| _ | tubelet | _ |
|---|
| Action Localization with | tubelet | s from Motion |
| Action | tubelet | Detector for Spatio-Temporal Action Localization |
| Actor-Centric | tubelet | s for Real-Time Activity Detection in Extended Videos |
| CenterTube: Tracking Multiple 3D Objects With 4D | tubelet | s in Dynamic Point Clouds |
| Detection and tracking based | tubelet | generation for video object detection |
| Discriminative action | tubelet | detector for weakly-supervised action detection |
| Generic | tubelet | Proposals for Action Localization |
| Object Detection from Video | tubelet | s with Convolutional Neural Networks |
| Object Detection in Videos with | tubelet | Proposal Networks |
| Recurrent | tubelet | Proposal and Recognition Networks for Action Detection |
| Social Fabric: | tubelet | Compositions for Video Relation Detection |
| T-CNN: | tubelet | s With Convolutional Neural Networks for Object Detection from Videos |
| TQRFormer: | tubelet | query recollection transformer for action detection |
| tubelet | -Contrastive Self-Supervision for Video-Efficient Generalization |
| tubelet | s: Unsupervised Action Proposals from Spatiotemporal Super-Voxels |
| TubeR: | tubelet | Transformer for Video Action Detection |
16 for tubelet