Stars
Official code Implementation of "Text and Image Are Mutually Beneficial: Enhancing Training-Free Few-Shot Classification with CLIP" (AAAI-25)
[CVPR 2025] SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing
Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition
This repo contains data sets that are required in order to perform the applications and exercises
Matplotlib中文教程，在线阅读地址：https://datawhalechina.github.io/fantastic-matplotlib/
[CVPR 2022] Official Pytorch Implementation for "Spatio-temporal Relation Modeling for Few-shot Action Recognition". SOTA Results for Few-shot Action Recognition
Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations, AAAI 2023
label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful
Enhance your application with the ability to see and interact with humans using any RGB camera.
The implementation for "Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition" (ECCV2020).
Efficient 3D human pose estimation in video using 2D keypoint trajectories
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
Repository for PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition
The implementation for "Skeleton-Based Action Recognition with Shift Graph Convolutional Network" (CVPR2020 oral).
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Compositional Learning for Human Object Interaction
A repository of common methods, datasets, and tasks for video research
An efficient video loader for deep learning with smart shuffling that's super easy to digest
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
PyTorch implementation of Multi-Label Image Recognition with Graph Convolutional Networks, CVPR 2019.
Code for ICLR 2020 paper "VL-BERT: Pre-training of Generic Visual-Linguistic Representations".
A curated list of Group Activity (a.k.a., Collective Activity) recognition papers, codes, datasets and other resources.
The model architecture of AS-GCN (for human action recognition)
[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment
Spatio-Temporal Action Localization System
My take on a practical implementation of Linformer for Pytorch.