| FineAction: A Fine-Grained Video Dataset for Temporal Action Localization | May 24, 2021 | Action DetectionAction Localization | CodeCode Available | 1 |
| VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding | May 20, 2021 | Action SegmentationLanguage Modeling | —Unverified | 0 |
| NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions | May 18, 2021 | Question AnsweringVideo Question Answering | CodeCode Available | 1 |
| MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions | May 16, 2021 | Action DetectionAction Localization | CodeCode Available | 1 |
| Relation-aware Hierarchical Attention Framework for Video Question Answering | May 13, 2021 | Question AnsweringRelation | CodeCode Available | 0 |
| Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions | May 10, 2021 | Contrastive LearningRetrieval | —Unverified | 0 |
| Stochastic Image-to-Video Synthesis using cINNs | May 10, 2021 | DiversityVideo Understanding | CodeCode Available | 1 |
| FrameExit: Conditional Early Exiting for Efficient Video Recognition | Apr 27, 2021 | Video RecognitionVideo Understanding | CodeCode Available | 1 |
| Skimming and Scanning for Untrimmed Video Action Recognition | Apr 21, 2021 | Action RecognitionTemporal Action Localization | —Unverified | 0 |
| Temporal Query Networks for Fine-grained Video Understanding | Apr 19, 2021 | Action ClassificationAction Recognition | —Unverified | 0 |
| Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting | Apr 19, 2021 | Action SpottingCamera Calibration | —Unverified | 0 |
| CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval | Apr 18, 2021 | RetrievalText Retrieval | CodeCode Available | 1 |
| Temporally smooth online action detection using cycle-consistent future anticipation | Apr 16, 2021 | Action DetectionAutonomous Driving | CodeCode Available | 0 |
| Adaptive Intermediate Representations for Video Understanding | Apr 14, 2021 | Action ClassificationOptical Flow Estimation | —Unverified | 0 |
| Crossover Learning for Fast Online Video Instance Segmentation | Apr 13, 2021 | Instance SegmentationSemantic Segmentation | CodeCode Available | 1 |
| Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation | Apr 10, 2021 | Objectobject-detection | —Unverified | 0 |
| FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation Framework | Apr 9, 2021 | Language ModellingMultiple-choice | CodeCode Available | 0 |
| TubeR: Tubelet Transformer for Video Action Detection | Apr 2, 2021 | Action ClassificationAction Detection | CodeCode Available | 1 |
| M3L: Language-based Video Editing via Multi-Modal Multi-Level Transformers | Apr 2, 2021 | DiagnosticVideo Editing | —Unverified | 0 |
| Visual Semantic Role Labeling for Video Understanding | Apr 2, 2021 | Semantic Role LabelingVideo Recognition | CodeCode Available | 1 |
| Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation | Mar 30, 2021 | Action DetectionTemporal Action Proposal Generation | —Unverified | 0 |
| Unified Graph Structured Models for Video Understanding | Mar 29, 2021 | Action DetectionGraph Classification | —Unverified | 0 |
| Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization | Mar 28, 2021 | Action ClassificationAction Localization | —Unverified | 0 |
| Learning Salient Boundary Feature for Anchor-free Temporal Action Localization | Mar 24, 2021 | Action LocalizationTemporal Action Localization | CodeCode Available | 1 |
| Temporal Context Aggregation Network for Temporal Action Proposal Refinement | Mar 24, 2021 | Action DetectionAction Localization | CodeCode Available | 1 |
