The official VOT Challenge evaluation and analysis toolkit

This is a collection of our NAS and Vision Transformer work.

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Code of Pyramidal Flow Matching for Efficient Video Generative Modeling

Flow-based visual scripting for Python

High-resolution models for human tasks.

Fast and memory-efficient exact attention

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Python scripts for the Segment Anythin 2 (SAM2) model in ONNX

Visual tracking library based on PyTorch.

OpenMMLab Pose Estimation Toolbox and Benchmark.

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Code for "LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model", CVPR 2024 Highlight

SeqTrackv2: Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking

[ICCV2023] The PyTorch implementation for "Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation"

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

[ECCV 2022] Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework

[CVPR23] Visual Prompt Multi-Modal Tracking

Multi-person Human Pose Estimation with HRNet in Pytorch

(CVPR 2021 Oral) Open World Object Detection

[ECCV'20] Ocean: Object-aware Anchor-Free Tracking

Few-shot Object Detection via Feature Reweighting

(ECCV 2020) PyTorch implementation of paper "Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild"

FewX is an open-source toolbox on top of Detectron2 for data-limited instance-level recognition tasks.