[CVPR 2024] Official implementation of the paper "Visual In-context Learning"

A repo for llm on ncnn

[ICCV2023] MixSort: The Customized Tracker in SportsMOT

Official Pytorch implementation of "Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose", ECCV 2020

PyTorch transcribed audioset classifier, including VGGish and YAMNet, along with utils to manipulate autioset category ontology.

VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMs

Muon is an optimizer for hidden layers in neural networks

The Amazon S3 Connector for PyTorch delivers high throughput for PyTorch training jobs that access and store data in Amazon S3.

基于人体姿态估计的AI健身系统

Learning from Synthetic Humans, CVPR 2017

The official implementation of OmniTrack: Omnidirectional Multi-Object Tracking (CVPR 2025)

Collection of common code that's shared among different research projects in FAIR computer vision team.

This is the official repo for the paper "LongCat-Flash-Omni Technical Report"

[ECCV 2024] Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance

MediaTek's TFLite delegate

Pytorch implementation of the 'Slim-neck by GSConv: a lightweight-design for real-time detector architectures'

ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment [Official, ICCV 2021]

Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)

YOLOE: Real-Time Seeing Anything [ICCV 2025]

A diverse benchmark database for multi-paradigm facial beauty prediction

Faster Whisper transcription with CTranslate2

MLX: An array framework for Apple silicon

A player reidentification challenge on Basketball images. An opportunity to publish at MMSports @ ACMMM and to win 2x $500.

Running Real Time face motioncapture using Mediapipe and AR-Kit Shapekeys

Winners of the 2022 DeepSportRadar player re-identification challenge

MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone

106点人脸关键点检测的PFLD算法实现

Official PyTorch implementation for the paper Generalizable Face Landmarking Guided by Conditional Face Warping (CVPR 2024).