識別的多層次分解網絡
628.Multi-Level Fusion Based 3D Object Detection From Monocular Images 基于多級融合的單眼圖像3D目標檢測
629.Multimodal Explanations: Justifying Decisions and Pointing to the Evidence 多式聯運的解釋：做出合理的決定并指向證據
630.Multimodal Visual Concept Learning With Weakly Supervised Techniques 弱監督技術的多模式視覺概念學習
631.Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation 通過角點定位和區域分割的多方位場景文本檢測
632.Multiple Granularity Group Interaction Prediction 多粒度群相互作用預測
633.Multi-Scale Location-Aware Kernel Representation for Object Detection 用于對象檢測的多尺度位置感知內核表示
634.Multi-Scale Weighted Nuclear Norm Image Restoration 多尺度加權核規范圖像復原
635.Multi-Shot Pedestrian Re-Identification via Sequential Decision Making 通過順序決策進行多步行人重新識別
636.Multispectral Image Intrinsic Decomposition via Subspace Constraint 通過子空間約束進行多光譜圖像固有分解
637.Multistage Adversarial Losses for Pose-Based Human Image Synthesis 基于姿勢的人體圖像合成的多階段對抗性損失
638.Multi-Task Adversarial Network for Disentangled Feature Learning 多任務對抗網絡的融合特征學習
639.Multi-Task Learning by Maximizing Statistical Dependence 通過最大化統計依賴性進行多任務學習
640.Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics 使用不確定性權衡場景幾何和語義損失的多任務學習
641.Multi-View Consistency as Supervisory Signal for Learning Shape and Pose Prediction 多視圖一致性作為學習形狀和姿勢預測的監督信號
642.Multi-View Harmonized Bilinear Network for 3D Object Recognition 用于3D對象識別的多視圖協調雙線性網絡
643.MX-LSTM: Mixing Tracklets and Vislets to Jointly Forecast Trajectories and Head Poses MX-LSTM：將小軌跡和小片段混合以共同預測軌跡和頭部姿勢
644.NAG: Network for Adversary Generation NAG：對手生成網絡
645.Natural and Effective Obfuscation by Head Inpainting 通過頭部繪畫進行自然而有效的混淆
646.NestedNet: Learning Nested Sparse Structures in Deep Neural Networks NestedNet：在深度神經網絡中學習嵌套的稀疏結構
647.Net2Vec: Quantifying and Explaining How Concepts Are Encoded by Filters in Deep Neural Networks Net2Vec：量化和解釋深度神經網絡中的過濾器如何編碼概念
648.Neural 3D Mesh Renderer 神經3D網格渲染器
649.Neural Baby Talk 神經嬰兒談話
650.Neural Kinematic Networks for Unsupervised Motion Retargetting 神經運動網絡的無監督運動重定向

論文概要

651.Neural Motifs: Scene Graph Parsing With Global Context 神經圖案：具有全局上下文的場景圖解析
652.NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning NeuralNetwork-Viterbi：弱監督視頻學習的框架
653.Neural Sign Language Translation 神經手語翻譯
654.Neural Style Transfer via Meta Networks 通過元網絡進行神經風格傳遞
655.NISP: Pruning Networks Using Neuron Importance Score Propagation NISP：使用神經元重要性分數傳播修剪網絡
656.Non-Blind Deblurring: Handling Kernel Uncertainty With CNNs 非盲去模糊：使用CNN處理內核不確定性
657.Nonlinear 3D Face Morphable Model 非線性3D人臉可變形模型
658.Non-Linear Temporal Subspace Representations for Activity Recognition 用于活動識別的非線性時間子空間表示
659.Nonlocal Low-Rank Tensor Factor Analysis for Image Restoration 用于圖像復原的非局部低秩張量因子分析
660.Non-Local Neural Networks 非局部神經網絡
661.Normalized Cut Loss for Weakly-Supervised CNN Segmentation 弱監督CNN分割的歸一化割損
662.Now You Shake Me: Towards Automatic 4D Cinema 現在，您讓我搖了搖：邁向自動4D電影院
663.OATM: Occlusion Aware Template Matching by Consensus Set Maximization OATM：通過共識集最大化來匹配遮擋感知模板
664.Object Referring in Videos With Language and Human Gaze 具有語言和人眼注視的視頻中的對象引用
665.Objects as Context for Detecting Their Semantic Parts 對象作為上下文來檢測其語義部分
666.Occluded Pedestrian Detection Through Guided Attention in CNNs 在CNN中通過引導注意力進行行人檢測
667.Occlusion-Aware Rolling Shutter Rectification of 3D Scenes 遮擋感知型3D場景的卷簾式快門矯正
668.Occlusion Aware Unsupervised Learning of Optical Flow 遮擋感知光流的無監督學習
669.OLE: Orthogonal Low-Rank Embedding - A Plug and Play Geometric Loss for Deep Learning OLE：正交低秩嵌入-深度學習的即插即用幾何損失
670.One-Shot Action Localization by Learning Sequence Matching Network 通過學習序列匹配網絡進行一鍵式動作定位
671.On the Convergence of PatchMatch and Its Variants 關于PatchMatch及其變體的收斂性
672.On the Duality Between Retinex and Image Dehazing Retinex與圖像去霧之間的對偶
673.On the Importance of Label Quality for Semantic Segmentation 標簽質量在語義分割中的重要性
674.On the Robustness of Semantic Segmentation Models to Adversarial Attacks 語義分割模型對對抗攻擊的魯棒性
675.Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition 光流引導功能：用于視頻動作識別的快速且魯棒的運動表示
676.Optimal Structured Light a La Carte 最佳結構燈點菜
677.Optimizing Filter Size in Convolutional Neural Networks for Facial Action Unit Recognition 卷積神經網絡中用于面部動作單元識別的濾波器大小優化
678.Optimizing Video Object Detection via a Scale-Time Lattice 通過比例時間格優化視頻對象檢測
679.Ordinal Depth Supervision for 3D Human Pose Estimation 3D人體姿勢估計的序數深度監督
680.PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning PackNet：通過迭代修剪將多個任務添加到單個網絡
681.PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing PAD-Net：多任務引導的預測和蒸餾網絡，用于同時深度估計和場景解析
682.PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup PairedCycleGAN：不對稱樣式轉移，用于涂抹和去除化妝
683.Parallel Attention: A Unified Framework for Visual Object Discovery Through Dialogs and Queries 并行注意：通過對話框和查詢發現可視對象的統一框架
684.Partially Shared Multi-Task Convolutional Neural Network With Local Constraint for Face Attribute Learning 具有局部約束的部分共享多任務卷積神經網絡用于人臉屬性學習
685.Partial Transfer Learning With Selective Adversarial Networks 選擇性對抗網絡的部分轉移學習
686.Path Aggregation Network for Instance Segmentation 用于實例分割的路徑聚合網絡
687.People, Penguins and Petri Dishes: Adapting Object Counting Models to New Visual Domains and Object Types Without Forgetting 人，企鵝和培養皿：在不忘記的情況下將對象計數模型適應新的可視域和對象類型
688.Person Re-Identification With Cascaded Pairwise Convolutions 級聯成對卷積的人員重新識別
689.Person Transfer GAN to Bridge Domain Gap for Person Re-Identification 人員轉移GAN到橋接域差距以進行人員重新識別
690.Perturbative Neural Networks 攝動神經網絡
691.PhaseNet for Video Frame Interpolation 用于視頻幀插值的PhaseNet
692.Photographic Text-to-Image Synthesis With a Hierarchically-Nested Adversarial Network 分層嵌套對抗網絡的攝影文本到圖像合成
693.Photometric Stereo in Participating Media Considering Shape-Dependent Forward Scatter 考慮形狀依賴性前向散射的參與介質中的光度立體
694.PiCANet: Learning Pixel-Wise Contextual Attention for Saliency Detection PiCANet：學習像素性上下文注意以進行顯著性檢測
695.PieAPP: Perceptual Image-Error Assessment Through Pairwise Preference PieAPP：通過成對偏好的感知圖像錯誤評估
696.Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling Pix3D：單圖像3D形狀建模的數據集和方法
697.Pixels, Voxels, and Views: A Study of Shape Representations for Single View 3D Object Shape Prediction 像素，體素和視圖：單視圖3D對象形狀預測的形狀表示研究
698.PIXOR: Real-Time 3D Object Detection From Point Clouds PIXOR：來自點云的實時3D對象檢測
699.Planar Shape Detection at Structural Scales 結構尺度的平面形狀檢測
700.PlaneNet: Piece-Wise Planar Reconstruction From a Single RGB Image PlaneNet：從單個RGB圖像進行明智的平面重建

論文概要

701.PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation PointFusion：用于3D邊界框估計的深度傳感器融合
702.PointGrid: A Deep Network for 3D Shape Understanding PointGrid：深入了解3D形狀的網絡
703.PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition PointNetVLAD：基于深度點云的大規模位置識別檢索
704.Pointwise Convolutional Neural Networks 點向卷積神經網絡
705.Polarimetric Dense Monocular SLAM 偏振密集單眼SLAM
706.PoseFlow: A Deep Motion Representation for Understanding Human Behaviors in Videos PoseFlow：用于理解視頻中人類行為的深度運動表示
707.Pose-Guided Photorealistic Face Rotation 姿勢引導的真實感人臉旋轉
708.pOSE: Pseudo Object Space Error for Initialization-Free Bundle Adjustment pOSE：用于無初始化捆綁調整的偽對象空間錯誤
709.Pose-Robust Face Recognition via Deep Residual Equivariant Mapping 基于深度殘差等變映射的姿勢魯棒人臉識別
710.PoseTrack: A Benchmark for Human Pose Estimation and Tracking PoseTrack：人體姿勢估計和跟蹤基準
711.Pose Transferrable Person Re-Identification 姿勢可轉移人員的重新識別
712.PoTion: Pose MoTion Representation for Action Recognition PoTion：用于動作識別的姿勢運動表示
713.PPFNet: Global Context Aware Local Features for Robust 3D Point Matching PPFNet：健壯的3D點匹配的全局上下文感知本地功能
714.Practical Block-Wise Neural Network Architecture Generation 實用的塊明智神經網絡架構生成
715.Preserving Semantic Relations for Zero-Shot Learning 保留語義關系以進行零射擊學習
716.Probabilistic Joint Face-Skull Modelling for Facial Reconstruction 面部重建的概率聯合面顱骨模型
717.Probabilistic Plant Modeling via Multi-View Image-to-Image Translation 通過多視圖圖像到圖像轉換的概率植物建模
718.Progressive Attention Guided Recurrent Network for Salient Object Detection 漸進式注意力引導循環網絡用于顯著物體檢測
719.Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection 用于RGB-D顯著目標檢測的漸進式互補感知融合網絡
720.Pseudo Mask Augmented Object Detection 偽蒙版增強對象檢測
721.Pulling Actions out of Context: Explicit Separation for Effective Combination 使動作脫離上下文：有效組合的顯式分離
722.PU-Net: Point Cloud Upsampling Network PU-Net：點云上采樣網絡
723.PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume PWC-Net：使用金字塔，翹曲和成本量的光流CNN
724.Pyramid Stereo Matching Network 金字塔立體匹配網絡
725.Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference 神經網絡的量化和訓練，以便進行有效的僅整數運算
726.Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation 完全卷積網絡的量化，用于精確的生物醫學圖像分割
727.Radially-Distorted Conjugate Translations 徑向變形的共軛翻譯
728.RayNet: Learning Volumetric 3D Reconstruction With Ray Potentials RayNet：使用射線勢學習體積3D重建
729.Real-Time Monocular Depth Estimation Using Synthetic Data With Domain Adaptation via Image Style Transfer 通過圖像樣式轉移使用具有域自適應的合成數據進行實時單眼深度估計
730.Real-Time Rotation-Invariant Face Detection With Progressive Calibration Networks 漸進式校準網絡的實時旋轉不變人臉檢測
731.Real-Time Seamless Single Shot 6D Object Pose Prediction 實時無縫單發6D對象姿態預測
732.Real-World Anomaly Detection in Surveillance Videos 監控視頻中的真實世界異常檢測
733.Real-World Repetition Estimation by Div, Grad and Curl 通過Div，Grad和Curl進行真實世界的重復估計
734.Recognize Actions by Disentangling Components of Dynamics 通過解開動力學的成分來識別動作
735.Recognizing Human Actions as the Evolution of Pose Estimation Maps 將人類行為識別為姿勢估計圖的演變
736.Reconstructing Thin Structures of Manifold Surfaces by Integrating Spatial Curves 通過積分空間曲線重建歧管表面的薄結構
737.Reconstruction Network for Video Captioning 視頻字幕重建網絡
738.Recovering Realistic Texture in Image Super-Resolution by Deep Spatial Feature Transform 通過深度空間特征變換在圖像超分辨率中恢復逼真的紋理
739.Recurrent Pixel Embedding for Instance Grouping 用于實例分組的遞歸像素嵌入
740.Recurrent Residual Module for Fast Inference in Videos 遞歸殘差模塊，可快速推斷視頻
741.Recurrent Saliency Transformation Network: Incorporating Multi-Stage Visual Cues for Small Organ Segmentation 循環顯著性轉換網絡：結合多階段視覺提示進行小器官分割
742.Recurrent Scene Parsing With Perspective Understanding in the Loop 循環場景解析與透視理解
743.Recurrent Slice Networks for 3D Segmentation of Point Clouds 用于點云3D分割的遞歸切片網絡
744.Referring Image Segmentation via Recurrent Refinement Networks 通過遞歸細化網絡引用圖像分割
745.Referring Relationships 推薦關系
746.Reflection Removal for Large-Scale 3D Point Clouds 大型3D點云的反射消除
747.Regularizing Deep Networks by Modeling and Predicting Label Structure 通過建模和預測標簽結構來規范化深層網絡
748.Regularizing RNNs for Caption Generation by Reconstructing the Past With the Present 通過重建過去與現在來規范RNN以生成字幕
749.Reinforcement Cutting-Agent Learning for Video Object Segmentation 用于視頻對象分割的增強切割代理學習
750.Relation Networks for Object Detection 用于對象檢測的關系網絡

論文概要

751.Representing and Learning High Dimensional Data With the Optimal Transport Map From a Probabilistic Viewpoint 從概率角度用最佳傳輸圖表示和學習高維數據
752.Repulsion Loss: Detecting Pedestrians in a Crowd 排斥力損失：檢測人群中的行人
753.Residual Dense Network for Image Super-Resolution 殘留密集網絡可實現圖像超分辨率
754.Residual Parameter Transfer for Deep Domain Adaptation 深度域適應的殘差參數傳遞
755.Resource Aware Person Re-Identification Across Multiple Resolutions 跨多種解決方案的資源感知人員重新識別
756.Rethinking Feature Distribution for Loss Functions in Image Classification 對圖像分類中損失函數的特征分布的重新思考
757.Rethinking the Faster R-CNN Architecture for Temporal Action Localization 重新思考用于時間動作本地化的更快的R-CNN架構
758.Revisiting Deep Intrinsic Image Decompositions 重新審視深度內在圖像分解
759.Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation 重訪擴張式卷積：一種用于弱監督和半監督語義分割的簡單方法
760.Revisiting Knowledge Transfer for Training Object Class Detectors 復習訓練對象類別檢測器的知識轉移
761.Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking 重溫牛津和巴黎：大型圖像檢索基準
762.Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects 回顧顯著對象檢測：多個顯著對象的同時檢測，排序和細分
763.Revisiting Video Saliency: A Large-Scale Benchmark and a New Model 回顧視頻顯著性：大規模基準和新模型
764.Reward Learning From Narrated Demonstrations 敘述式學習中的獎勵學習
765.Re-Weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation 無權域適應的加權加權對抗適應網絡
766.R-FCN-3000 at 30fps: Decoupling Detection and Classification R-FCN-3000的30fps：解耦檢測和分類
767.Ring Loss: Convex Feature Normalization for Face Recognition 環損：用于面部識別的凸特征歸一化
768.ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes ROAD：針對城市場景的語義分割的面向現實的適應
769.RoadTracer: Automatic Extraction of Road Networks From Aerial Images RoadTracer：從航拍圖像中自動提取路網
770.Robust Classification With Convolutional Prototype Learning 卷積原型學習的魯棒分類
771.Robust Depth Estimation From Auto Bracketed Images 通過自動包圍曝光圖像進行穩健的深度估計
772.Robust Facial Landmark Detection via a Fully-Convolutional Local-Global Context Network 通過全卷積局部全局上下文網絡進行魯棒的面部地標檢測
773.Robust Hough Transform Based 3D Reconstruction From Circular Light Fields 基于魯棒霍夫變換的圓形光場3D重構
774.Robust Physical-World Attacks on Deep Learning Visual Classification 深度學習視覺分類的強大物理世界攻擊
775.Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework CNN框架中針對雨水去除的強大視頻內容對齊和補償
776.Rolling Shutter and Radial Distortion Are Features for High Frame Rate Multi-Camera Tracking 滾動快門和徑向失真是高幀率多攝像機跟蹤的功能
777.Rotation Averaging and Strong Duality 旋轉平均和強對偶
778.RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews From Unsupervised Viewpoints RotationNet：使用來自無監督觀點的多視圖進行聯合對象分類和姿勢估計
779.Rotation-Sensitive Regression for Oriented Scene Text Detection 面向場景文本檢測的旋轉敏感回歸
780.Salience Guided Depth Calibration for Perceptually Optimized Compressive Light Field 3D Display 針對感知優化的壓縮光場3D顯示的顯著性深度深度校準
781.Salient Object Detection Driven by Fixation Prediction 固定預測驅動的顯著物體檢測
782.SBNet: Sparse Blocks Network for Fast Inference SBNet：稀疏塊網絡以進行快速推理
783.Scalable and Effective Deep CCA via Soft Decorrelation 通過軟解相關可擴展且有效的深度CCA
784.Scalable Dense Non-Rigid Structure-From-Motion: A Grassmannian Perspective 運動可伸縮的密集非剛性結構：格拉斯曼觀點
785.Scale-Recurrent Network for Deep Image Deblurring 用于深度圖像去模糊的縮放遞歸網絡
786.Scale-Transferrable Object Detection 可縮放的目標檢測
787.ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans ScanComplete：3D掃描的大規模場景完成和語義分割
788.SeedNet: Automatic Seed Generation With Deep Reinforcement Learning for Robust Interactive Segmentation SeedNet：具有深度強化學習功能的自動種子生成，可實現可靠的交互式細分
789.Seeing Small Faces From Robust Anchor’s Perspective 從穩固的錨點角度看小臉
790.Seeing Temporal Modulation of Lights From Standard Cameras 從標準相機看到光的時間調制
791.Seeing Voices and Hearing Faces: Cross-Modal Biometric Matching 看到聲音和聽覺的面孔：跨模態生物特征匹配
792.SeGAN: Segmenting and Generating the Invisible SeGAN：分割和生成不可見
793.Self-Calibrating Polarising Radiometric Calibration 自校準偏振輻射校準
794.Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval 自我監督的對抗式哈希網絡，用于跨模態檢索
795.Self-Supervised Feature Learning by Learning to Spot Artifacts 通過學習發現偽像進行自我監督的特征學習
796.Self-Supervised Learning of Geometrically Stable Features Through Probabilistic Introspection 通過概率自省對幾何穩定特征進行自我監督學習
797.Self-Supervised Multi-Level Face Model Learning for Monocular Reconstruction at Over 250 Hz 用于250 Hz以上單眼重建的自監督多級面部模型學習
798.Semantic Video Segmentation by Gated Recurrent Flow Propagation 門控循環流傳播的語義視頻分割
799.Semantic Visual Localization 語義視覺本地化
800.Semi-Parametric Image Synthesis 半參數圖像合成

論文概要

801.SemStyle: Learning to Generate Stylised Image Captions Using Unaligned Text SemStyle：學習使用未對齊的文本生成樣式化的圖像標題
802.Separating Self-Expression and Visual Content in Hashtag Supervision 在標簽監督中分離自我表達和視覺內容
803.Separating Style and Content for Generalized Style Transfer 分隔樣式和內容以進行廣義樣式轉移
804.SfSNet: Learning Shape, Reflectance and Illuminance of Faces `in the Wild’ SfSNet：學習“野外”面孔的形狀，反射率和照度
805.SGAN: An Alternative Training of Generative Adversarial Networks SGAN：生成對抗網絡的替代培訓
806.SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation SGPN：3D點云實例細分的相似性組建議網絡
807.Shape From Shading Through Shape Evolution 從陰影到形狀進化
808.Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions 移位：零卷積，零參數替代空間卷積
809.Show Me a Story: Towards Coherent Neural Story Illustration 告訴我一個故事：邁向連貫的神經故事插圖
810.ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices ShuffleNet：用于移動設備的極其高效的卷積神經網絡
811.Sim2Real Viewpoint Invariant Visual Servoing by Recurrent Control 通過遞歸控制實現Sim2Real Viewpoint不變視覺伺服
812.Single Image Dehazing via Conditional Generative Adversarial Network 通過條件生成對抗網絡進行單圖像去霧
813.Single-Image Depth Estimation Based on Fourier Domain Analysis 基于傅立葉域分析的單圖像深度估計
814.Single Image Reflection Separation With Perceptual Losses 具有感知損失的單圖像反射分離
815.Single-Shot Object Detection With Enriched Semantics 具有豐富語義的單發目標檢測
816.Single-Shot Refinement Neural Network for Object Detection 用于目標檢測的單發細化神經網絡
817.Single View Stereo Matching 單視圖立體聲匹配
818.SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation SINT ++：通過對抗性積極實例生成進行可靠的視覺跟蹤
819.Sketch-a-Classifier: Sketch-Based Photo Classifier Generation 草圖分類器：基于草圖的照片分類器生成
820.SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval SketchMate：數以百萬計的人類草圖檢索的深度哈希
821.SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis SketchyGAN：向圖像合成中逼真的素描
822.Sliced Wasserstein Distance for Learning Gaussian Mixture Models 切片Wasserstein距離用于學習高斯混合模型
823.Smooth Neighbors on Teacher Graphs for Semi-Supervised Learning 教師圖上的平滑鄰居用于半監督學習
824.SobolevFusion: 3D Reconstruction of Scenes Undergoing Free Non-Rigid Motion SobolevFusion：進行自由非剛性運動的場景的3D重建
825.Soccer on Your Tabletop 桌上足球
826.Social GAN: Socially Acceptable Trajectories With Generative Adversarial Networks 社交GAN：具有生成對抗網絡的社交可接受軌跡
827.Solving the Perspective-2-Point Problem for Flying-Camera Photo Composition 解決飛行相機照片構圖的透視2點問題
828.SO-Net: Self-Organizing Network for Point Cloud Analysis SO-Net：用于點云分析的自組織網絡
829.SoS-RSC: A Sum-of-Squares Polynomial Approach to Robustifying Subspace Clustering Algorithms SoS-RSC：一種平方和多項式方法，用于魯棒子空間聚類算法
830.Sparse Photometric 3D Face Reconstruction Guided by Morphable Models 可變形模型指導的稀疏光度3D人臉重建
831.Sparse, Smart Contours to Represent and Edit Images 稀疏的智能輪廓來表示和編輯圖像
832.Spatially-Adaptive Filter Units for Deep Neural Networks 用于深度神經網絡的空間自適應濾波器單元
833.SPLATNet: Sparse Lattice Networks for Point Cloud Processing SPLATNet：用于點云處理的稀疏格子網絡
834.SplineCNN: Fast Geometric Deep Learning With Continuous B-Spline Kernels SplineCNN：具有連續B樣條曲線核的快速幾何深度學習
835.Spline Error Weighting for Robust Visual-Inertial Fusion 樣條誤差加權，實現穩健的視覺慣性融合
836.Squeeze-and-Excitation Networks 擠壓和激勵網絡
837.SSNet: Scale Selection Network for Online 3D Action Prediction SSNet：在線3D動作預測的量表選擇網絡
838.Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal 聯合學習陰影檢測和陰影去除的堆疊條件生成對抗網絡
839.Stacked Latent Attention for Multimodal Reasoning 多模態推理的堆疊潛在注意力
840.StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation StarGAN：用于多域圖像到圖像翻譯的統一生成對抗網絡
841.Statistical Tomography of Microscopic Life 微觀生命的統計斷層掃描
842.Stereoscopic Neural Style Transfer 立體神經風格轉換
843.ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing ST-GAN：用于圖像合成的空間變壓器生成對抗網絡
844.Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks 卷積網絡中用于成本可調推斷和改進正則化的隨機下采樣
845.Stochastic Variational Inference With Gradient Linearization 梯度線性化的隨機變分推斷
846.Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation 結構化注意力導向的卷積神經場用于單眼深度估計
847.Structured Set Matching Networks for One-Shot Part Labeling 一站式零件貼標的結構化集合匹配網絡
848.Structured Uncertainty Prediction Networks 結構化不確定性預測網絡
849.Structure From Recurrent Motion: From Rigidity to Recurrency 循環運動的結構：從剛度到遞歸
850.Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships 結構推斷網：使用場景級上下文和實例級關系的對象檢測

論文概要

851.Structure Preserving Video Prediction 保留結構的視頻預測
852.Style Aggregated Network for Facial Landmark Detection 用于面部地標檢測的樣式聚合網絡
853.Super-FAN: Integrated Facial Landmark Localization and Super-Resolution of Real-World Low Resolution Faces in Arbitrary Poses With GANs Super-FAN：具有GAN的任意姿勢中的集成面部地標定位和真實世界低分辨率面孔的超分辨率
854.Super-Resolving Very Low-Resolution Face Images With Supplementary Attributes 具有補充屬性的超分辨率超低分辨率人臉圖像
855.Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation Super SloMo：用于視頻插值的多個中間幀的高質量估計
856.Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors 注冊監督：一種無監督的方法來提高面部地標檢測器的精度
857.Surface Networks 地面網絡
858.SurfConv: Bridging 3D and 2D Convolution for RGBD Images SurfConv：橋接RGBD圖像的3D和2D卷積
859.Synthesizing Images of Humans in Unseen Poses 在看不見的姿勢中合成人的形象
860.SYQ: Learning Symmetric Quantization for Efficient Deep Neural Networks SYQ：為高效的深度神經網絡學習對稱量化
861.Tagging Like Humans: Diverse and Distinct Image Annotation 像人類一樣標記：多樣化且獨特的圖像注釋
862.Tags2Parts: Discovering Semantic Regions From Shape Tags 標簽2部分：從形狀標簽中發現語義區域
863.Tangent Convolutions for Dense Prediction in 3D 切線卷積用于3D密集預測
864.Taskonomy: Disentangling Task Transfer Learning Taskonomy：解開任務轉移學習
865.Teaching Categories to Human Learners With Visual Explanations 用視覺解釋向人類學習者教授類別
866.Tell Me Where to Look: Guided Attention Inference Network 告訴我在哪里看：引導注意推理網絡
867.Temporal Deformable Residual Networks for Action Segmentation in Videos 視頻中的時間分段的時間可變形殘差網絡
868.Temporal Hallucinating for Action Recognition With Few Still Images 時間幻覺的動作識別很少有靜止圖像
869.Tensorize, Factorize and Regularize: Robust Visual Relationship Learning 張量化，分解和正則化：穩健的視覺關系學習
870.Textbook Question Answering Under Instructor Guidance With Memory Networks 記憶網絡下教師指導下的教科書問答
871.TextureGAN: Controlling Deep Image Synthesis With Texture Patches TextureGAN：使用紋理補丁控制深度圖像合成
872.Texture Mapping for 3D Reconstruction With RGB-D Sensor 使用RGB-D傳感器進行3D重建的紋理映射
873.The Best of Both Worlds: Combining CNNs and Geometric Constraints for Hierarchical Motion Segmentation 兩全其美：結合CNN和幾何約束進行分層運動分割
874.The INaturalist Species Classification and Detection Dataset 非自然物種分類和檢測數據集
875.The LovaSz-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks LovaSz-Softmax損失：神經網絡交叉口聯合測量的優化的可替代替代方法
876.The Perception-Distortion Tradeoff 感知失真權衡
877.The Power of Ensembles for Active Learning in Image Classification 集成在圖像分類中主動學習的力量
878.The Unreasonable Effectiveness of Deep Features as a Perceptual Metric 深度特征作為感知指標的不合理有效性
879.Thoracic Disease Identification and Localization With Limited Supervision 有限監督下的胸腔疾病鑒定和定位
880.Through-Wall Human Pose Estimation Using Radio Signals 使用無線電信號的全程人體姿態估計
881.TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-Rays TieNet：普通胸部疾病分類和胸部X光報告的文本圖像嵌入網絡
882.Time-Resolved Light Transport Decomposition for Thermal Photometric Stereo 熱光度立體的時間分辨光傳輸分解
883.Tips and Tricks for Visual Question Answering: Learnings From the 2017 Challenge 視覺問題解答的提示和技巧：2017年挑戰的經驗教訓
884.TOM-Net: Learning Transparent Object Matting From a Single Image TOM-Net：從單個圖像學習透明對象遮罩
885.Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies 總捕獲：用于跟蹤面部，手部和身體的3D變形模型
886.Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoning 對駕駛場景的理解：學習駕駛員行為和因果推理的數據集
887.Towards a Mathematical Understanding of the Difficulty in Learning With Feedforward Neural Networks 對前饋神經網絡學習困難的數學理解
888.Towards Dense Object Tracking in a 2D Honeybee Hive 在2D蜜蜂蜂巢中實現密集對象跟蹤
889.Towards Effective Low-Bitwidth Convolutional Neural Networks 邁向有效的低位寬卷積神經網絡
890.Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization 通過迭代矩陣平方根歸一化來更快地訓練全局協方差合并網絡
891.Towards High Performance Video Object Detection 邁向高性能視頻目標檢測
892.Towards Human-Machine Cooperation: Self-Supervised Sample Mining for Object Detection 走向人機合作：用于對象檢測的自監督樣本挖掘
893.Towards Open-Set Identity Preserving Face Synthesis 邁向開放式身份保留人臉綜合
894.Towards Pose Invariant Face Recognition in the Wild 走向野外姿勢不變的人臉識別
895.Towards Universal Representation for Unseen Action Recognition 走向通用表示以實現看不見的動作識別
896.Tracking Multiple Objects Outside the Line of Sight Using Speckle Imaging 使用散斑成像跟蹤視線外的多個物體
897.Transductive Unbiased Embedding for Zero-Shot Learning 零射學習的傳導無偏嵌入
898.Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification 可轉移的聯合屬性-身份深度學習，用于無監督人員重新識別
899.Translating and Segmenting Multimodal Medical Volumes With Cycle- and Shape-Consistency Generative Adversarial Network 使用周期和形狀一致性生成對抗網絡對多峰醫療量進行翻譯和分段
900.Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning 設計上的透明度：彌合視覺推理中性能和可解釋性之間的差距

論文概要

901.Trapping Light for Time of Flight 飛行時間的陷阱燈
902.Triplet-Center Loss for Multi-View 3D Object Retrieval 多視圖3D對象檢索的三重態中心損失
903.Trust Your Model: Light Field Depth Estimation With Inline Occlusion Handling 信任您的模型：內聯遮擋處理的光場深度估計
904.Two Can Play This Game: Visual Dialog With Discriminative Question Generation and Answering 兩個人可以玩這個游戲：具有判別性問題生成和回答的可視對話框
905.Two-Step Quantization for Low-Bit Neural Networks 低位神經網絡的兩步量化
906.Two-Stream Convolutional Networks for Dynamic Texture Synthesis 用于動態紋理合成的兩流卷積網絡
907.Uncalibrated Photometric Stereo Under Natural Illumination 自然照明下未經校準的測光立體
908.Unifying Identification and Context Learning for Person Recognition 統一身份識別和上下文學習以實現人的識別
909.Universal Denoising Networks : A Novel CNN Architecture for Image Denoising 通用降噪網絡：一種用于圖像降噪的新型CNN架構
910.Unsupervised Correlation Analysis 無監督相關分析
911.Unsupervised Cross-Dataset Person Re-Identification by Transfer Learning of Spatial-Temporal Patterns 通過時空模式的轉移學習對無監督的跨數據集人員進行重新識別
912.Unsupervised Deep Generative Adversarial Hashing Network 無監督的深度生成對抗式哈希網絡
913.Unsupervised Discovery of Object Landmarks as Structural Representations 無監督地發現對象地標作為結構表示形式
914.Unsupervised Domain Adaptation With Similarity Learning 具有相似性學習的無監督域自適應
915.Unsupervised Feature Learning via Non-Parametric Instance Discrimination 通過非參數實例區分進行無監督特征學習
916.Unsupervised Learning and Segmentation of Complex Activities From Video 視頻的無監督學習和復雜活動細分
917.Unsupervised Learning of Depth and Ego-Motion From Monocular Video Using 3D Geometric Constraints 使用3D幾何約束從單眼視頻進行無監督的深度和自我運動學習
918.Unsupervised Learning of Monocular Depth Estimation and Visual Odometry With Deep Feature Reconstruction 具有深度特征重構的單眼深度估計和視覺測程的無監督學習
919.Unsupervised Person Image Synthesis in Arbitrary Poses 任意姿勢下的無人監督圖像合成
920.Unsupervised Sparse Dirichlet-Net for Hyperspectral Image Super-Resolution 無監督稀疏Dirichlet-Net用于高光譜圖像超分辨率
921.Unsupervised Textual Grounding: Linking Words to Image Concepts 無監督的文本基礎：將單詞鏈接到圖像概念
922.Unsupervised Training for 3D Morphable Model Regression 3D變形模型回歸的無監督訓練
923.UV-GAN: Adversarial Facial UV Map Completion for Pose-Invariant Face Recognition UV-GAN：對抗性面部UV貼圖完成，用于姿勢不變的面部識別
924.V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation From a Single Depth Map V2V-PoseNet：用于從單個深度圖進行精確3D手和人姿估計的體素到體素預測網絡
925.Variational Autoencoders for Deforming 3D Mesh Models 變形3D網格模型的變體自動編碼器
926.Very Large-Scale Global SfM by Distributed Motion Averaging 分布式運動平均的超大規模全球SfM
927.Video Based Reconstruction of 3D People Models 基于視頻的3D人模型重構
928.Video Captioning via Hierarchical Reinforcement Learning 通過分層強化學習進行視頻字幕
929.Video Person Re-Identification With Competitive Snippet-Similarity Aggregation and Co-Attentive Snippet Embedding 具有競爭性摘要相似性聚合和共同關注性摘要嵌入的視頻人重新識別
930.Video Rain Streak Removal by Multiscale Convolutional Sparse Coding 多尺度卷積稀疏編碼去除視頻雨紋
931.Video Representation Learning Using Discriminative Pooling 使用區分池的視頻表示學習
932.View Extrapolation of Human Body From a Single Image 從單個圖像查看人體外推
933.Viewpoint-Aware Attentive Multi-View Inference for Vehicle Re-Identification 用于車輛重新識別的具有視點意識的多視圖推理
934.Viewpoint-Aware Video Summarization 視點感知視頻摘要
935.VirtualHome: Simulating Household Activities via Programs VirtualHome：通過程序模擬家庭活動
936.Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments 視覺和語言導航：解釋真實環境中的視覺地面導航說明
937.Visual Feature Attribution Using Wasserstein GANs 使用Wasserstein GAN的視覺特征歸因
938.Visual Grounding via Accumulated Attention 通過累積注意力進行視覺接地
939.Visual Question Answering With Memory-Augmented Networks 內存增強網絡的視覺問題解答
940.Visual Question Generation as Dual Task of Visual Question Answering 視覺問題生成是視覺問題回答的雙重任務
941.Visual Question Reasoning on General Dependency Tree 一般依賴樹上的視覺問題推理
942.Visual to Sound: Generating Natural Sound for Videos in the Wild 視覺到聲音：為野外視頻生成自然聲音
943.VITAL: VIsual Tracking via Adversarial Learning VITAL：通過對抗性學習進行視覺跟蹤
944.VITON: An Image-Based Virtual Try-On Network VITON：基于映像的虛擬試穿網絡
945.VizWiz Grand Challenge: Answering Visual Questions From Blind People VizWiz大挑戰：回答盲人的視覺問題
946.VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection VoxelNet：基于點云的3D對象檢測的端到端學習
947.W2F: A Weakly-Supervised to Fully-Supervised Framework for Object Detection W2F：弱監督到完全監督的對象檢測框架
948.Wasserstein Introspective Neural Networks Wasserstein自省神經網絡
949.Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer 通過姿勢指導的知識轉移進行弱而半監督的人體部位解析
950.Weakly Supervised Action Localization by Sparse Temporal Pooling Network 稀疏時間池網絡對行為的弱監督

論文概要

951.Weakly-Supervised Action Segmentation With Iterative Soft Boundary Assignment 具有迭代軟邊界分配的弱監督動作細分
952.Weakly Supervised Coupled Networks for Visual Sentiment Analysis 弱監督耦合網絡，用于視覺情感分析
953.Weakly-Supervised Deep Convolutional Neural Network Learning for Facial Action Unit Intensity Estimation 弱監督深度卷積神經網絡學習，用于面部動作單元強度估計
954.Weakly Supervised Facial Action Unit Recognition Through Adversarial Training 通過對抗訓練對面部動作單元識別進行監督不足
955.Weakly Supervised Instance Segmentation Using Class Peak Response 使用類峰值響應的弱監督實例分割
956.Weakly Supervised Learning of Single-Cell Feature Embeddings 單細胞特征嵌入的弱監督學習
957.Weakly Supervised Phrase Localization With Multi-Scale Anchored Transformer Network 多尺度錨定變壓器網絡的弱監督短語定位
958.Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features 通過迭代挖掘常見對象特征的弱監督語義分割
959.Weakly-Supervised Semantic Segmentation Network With Deep Seeded Region Growing 具有深度種子區域增長的弱監督語義分割網絡
960.Webly Supervised Learning Meets Zero-Shot Learning: A Hybrid Approach for Fine-Grained Classification 網上監督學習與零射擊學習：精細分類的混合方法
961.What Do Deep Networks Like to See? 深度網絡喜歡看什么？
962.What Have We Learned From Deep Representations for Action Recognition? 我們從用于動作識別的深度表示中學到了什么？
963.What Makes a Video a Video: Analyzing Temporal Information in Video Understanding Models and Datasets 是什么使視頻成為視頻：分析視頻中的時間信息了解模型和數據集
964.When Will You Do What? - Anticipating Temporal Occurrences of Activities 您什么時候會做什么？ -預期活動的臨時發生
965.Where and Why Are They Looking? Jointly Inferring Human Attention and Intentions in Complex Tasks 他們在哪里看，為什么看？共同推斷人類的注意力和復雜任務中的意圖
966.Who Let the Dogs Out? Modeling Dog Behavior From Visual Data 誰讓狗出去了？根據視覺數據模擬狗的行為
967.Who’s Better? Who’s Best? Pairwise Deep Ranking for Skill Determination 誰更好？誰最好成對確定技能的深度排名
968.Wide Compression: Tensor Ring Nets 寬壓縮：張量環網
969.WILDTRACK: A Multi-Camera HD Dataset for Dense Unscripted Pedestrian Detection WILDTRACK：用于密集無腳本行人檢測的多攝像機高清數據集
970.Wing Loss for Robust Facial Landmark Localisation With Convolutional Neural Networks 用卷積神經網絡進行穩健的人臉地標定位的機翼損失
971.Wrapped Gaussian Process Regression on Riemannian Manifolds 黎曼流形上的包裹高斯過程回歸
972.xUnit: Learning a Spatial Activation Function for Efficient Image Restoration xUnit：學習空間激活功能以進行有效的圖像恢復
973.Zero-Shot Kernel Learning 零射內核學習
974.Zero-Shot Recognition via Semantic Embeddings and Knowledge Graphs 通過語義嵌入和知識圖進行零散識別
975.Zero-Shot Sketch-Image Hashing 零射素描圖像散列
976.“Zero-Shot” Super-Resolution Using Deep Internal Learning 使用深度內部學習的“零射擊”超分辨率
977.Zero-Shot Visual Recognition Using Semantics-Preserving Adversarial Embedding Networks 保留語義對抗性嵌入網絡的零射視覺識別
978.Zigzag Learning for Weakly Supervised Object Detection 鋸齒形學習用于弱監督對象檢測
979.Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains 縮放和學習：將深度立體聲匹配推廣到新穎領域

總結

以上是生活随笔為你收集整理的（十：2020.08.28）CVPR 2018 追踪之论文纲要（译）的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。