facebookresearch / MotionformerLinks
Code + pre-trained models for the paper Keeping Your Eye on the Ball Trajectory Attention in Video Transformers
☆229Updated 3 years ago
Alternatives and similar repositories for Motionformer
Users that are interested in Motionformer are comparing it to the libraries listed below
Sorting:
- Code Release for MeMViT Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition, CVPR 2022☆148Updated 2 years ago
- Reducing spatial redundancy in video recognition. SOTA computational efficiency.☆125Updated 7 months ago
- Code for ECCV2022 "Real-time Online Video Detection with Temporal Smoothing Transformers"☆110Updated last year
- [NeurIPS 2021 Spotlight] Official implementation of Long Short-Term Transformer for Online Action Detection☆136Updated 11 months ago
- Official repository for "Self-Supervised Video Transformer" (CVPR'22)☆108Updated last year
- ☆44Updated 4 years ago
- Video Contrastive Learning with Global Context, ICCVW 2021☆158Updated 3 years ago
- [ICLR2021] AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition☆34Updated 4 years ago
- [ICLR 2022] TAda! Temporally-Adaptive Convolutions for Video Understanding. This codebase provides solutions for video classification, vi…☆239Updated last year
- PyTorch implementation of BEVT (CVPR 2022) https://arxiv.org/abs/2112.01529☆162Updated 2 years ago
- Code release for ICCV 2021 paper "Anticipative Video Transformer"☆153Updated 3 years ago
- Official implementation of "An Image is Worth 16x16 Words, What is a Video Worth?" (2021 paper)☆222Updated 2 years ago
- Rethinking Self-Supervised Correspondence Learning: A Video Frame-level Similarity Perspective, in ICCV 2021 (Oral)☆146Updated 3 years ago
- Code for our CVPR 2021 paper "Coarse-Fine Networks for Temporal Activity Detection in Videos"☆57Updated 3 years ago
- ☆71Updated 4 years ago
- Code and model for "Multi-dataset Training of Transformers for Robust Action Recognition", NeurIPS 2022 Spotlight☆20Updated last year
- ☆84Updated last year
- Code accompanying Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos (CVPR 2021)☆34Updated 4 years ago
- Official implementation of "ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos" (ACM ICMRW 2021)☆53Updated 2 years ago
- Official implementation of the paper Vision Transformer with Progressive Sampling, ICCV 2021.☆153Updated 3 years ago
- This is the code for HOI Transformer☆151Updated 3 years ago
- Series of work (ECCV2020, CVPR2021, CVPR2021, ECCV2022) about Compositional Learning for Human-Object Interaction Exploration☆81Updated 2 years ago
- [CVPR 2022 Oral] TubeDETR: Spatio-Temporal Video Grounding with Transformers☆181Updated last year
- Code for our ICCV 2021 Paper "OadTR: Online Action Detection with Transformers".☆92Updated last year
- This is an official implementation of TubeR: Tubelet Transformer for Video Action Detection☆81Updated 2 years ago
- Official repo for ECCV 2020 paper - RubiksNet: Learnable 3D-Shift for Efficient Video Action Recognition☆100Updated 4 years ago
- [ECCV'20 Spotlight] Memory-augmented Dense Predictive Coding for Video Representation Learning. Tengda Han, Weidi Xie, Andrew Zisserman.☆165Updated 4 years ago
- ☆72Updated last year
- Implementation of paper "Modeling Multi-Label Action Dependencies for Temporal Action Localization"☆51Updated 2 years ago
- [CVPR 2022] An Empirical Study of End-to-end Temporal Action Detection☆85Updated 2 years ago