This repository serves as a curated list of seminal academic papers for individuals new to computer vision and NLP, aiming to accelerate their learning curve. It categorizes influential research across various subfields, providing a structured path for understanding key advancements and their impact.

How It Works

The project organizes papers by topic, such as Convolutional Neural Networks (CNNs) for image classification, object detection, and segmentation, as well as Transformers in Vision and NLP. Each entry includes the paper's abbreviation, title, citation count, journal, year, first author, and their affiliation, offering a comprehensive overview of foundational research.

Quick Start & Requirements

This is a curated list of papers and does not require installation or execution. All information is presented in the README.

Highlighted Details

• Comprehensive coverage of traditional computer vision methods (SIFT, HOG) and modern deep learning architectures (AlexNet, ResNet, EfficientNet).
• Detailed sections on object detection (RCNN, YOLO), segmentation (FCN, U-Net), and face recognition (FaceNet, ArcFace).
• Includes significant papers on Neural Architecture Search (NAS), image super-resolution, denoising, and model compression techniques (pruning, quantization).
• Features key Transformer models for both vision (ViT, DETR) and NLP (BERT, Attention Is All You Need).

Maintenance & Community

The project welcomes contributions via pull requests or issues to expand the list with more subjects or valuable papers.

Licensing & Compatibility

The repository content is presented as a list of academic papers. The underlying code or data for these papers is not included, and thus licensing is not directly applicable to the repository itself.

Limitations & Caveats

The list is a curated selection and may not be exhaustive. It focuses on widely recognized papers and does not include implementation code or experimental results.