hongsong-wang/CV_Paper_Portal

Paper Portal for Top Conferences in the Field of Computer Vision and Artificial intelligence

What it solves

Finding a specific paper across dozens of top AI conferences is time-consuming because each conference has its own website and abstracts are scattered. This project gathers abstracts from major conferences in computer vision, language, learning, and robotics into one place, so researchers can quickly locate papers by keywords instead of browsing multiple official sites.

How it works

The author collected abstracts from conference proceedings (mostly sourced from arXiv) and organised them into dedicated web pages for each conference and year. Each conference (e.g., CVPR, ICLR, NeurIPS, ACL, CoRL) has a section with links to yearly pages that list the accepted papers and their abstracts. A separate search portal (http://47.102.131.153/) is also provided to search across these papers. The pages are publicly hosted on GitHub and updated as new conference editions appear.

Who it's for

Students and researchers in computer vision, natural language processing, machine learning, and robotics who need to browse or search papers from top conferences. It is also useful for anyone who wants a single, organised entry point to multiple years of conference proceedings.

Highlights

  • Covers a broad range of top conferences: CVPR, ICCV, ECCV, ACM Multimedia, SIGGRAPH, ACL, NAACL, EMNLP, COLING, ICLR, NeurIPS, ICML, AAAI, CoRL, RSS, IROS, ICRA
  • Provides per-conference, per-year abstract pages, going back to 2013 or earlier for some venues
  • Includes a dedicated search portal for finding papers by keywords
  • Regularly updated with new conference editions (e.g., NeurIPS 2026, ACMMM 2026, ECCV 2026)
  • Open access: all pages are freely available on GitHub
  • Companion projects exist for journal papers, arXiv papers, and best-paper awards

Related

  • Project
    google-deepmind/representations4d

    DeepMind’s representations4d provides research‑grade video models that learn 4‑D (spatial + temporal) features via masked auto‑encoding, moving‑token attention, recurrent masking, multimodal alignment, and diffusion‑based perception. It ships pretrained checkpoints (up to 22 B parameters), Colab demos, and a small Python library for inference on depth, tracking, segmentation, and text‑prompted multi‑task vision.

  • Project
    hacker-frok/qq-farm-bot-ai

    A visual automation bot for the QQ Classic Farm game that uses OpenCV template matching to automate farming, seed management, and social interactions.

  • Project
    Kohulan/DECIMER-Image_Transformer

    DECIMER is an open-source deep learning tool that automatically recognizes chemical structures in images and converts them into SMILES strings, the standard text format for molecules. It helps chemists digitize printed or hand-drawn chemical structures without manual data entry.

  • Project
    ZZZHANG-jx/Recommendations-Document-Image-Processing

    This repository is a carefully organised collection of academic papers, datasets, and benchmark results for document image processing, covering tasks such as shadow removal, dewarping, deblurring, and appearance enhancement. It serves as a reference hub for researchers and developers looking to understand or apply state-of-the-art methods to clean up photographed documents.