mengyuest / AdaFuse
AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition (ICLR 2021)
☆33Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for AdaFuse
- ☆61Updated 4 years ago
- Code for our CVPR 2021 paper "Coarse-Fine Networks for Temporal Activity Detection in Videos"☆55Updated 3 years ago
- Implementations of some few-shot action recognition methods.☆42Updated 3 years ago
- [ICCV 2021] MGSampler: An Explainable Sampling Strategy for Video Action Recognition☆48Updated 2 years ago
- [CVPR 2022 Oral] Towards Open Set Temporal Action Localization☆50Updated last year
- Official PyTorch Implementation of Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition, ICCV 20…☆26Updated 3 years ago
- ☆71Updated 3 years ago
- [ECCV 2020] Boundary-Aware Cascade Networks for Temporal Action Segmentation☆84Updated 3 years ago
- ☆32Updated 3 years ago
- ☆73Updated 2 years ago
- Repository to contain the code for the CVPR 2020 publication: Multi-Modal Domain Adaptation for Fine-Grained Action Recognition☆59Updated 4 years ago
- Reducing spatial redundancy in video recognition. SOTA computational efficiency.☆122Updated 2 years ago
- CVPR2021: Temporal Context Aggregation Network for Temporal Action Proposal Refinement☆70Updated 3 years ago
- The implementation of CVPR2021 paper Temporal Query Networks for Fine-grained Video Understanding☆62Updated 2 years ago
- This is the official implementation of Elaborative Rehearsal for Zero-shot Action Recognition (ICCV2021)☆36Updated 2 years ago
- ☆21Updated 4 years ago
- Weakly Supervised Temporal Action Localization Using Deep Metric Learning☆29Updated 4 years ago
- Pytorch Implementation of Videos as Space-Time Region Graphs☆26Updated 3 months ago
- [CVPR 2022] An Empirical Study of End-to-end Temporal Action Detection☆82Updated last year
- Official code for "Detecting Human-Object Interactions with Action Co-occurrence Priors☆33Updated 2 years ago
- Temporal Action Localization Visualization Tool (TALVT) is a Javascript based simple visualization tool to visualize the outcomes of the …☆27Updated 4 years ago
- ☆26Updated 5 years ago
- ICCV 19 Grouped Spatial-Temporal Aggretation for Efficient Action Recognition☆43Updated 5 years ago
- Video Representation Learning by Recognizing Temporal Transformations. In ECCV, 2020.☆48Updated 3 years ago
- Official Pytorch Implementation of Relational Self-Attention, NeurIPS 2021☆49Updated 2 years ago
- ☆14Updated 3 years ago
- ☆40Updated 2 years ago
- Codes for arXiv paper "Semi-supervised Few-shot Atomic Action Recognition".☆17Updated 3 years ago
- Code for CVPR'21 paper "Weakly Supervised Action Selection Learning in Video"☆22Updated 3 years ago
- Code for our ICCV 2021 Paper "OadTR: Online Action Detection with Transformers".☆90Updated last year