This repository provides a daily-updated list of computer vision papers from arXiv, organized by topic. The updates are automated using GitHub Actions to ensure you stay current with the latest research.
Online documentation: https://islinxu.github.io/paper-list/
- Dashboard: docs/analytics/
To generate the paper list locally, follow these steps:
-
Install Dependencies
pip install -r requirements.txt
-
Run the Script
python get_paper.py
-
Configuration You can customize the search keywords and other settings in
config.yaml.
You can also use the scripts in the scripts/ directory for additional tasks:
- Count Papers in Range: Count the number of papers within a specific date range.
python scripts/count_range.py 2024-01-01 2024-12-31
- Classification
- Object Detection
- Semantic Segmentation
- Object Tracking
- Action Recognition
- Pose Estimation
- Image Generation
- LLM
- Scene Understanding
- Depth Estimation
- Audio Processing
- Multimodal
- Anomaly Detection
- Transfer Learning
- Optical Flow
- Reinforcement Learning
- Graph Neural Networks
- Latent Space LLM
- Diffusion Models
- Video Understanding
- Neural Rendering





