ICCV 2019 accepted papers on Video
104 of the 1,075 papers accepted at ICCV 2019 (9.7%) are on Video, compared with 15.1% at ICCV 2017. They fall into 4 topics.
See ICCV 2019 in the interactive map
Submitting to ICCV? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Video segmentation and tracking · 52 papers
- Video Object Segmentation Using Space-Time Memory Networks (810 citations)
- Video Instance Segmentation (541 citations)
- Anomaly Detection in Video Sequence With Appearance-Motion Correspondence (490 citations)
- End-to-End Learning of Representations for Asynchronous Event-Based Data (424 citations)
- Remote Heart Rate Measurement From Highly Compressed Facial Videos: An End-to-End Deep Learning Solution With Video Enhancement (361 citations)
- Seeing Motion in the Dark (321 citations)
- Progressive Fusion Video Super-Resolution Network via Exploiting Non-Local Spatio-Temporal Correlations (316 citations)
- Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks (312 citations)
- Global-Local Temporal Representations for Video Person Re-Identification (279 citations)
- RANet: Ranking Attention Network for Fast Video Object Segmentation (248 citations)
- Learned Video Compression (241 citations)
- Video Compression With Rate-Distortion Autoencoders (236 citations)
and 40 more in the interactive map.
Action recognition · 34 papers
- SlowFast Networks for Video Recognition (4,245 citations)
- VideoBERT: A Joint Model for Video and Language Representation Learning (1,265 citations)
- BMN: Boundary-Matching Network for Temporal Action Proposal Generation (728 citations)
- STM: SpatioTemporal and Motion Encoding for Action Recognition (503 citations)
- HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization (293 citations)
- SCSampler: Sampling Salient Clips From Video for Efficient Action Recognition (235 citations)
- Drive&Act: A Multi-Modal Dataset for Fine-Grained Driver Behavior Recognition in Autonomous Vehicles (215 citations)
- Temporal Recurrent Networks for Online Action Detection (212 citations)
- Toyota Smarthome: Real-World Activities of Daily Living (196 citations)
- Weakly-Supervised Action Localization With Background Modeling (186 citations)
- What Would You Expect? Anticipating Egocentric Actions With Rolling-Unrolling LSTMs and Modality Attention (183 citations)
- 3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization (181 citations)
and 22 more in the interactive map.
Video-language understanding · 13 papers
- TSM: Temporal Shift Module for Efficient Video Understanding (2,227 citations)
- HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips (1,045 citations)
- VaTeX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research (536 citations)
- Controllable Video Captioning With POS Sequence Guidance Based on Gated Fusion Network (201 citations)
- Understanding Human Gaze Communication by Spatio-Temporal Graph Reasoning (137 citations)
- Joint Syntax Representation Learning and Visual Cue Translation for Video Captioning (99 citations)
- Asymmetric Cross-Guided Attention Network for Actor and Action Video Segmentation From Natural Language Query (90 citations)
- ViSiL: Fine-Grained Spatio-Temporal Video Similarity Learning (86 citations)
- A Graph-Based Framework to Bridge Movies and Synopses (57 citations)
- SVD: A Large-Scale Short Video Dataset for Near-Duplicate Video Retrieval (53 citations)
- Neighborhood Preserving Hashing for Scalable Video Retrieval (49 citations)
- VideoMem: Constructing, Analyzing, Predicting Short-Term and Long-Term Video Memorability (45 citations)
and 1 more in the interactive map.
Video generation · 5 papers
- Everybody Dance Now (806 citations)
- Live Face De-Identification in Video (158 citations)
- Talking With Hands 16.2M: A Large-Scale Dataset of Synchronized Body-Finger Motion and Audio for Conversational Motion Analysis and Synthesis (80 citations)
- Point-to-Point Video Generation (23 citations)
- Hiding Video in Audio via Reversible Generative Models (16 citations)
