CVPR 2019 accepted papers on Video
117 of the 1,294 papers accepted at CVPR 2019 (9.0%) are on Video, compared with 10.9% at CVPR 2018. They fall into 4 topics.
See CVPR 2019 in the interactive map
Submitting to CVPR? 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 · 62 papers
- DVC: An End-To-End Deep Video Compression Framework (744 citations)
- Depth-Aware Video Frame Interpolation (577 citations)
- Recurrent Back-Projection Network for Video Super-Resolution (577 citations)
- Unsupervised Event-Based Learning of Optical Flow, Depth, and Egomotion (574 citations)
- Learning 3D Human Dynamics From Video (563 citations)
- See More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese Networks (533 citations)
- Learning Correspondence From the Cycle-Consistency of Time (479 citations)
- FEELVOS: Fast End-To-End Embedding Learning for Video Object Segmentation (463 citations)
- Events-To-Video: Bringing Modern Computer Vision to Event Cameras (428 citations)
- Animating Arbitrary Objects via Deep Motion Transfer (373 citations)
- Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos (340 citations)
- Bringing a Blurry Frame Alive at High Frame-Rate With an Event Camera (304 citations)
and 50 more in the interactive map.
Action recognition · 38 papers
- An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition (945 citations)
- MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation (685 citations)
- Self-Supervised Spatiotemporal Learning via Video Clip Order Prediction (446 citations)
- Gaussian Temporal Awareness Networks for Action Localization (390 citations)
- Large-Scale Weakly-Supervised Pre-Training for Video Action Recognition (304 citations)
- MARS: Motion-Augmented RGB Stream for Action Recognition (295 citations)
- Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization (267 citations)
- Temporal Cycle-Consistency Learning (257 citations)
- COIN: A Large-Scale Dataset for Comprehensive Instructional Video Analysis (256 citations)
- Timeception for Complex Action Recognition (238 citations)
- AdaFrame: Adaptive Frame Selection for Fast Video Recognition (232 citations)
- Multi-Granularity Generator for Temporal Action Proposal (227 citations)
and 26 more in the interactive map.
Video-language understanding · 15 papers
- Long-Term Feature Banks for Detailed Video Understanding (461 citations)
- MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment (357 citations)
- Dual Encoding for Zero-Example Video Retrieval (301 citations)
- Memory-Attended Recurrent Network for Video Captioning (249 citations)
- Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning (243 citations)
- Weakly Supervised Video Moment Retrieval From Text Queries (219 citations)
- Grounded Video Description (201 citations)
- Object-Aware Aggregation With Bidirectional Temporal Graph for Video Captioning (188 citations)
- Audio Visual Scene-Aware Dialog (178 citations)
- Streamlined Dense Video Captioning (159 citations)
- Video Relationship Reasoning Using Gated Spatio-Temporal Energy Graph (99 citations)
- Adversarial Inference for Multi-Sentence Video Description (97 citations)
and 3 more in the interactive map.
Video generation · 2 papers
- Hierarchical Cross-Modal Talking Face Generation With Dynamic Pixel-Wise Loss (440 citations)
- Video Generation From Single Semantic Label Map (99 citations)
