PyTorch implementation of "Integral Human Pose Regression", ECCV 2018

PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)

A curated list of recent monocular depth estimation papers

Focal and Global Knowledge Distillation for Detectors (CVPR 2022)

[ICCV2023] DETRDistill: A Universal Knowledge Distillation Framework for DETR-families

[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]

Ultralytics YOLO11 🚀

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

PyTorch code and models for the DINOv2 self-supervised learning method.

Code release for ConvNeXt V2 model

RepViT: Revisiting Mobile CNN From ViT Perspective [CVPR 2024] and RepViT-SAM: Towards Real-Time Segmenting Anything

Pytorch implementation of various Knowledge Distillation (KD) methods.

SOTA Re-identification Methods and Toolbox

A best practice for deep learning project template architecture.

Torchreid: Deep learning person re-identification in PyTorch.

Official implementation of "Local All-Pair Correspondence for Point Tracking" (ECCV 2024)

Tracking Any Point (TAP)

OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.

A Library for Advanced Deep Time Series Models.

Pytorch implementation of "Fine-grained Visual Classification with High-temperature Refinement and Background Suppression"

Official code for NetTrack [CVPR 2024]

[CVPR 2025] Multiple Object Tracking as ID Prediction

State-of-the-art 2D and 3D Face Analysis Project

[ICCV2023] MixSort: The Customized Tracker in SportsMOT

[AAAI2024]Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking

[CVPR2023] The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models