Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
International Journal of Computer Vision· 2017· 0 citations· Open access · green
Research, charted
Search by author name to explore publications across years, formats, citations, and open access.
Try Andrew Ng, Yann LeCun, or Fei-Fei Li
Stanford University · Computer vision
Search to load current OpenAlex data3 publications
International Journal of Computer Vision· 2017· 0 citations· Open access · green
International Journal of Computer Vision· 2015· 0 citations· Open access · green
CVPR· 2009· 0 citations· Access not listed
Names are matched with affiliations, topics, ORCID, and record counts. You choose the identity—Publication Atlas never silently merges people with similar names.
Metadata comes from OpenAlex and may change as its graph is refreshed. “PDF” means a direct open file was listed; otherwise the site labels the destination honestly as “View source.”
Design by Assoc. Prof. Dr. Charnsak Srisawatsakul
Built by ChatGPT Codex
The only live data API called by this page. Author identities, affiliations, topics, publication metadata, citation counts, open-access status, and PDF/source locations are fetched directly from the OpenAlex REST API in the visitor’s browser.
DOI.org resolves DOI links. arXiv, publishers, repositories, and other source hosts provide outbound landing pages or PDFs. The page links to them but does not proxy or re-host their files. ORCID identifiers are displayed only when supplied by OpenAlex; the ORCID API is not called.
The interface is built with Vinext, Next.js, React, and Tailwind CSS, and is served on the Cloudflare Workers runtime. No external font API or analytics service is used.
The background map is an original static image created for this page with OpenAI image generation. It is bundled with the site; no image-generation API is called while visitors use the page.