tag:blogger.com,1999:blog-15418143.post2854664141789313683..comments2024-03-09T05:42:18.102-05:00Comments on Tombone's Computer Vision Blog: Scene Prototype Models for Indoor Image RecognitionTomasz Malisiewiczhttp://www.blogger.com/profile/17507234774392358321noreply@blogger.comBlogger4125tag:blogger.com,1999:blog-15418143.post-19059506096298391112009-10-24T04:01:24.537-05:002009-10-24T04:01:24.537-05:00While I think this approach does use a reasonably ...While I think this approach does use a reasonably sized set of images, it is somewhat orthogonal to the gargantuan datasets used in Hays/Efros-style image matching or Torralba-style 80 million tiny image approaches.<br /><br />I think that this paper is more similar to Torralba's work on context regarding object information given the gist. The most similar prior work to this from Torralba's group is Bryan Russell's Scene Alignment paper from NIPS.<br /><br />Because they are using prototypes, this paper has a nice link to representational theories of concepts from psychology.<br /><br />In the next decade or so we will see these types of deformable scene models applied to millions of images. These type of work might even come out of Torralba's group -- if I don't beat them to it!Tomasz Malisiewiczhttps://www.blogger.com/profile/17507234774392358321noreply@blogger.comtag:blogger.com,1999:blog-15418143.post-40614135780605194042009-10-23T20:20:37.476-05:002009-10-23T20:20:37.476-05:00This is one of attempt in exploiting the benefit o...This is one of attempt in exploiting the benefit of huge visual space (from similar images) into recognition/detection? I see Torralba's group is pursuiting this direction couple years.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-15418143.post-21878562323986900332009-10-20T10:34:26.845-05:002009-10-20T10:34:26.845-05:00Yeah this work reminds me of the Deformable Part M...Yeah this work reminds me of the Deformable Part Models that Deva and Pedro have worked on!Tomasz Malisiewiczhttps://www.blogger.com/profile/17507234774392358321noreply@blogger.comtag:blogger.com,1999:blog-15418143.post-17253425993749239562009-10-20T06:41:56.652-05:002009-10-20T06:41:56.652-05:00Isn't it similar to the part-based detector wo...Isn't it similar to the part-based detector works. I guess the region prototypes are treated as latent variables.Santoshhttps://www.blogger.com/profile/09446680597463892532noreply@blogger.com