An Open Source Machine Learning Framework for Everyone

(ECCV2022) This is the official PyTorch implementation of ECCV2022 paper: Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing

code for CVPR2024 paper: DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction

Mamba models toolbox (MambaTrack, TrackSSM, etc.) used for Multi-object Tracking

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

Code for the book "Software Engineering for Data Scientists"

[ECCV 2024] Official repository of SkateFormer

Mamba based SSD object detection

OpenMMLab Detection Toolbox and Benchmark

Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone

This is an official implementation of TubeR: Tubelet Transformer for Video Action Detection

<Do it! 쉽게 배우는 파이썬 데이터 분석> 저장소

A toolbox for skeleton-based action recognition.

The dataset and codes of the paper UniMod1K: Towards a More Universal Large-Scale Dataset and Benchmark for Multi-Modal Learning.

Forest fire prediction using finetuning on CPU with MODIS and NAIP aerial photos and resnet with acceleration using Intel Extensions for PyTorch

PyCIL: A Python Toolbox for Class-Incremental Learning

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

[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding

[ECCV'22] The official PyTorch implementation of our ECCV 2022 paper: "AiATrack: Attention in Attention for Transformer Visual Tracking".

Visual tracking library based on PyTorch.