This repository is a curated list of research papers focusing on the application of Transformer architectures in Computer Vision (CV). It serves as a comprehensive resource for researchers and practitioners interested in visual transformers, providing links to papers, code, and relevant surveys.

How It Works

The repository organizes papers by their contribution to visual transformers, covering a wide range of CV tasks such as object detection, segmentation, image restoration, and more. It includes foundational papers like the original Transformer and key works like Vision Transformer (ViT), alongside numerous specialized variants and applications.

Quick Start & Requirements

This is a curated list of papers and does not have a direct installation or execution command. Users can browse the list to find relevant research papers and their associated code repositories.

Highlighted Details

• Extensive collection of papers, categorized by conference and topic.
• Includes links to official papers and, where available, associated code repositories.
• Features survey papers providing an overview of the field.
• Covers a broad spectrum of computer vision tasks where transformers are applied.

Maintenance & Community

The repository is maintained by dk-liang and welcomes contributions through issues or pull requests for overlooked papers.

Licensing & Compatibility

The repository itself is not software and thus not subject to software licensing. Individual papers and code repositories linked within will have their own licenses.

Limitations & Caveats

This is a passive collection of links; it does not provide any executable code or pre-trained models directly. Users must follow the links to access the actual research and implementations.