This repository serves as a curated collection of academic papers and resources across various computer vision and related fields, including chip design, SLAM, medical imaging, and deep learning architectures. It targets researchers, engineers, and students seeking foundational and state-of-the-art literature for specific domains. The primary benefit is a centralized, organized reference point for key publications.

How It Works

The repository is structured by topic, with each section listing relevant papers, their publication times, and direct links to their sources (often arXiv or publisher pages). This organization facilitates quick discovery of seminal works and recent advancements within specialized areas like object detection, semantic segmentation, and neural rendering.

Quick Start & Requirements

No installation or execution is required. This is a reference repository.

Highlighted Details

• Extensive coverage of chip design and design space exploration (DSE) papers, including simulators like gem5 and Rocket-Chip.
• Comprehensive lists for various computer vision tasks: object detection (R-CNN, YOLO, SSD), semantic segmentation (FCN, DeepLab), keypoint detection, and face analysis.
• Includes foundational and modern deep learning models and algorithms (AlexNet, ResNet, ViT, GANs, Transformers).
• Dedicated sections for medical imaging, SLAM, and inference frameworks (TVM, Caffe).

Maintenance & Community

Information regarding maintenance, contributors, or community channels is not present in the README.

Licensing & Compatibility

The licensing of the repository itself is not specified. The linked papers are subject to their respective publisher or archival licenses.

Limitations & Caveats

This repository is a static collection of links and does not provide code, implementations, or direct access to the papers themselves. Users must follow the provided links to access the content, which may be behind paywalls or require specific academic access.