blackfeather-wang / AdaFocus
Reducing spatial redundancy in video recognition. SOTA computational efficiency.
☆125Updated 3 months ago
Alternatives and similar repositories for AdaFocus:
Users that are interested in AdaFocus are comparing it to the libraries listed below
- ☆61Updated 4 years ago
- AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition (ICLR 2021)☆34Updated 3 years ago
- [AAAI 2020] Temporal Interlacing Network☆84Updated 4 years ago
- Official pytorch implementation of paper "VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples" (CVP…☆146Updated 3 years ago
- [ICCV 2021] Relaxed Transformer Decoders for Direct Action Proposal Generation☆89Updated 2 years ago
- [ECCV 2020] Boundary-Aware Cascade Networks for Temporal Action Segmentation☆84Updated 4 years ago
- Official Code for VideoLT: Large-scale Long-tailed Video Recognition (ICCV 2021)☆33Updated 2 years ago
- CVPR2021: Temporal Context Aggregation Network for Temporal Action Proposal Refinement☆71Updated 3 years ago
- Learning Representational Invariances for Data-Efficient Action Recognition☆33Updated 3 years ago
- ☆71Updated 3 years ago
- code for our ECCV-2020 paper: Self-supervised Video Representation Learning by Pace Prediction☆99Updated 3 years ago
- ☆70Updated last year
- Rethinking Self-Supervised Correspondence Learning: A Video Frame-level Similarity Perspective, in ICCV 2021 (Oral)☆145Updated 3 years ago
- ☆34Updated 3 years ago
- Code for our CVPR 2021 paper "Coarse-Fine Networks for Temporal Activity Detection in Videos"☆57Updated 3 years ago
- ☆40Updated 2 years ago
- ☆44Updated 3 years ago
- ☆72Updated 3 years ago
- [ICCV 2021] MGSampler: An Explainable Sampling Strategy for Video Action Recognition☆48Updated 2 years ago
- A Toolkit for Video Action Recognition(Classification/Detection)☆17Updated 3 years ago
- Official PyTorch implementation of the ECCV 2022 paper: Efficient Video Transformers with Spatial-Temporal Token Selection.☆46Updated 2 years ago
- PyTorch implementation of BEVT (CVPR 2022) https://arxiv.org/abs/2112.01529☆159Updated 2 years ago
- ☆89Updated 3 months ago
- [ICLR2021] official implementation of CT-Net☆37Updated 3 years ago
- Code accompanying Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos (CVPR 2021)☆33Updated 3 years ago
- Code for our ICCV 2021 Paper "OadTR: Online Action Detection with Transformers".☆90Updated last year
- [CVPR 2022 Oral] Towards Open Set Temporal Action Localization☆52Updated last year
- Official code for "Detecting Human-Object Interactions with Action Co-occurrence Priors☆33Updated 3 years ago
- Video Representation Learning by Recognizing Temporal Transformations. In ECCV, 2020.☆48Updated 4 years ago
- Unsupervised Film Genre Classification using Spatio-Temporal Contrastive Learning☆32Updated last year