This repository serves as a curated collection of academic papers, code, and datasets related to Person Re-Identification (ReID) and related computer vision tasks. It aims to provide researchers and practitioners with a comprehensive and up-to-date resource for the field, facilitating easier access to state-of-the-art research.

How It Works

The repository organizes papers by conference (e.g., CVPR, ICCV, ECCV) and topic (e.g., Person ReID, Vehicle ReID, Person Search, Object ReID). It primarily links to publicly available PDFs, often hosted on arXiv, but also includes links to associated GitHub repositories for code implementations. The content is regularly updated to reflect the latest publications.

Quick Start & Requirements

This is a curated list of research papers and does not have a direct installation or execution command. Users are expected to follow the links provided to access individual papers and their associated code repositories, which will have their own specific setup instructions and dependencies (e.g., Python, PyTorch, TensorFlow, specific datasets).

Highlighted Details

• Comprehensive coverage of major computer vision conferences from 2017 to present.
• Includes links to associated GitHub repositories for many papers, enabling code access.
• Features curated lists for related tasks like Vehicle Re-Identification and Person Search.
• Provides links to leaderboards for popular ReID datasets like Market-1501 and DukeMTMC.

Maintenance & Community

The repository is maintained by a proactive researcher with a background in computer vision and machine learning, who has published in top-tier conferences. Updates are frequent, with recent additions from CVPR2024 and WACV2024. Suggestions for new categories, corrections, and additions are welcomed via pull requests.

Licensing & Compatibility

The repository itself is a collection of links and does not host any code or data directly. Therefore, licensing is determined by the individual papers and their associated code repositories. Users must adhere to the licenses of the linked resources.

Limitations & Caveats

Access to some papers may require academic subscriptions as they are hosted on publisher websites (e.g., IEEE, Springer). The repository is a curated list and does not provide a unified framework or codebase for running experiments.