hongsongwang

GeoDrag. Dragging with Geometry: From Pixels to Geometry-Guided Image Editing

DVTA. Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment

LOTA. Code for the LOTA: Bit-Planes Guided AI-Generated Image Detection

CS_arXiv_Paper. arXiv Paper Portal in Computer Science of 2025-2026

Survey-Video-Diffusion. The official paper summary of TMLR'25 paper "Survey of Video Diffusion Models: Foundations, Implementations, and Applications"

CV_Paper_Portal. Paper Portal for Top Conferences in the Field of Computer Vision and Artificial intelligence

AI_arXiv_Portal. arXiv Paper Portal for Computer Vision, Machine Learning and Artificial Intelligence

BestPaperAwards_AI. Best Paper Awards in Top Conferences of Artificial Intelligence

PGPFR-3. Python

FoundSkelModel. [TPAMI 2025] This repository is the official implementation of "Foundation Model for Skeleton-Based Human Action Understanding".

DGSDP. Python

PAMD. We introduce PAMD, a framework for generating dances that are both musically aligned and physically realistic.

awesome-test-time-adaptation. Collection of awesome test-time (domain/batch/instance) adaptation methods

USDRL. [AAAI 2025] This repository is the official implementation of "Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation".

NSFC-LaTex. BibTeX Style

DAMO-YOLO. DAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement.

GaitMixer. Official repository for "GaitMixer: Skeleton-based Gait Representation Learning via Wide-spectrum Multi-axial Mixer" (ICASSP 2023)

GCN_rerank. Python

Instance-Search. Python

deep3dmap. deep 3d reconstruction

Google_Landmark_Retrieval_2021_2nd_Place_Solution. Python

PVRNN. PVRNN for human motion prediction

fast-reid. SOTA Re-identification Methods and Toolbox

MinkowskiEngine. Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

Pedestrian-Detection. Pedestrian Detection Papers

agame-vos. PyTorch implementation of the paper "A Generative Appearance Model for End-to-End Video Object Segmentation".

FFNet. Implementation of our CVPR 2018 Paper (FFNet: Video Fast-Forwarding via Reinforcement Learning)