Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1612.01887/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTKnowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning — mentioned by Smerityhttps://news.ycombinator.com/item?id=14356931urn:hackerpapers:mention:1612.01887:14356931Wed, 17 May 2017 09:49:16 GMT<p>This is all doable today. As an example, check out some bird photos[1] from the Visual Genome[2] project that are similar to your examples. I selected the photos and hosted them on Imgur in hopes we don&#x27;t kill Visual Genome with traffic ;) The systems to do this today are not highly efficient or without flaws but it can certainly be done. The research group I am part of, Salesforce Research (formerly MetaMind), have a model that does this &quot;accidentally&quot; - and there&#x27;s even an example image of a bird[3]! The model is only meant to provide a caption for an image, not to segment the image into…</p><p><a href="https://hackerpaper.kaipfister.de/p/1612.01887/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV