CVPR 2020 accepted papers on Video
119 of the 1,467 papers accepted at CVPR 2020 (8.1%) are on Video, compared with 9.0% at CVPR 2019. They fall into 4 topics.
See CVPR 2020 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
- BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning (2,481 citations)
- Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics (1,725 citations)
- X3D: Expanding Architectures for Efficient Video Recognition (1,252 citations)
- Learning Memory-Guided Normality for Anomaly Detection (933 citations)
- TDAN: Temporally-Deformable Alignment Network for Video Super-Resolution (616 citations)
- DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection (579 citations)
- Softmax Splatting for Video Frame Interpolation (395 citations)
- Central Similarity Quantization for Efficient Image and Video Retrieval (387 citations)
- Scale-Space Flow for End-to-End Optimized Video Compression (316 citations)
- Disentangling Physical Dynamics From Unknown Factors for Unsupervised Video Prediction (312 citations)
- FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation (283 citations)
- AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation (281 citations)
and 50 more in the interactive map.
Action recognition · 40 papers
- Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition (655 citations)
- End-to-End Learning of Visual Representations From Uncurated Instructional Videos (595 citations)
- GaitPart: Temporal Part-Based Model for Gait Recognition (584 citations)
- TEA: Temporal Excitation and Aggregation for Action Recognition (570 citations)
- G-TAD: Sub-Graph Localization for Temporal Action Detection (489 citations)
- Temporal Pyramid Network for Action Recognition (469 citations)
- FineGym: A Hierarchical Video Dataset for Fine-Grained Action Understanding (338 citations)
- Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs (309 citations)
- Few-Shot Video Classification via Temporal Alignment (273 citations)
- Listen to Look: Action Recognition by Previewing Audio (269 citations)
- SpeedNet: Learning the Speediness in Videos (248 citations)
- Gate-Shift Networks for Video Action Recognition (200 citations)
and 28 more in the interactive map.
Video-language understanding · 15 papers
- ActBERT: Learning Global-Local Video-Text Representations (412 citations)
- Object Relational Graph With Teacher-Recommended Learning for Video Captioning (328 citations)
- Dense Regression Network for Video Grounding (303 citations)
- Local-Global Video-Text Interactions for Temporal Grounding (302 citations)
- Spatio-Temporal Graph for Video Captioning With Knowledge Distillation (265 citations)
- Hierarchical Conditional Relation Networks for Video Question Answering (262 citations)
- Syntax-Aware Action Targeting for Video Captioning (197 citations)
- Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences (108 citations)
- Violin: A Large-Scale Dataset for Video-and-Language Inference (60 citations)
- Visual-Textual Capsule Routing for Text-Based Video Segmentation (58 citations)
- Video Object Grounding Using Semantic Roles in Language Description (40 citations)
- Large Scale Video Representation Learning via Relational Graph Clustering (17 citations)
and 3 more in the interactive map.
Video generation · 2 papers
- G3AN: Disentangling Appearance and Motion for Video Generation (83 citations)
- Non-Adversarial Video Synthesis With Learned Priors (16 citations)
