thuml / VideoDGLinks
☆20Updated 2 years ago
Alternatives and similar repositories for VideoDG
Users that are interested in VideoDG are comparing it to the libraries listed below
Sorting:
- Shared Attention for Multi-label Zero-shot Learning accepted @ CVPR20☆32Updated 4 years ago
- Learning from Temporal Gradient for Semi-supervised Action Recognition (CVPR 2022)☆30Updated 3 years ago
- Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency☆17Updated 4 years ago
- This is the official implementation of Elaborative Rehearsal for Zero-shot Action Recognition (ICCV2021)☆36Updated 3 years ago
- Code for Temporal Data Augmentations (ECCVW 2020)☆37Updated 5 years ago
- [CVPR 2022] Code for Motion-aware Contrastive Video Representation Learning via Foreground-background Merging☆49Updated 2 years ago
- Official Code for VideoLT: Large-scale Long-tailed Video Recognition (ICCV 2021)☆34Updated 3 years ago
- ☆85Updated 3 years ago
- Official code for "Dynamic Token Normalization Improves Vision Transformer", ICLR 2022.☆29Updated 3 years ago
- [ECCV2022] The PyTorch implementation of paper "Equivariance and Invariance Inductive Bias for Learning from Insufficient Data"☆19Updated 3 years ago
- a pytorch implementation for MoCo V3☆32Updated 4 years ago
- (CVPR 2020) Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition☆40Updated 4 years ago
- ☆47Updated 4 years ago
- Reducing spatial redundancy in video recognition. SOTA computational efficiency.☆127Updated last year
- Code of our Neurips2020 paper "Auto Learning Attention", coming soon☆22Updated 4 years ago
- Code repo for "FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation" (ICCV 2021)☆30Updated 4 years ago
- Pytorch code for our NeurIPS 2019 paper "Cross-channel Communication Networks"☆41Updated 6 years ago
- ☆17Updated 3 years ago
- 🏆 The 2nd Place Submission to the CVPR2021-Evoked Emotion from Videos challenge.☆17Updated 4 years ago
- ☆16Updated 5 years ago
- AutoGesture with Temporal Difference Convolutions (TIP'21)☆53Updated 4 years ago
- Learning Representational Invariances for Data-Efficient Action Recognition☆33Updated 4 years ago
- PyTorch code for the paper: "FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning"☆50Updated 4 years ago
- SoT: Delving Deeper into Classification Head for Transformer☆50Updated 4 years ago
- [CVPR 2022 Oral] Towards Open Set Temporal Action Localization☆54Updated 2 years ago
- ☆41Updated 3 years ago
- Repository for ECCV 2022 paper "Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition"☆24Updated 2 years ago
- Official implementation of AdaMML. https://arxiv.org/abs/2105.05165.☆51Updated 3 years ago
- code for our ECCV-2020 paper: Self-supervised Video Representation Learning by Pace Prediction☆100Updated 4 years ago
- ☆20Updated 4 years ago