Transferable Unintentional Action Localization with Language-guided Intention Translation (IEEE TPAMI 2025)

CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control

Deep Learning for 3D Human Pose Estimation and Mesh Recovery: A Survey

Pytorch demo code and models for Multi-HMR

ScoreHMR: Score-Guided Diffusion for 3D Human Recovery (CVPR 2024)

The repository contains the official implementation of "DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery", CVPR 2024

[CVPR 2024] TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation

👾 E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding (NeurIPS 2024)

Model Merging with SVD to Tie the KnOTS [ICLR 2025]

Ultralytics YOLO11 🚀

High-resolution models for human tasks.

Official PyTorch implementation of "Expressive Whole-Body 3D Gaussian Avatar", ECCV 2024.

🔥[ACMMM 2023, Official Code] for paper "EAT: An Enhancer for Aesthetics-Oriented Transformers". Official Weights and Demos provided. 目前是地表最强开源美学评估模型之一.

computer vision and sports

[IROS24] Offical Code for "FruitNeRF: A Unified Neural Radiance Field based Fruit Counting Framework" - Inegrated into Nerfstudio

🔥🔥🔥Latest Papers, Codes and Datasets on Vid-LLMs.

Official repository for "PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout" (CVPR 2023).

FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models

[ECCV2024] VideoMamba: State Space Model for Efficient Video Understanding

A Ball 3D Localization challenge on Basketball images. An opportunity to publish at MMSports @ ACMMM and to win 2x $500.

A collection of recent video understanding datasets, under construction!

Efficient 3D human pose estimation in video using 2D keypoint trajectories

Official implementation of the paper "MotionAGFormer: Enhancing 3D Pose Estimation with a Transformer-GCNFormer Network" (WACV 2024).

Pyramid Grafting Network for One-Stage High Resolution Saliency Detection. CVPR 2022

Awesome Action Quality Assessment (AQA)

Cross-Modal-Real-valuded-Retrieval

Code repository for the paper "Tracking People by Predicting 3D Appearance, Location & Pose". (CVPR 2022 Oral)