| OpenTAL: Towards Open Set Temporal Action Localization | Mar 10, 2022 | Action ClassificationAction Localization | CodeCode Available | 1 |
| Quantification of Occlusion Handling Capability of a 3D Human Pose Estimation Framework | Mar 8, 2022 | 3D Human Pose EstimationAction Classification | CodeCode Available | 0 |
| Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions | Feb 23, 2022 | Action ClassificationAction Recognition | CodeCode Available | 1 |
| Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision | Feb 16, 2022 | Action ClassificationAction Recognition | —Unverified | 0 |
| Learning To Recognize Procedural Activities with Distant Supervision | Jan 26, 2022 | Action ClassificationLanguage Modelling | CodeCode Available | 1 |
| MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition | Jan 20, 2022 | Action AnticipationAction Classification | CodeCode Available | 1 |
| Omnivore: A Single Model for Many Visual Modalities | Jan 20, 2022 | Action ClassificationAction Recognition | CodeCode Available | 2 |
| End-to-end Generative Pretraining for Multimodal Video Captioning | Jan 20, 2022 | Action ClassificationDecoder | —Unverified | 0 |
| Video Transformers: A Survey | Jan 16, 2022 | Action ClassificationSelf-Supervised Learning | —Unverified | 0 |
| Multiview Transformers for Video Recognition | Jan 12, 2022 | Action ClassificationAction Recognition | —Unverified | 0 |
