This repository serves as a comprehensive, actively maintained list of papers, code, and related websites focused on Vision Transformers and attention mechanisms in computer vision. It is an invaluable resource for researchers, engineers, and practitioners looking to stay abreast of advancements in this rapidly evolving field.

How It Works

The list is meticulously curated and categorized by application area, such as image classification, object detection, segmentation, and video understanding. Each entry typically includes a link to the paper and, where available, its corresponding code repository, facilitating easy access and exploration of the latest research.

Quick Start & Requirements

This repository is a curated list and does not have direct installation or execution requirements. Users can browse the extensive collection of papers and code links provided.

Highlighted Details

• Extensive categorization covering a wide array of computer vision tasks.
• Regular updates, including recent papers from major conferences like NeurIPS, ICCV, ICML, and CVPR.
• Links to official papers and code repositories for most entries.
• Includes a dedicated section for multi-modal research.

Maintenance & Community

The list is actively maintained by Min-Hung Chen, with contributions welcomed via pull requests, issues, or email.

Licensing & Compatibility

This repository is a list of external resources and does not have its own licensing. The licensing of individual papers and code repositories will vary.

Limitations & Caveats

While comprehensive, the sheer volume of papers means users may need to filter based on their specific interests. The availability and quality of linked code repositories can vary.