tag:blogger.com,1999:blog-15418143.post7962697345864684356..comments2024-06-04T04:08:36.236-05:00Comments on Tombone's Computer Vision Blog: Recognition by Association via Learning Per-exemplar DistancesTomasz Malisiewiczhttp://www.blogger.com/profile/17507234774392358321noreply@blogger.comBlogger3125tag:blogger.com,1999:blog-15418143.post-31301768714970151642008-04-17T20:51:00.000-05:002008-04-17T20:51:00.000-05:00Hey Tomasz - congrats on cvpr!Hey Tomasz - congrats on cvpr!Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-15418143.post-64262727011701007752008-04-14T19:44:00.000-05:002008-04-14T19:44:00.000-05:00Hi Regis,Finding the distance weights, or learning...Hi Regis,<BR/><BR/>Finding the distance weights, or learning a distance function per-exemplars, is not that slow. The bottleneck is the distance computations. Given 13,000 exemplars spanning 171 unique labels whose distance functions I want to learn and 30,000 negative segments, it takes less than 6 hours to learn the weights. Since each learning problem is independent I never compute the entire (13,000 x 43,000 x 14) elementary-distance matrix.<BR/><BR/>This is a total of 13,000x15 different numbers that are learned.<BR/><BR/>In terms of using LabelMe, a problem is that it is a 'growing' dataset. However you can still use another algorithm (maybe get code from the author) and run it on your subset of LabelMe.Tomasz Malisiewiczhttps://www.blogger.com/profile/17507234774392358321noreply@blogger.comtag:blogger.com,1999:blog-15418143.post-66414372268487817742008-04-10T02:58:00.000-05:002008-04-10T02:58:00.000-05:00Hi,I just read your CVPR2008 paper and I got a few...Hi,<BR/>I just read your CVPR2008 paper and I got a few questions that I'd like to ask you. Do not take them as critics, I am a PhD student just like you and I hate paper bashing. Plus your results look great, which is something that should be respected.<BR/><BR/>Here we go:<BR/><BR/>1) Could you give me a hint at the approximate time that is required to compute the distance weights? That must be awfully long, right?<BR/><BR/>2) Similarly to your paper, I am currently working on an approach that aims at matching candidate object parts to one or several model parts. (The method that I am investigating is way different than yours though. The meat of my work is the localisation of interesting parts in the image and its representation, and I use very simple distance functions between my representations). This is for BMVC2008 (deadline in two weeks). I am having trouble finding ways to compare my results to others, as I guess you must have as well since no one uses the same LabelMe dataset. So:<BR/>a) As a paper author, I was wondering if you had any reproaches from a reviewer about the lack of comparison with existing methods?<BR/>b) In the future, will you consider releasing the subset of the LabelMe dataset that you used so that others can compare their results with yours?<BR/><BR/>Thanks<BR/>RĂ©gis<BR/>PS: I really like the idea of a research blog. I have thought about starting one for some time now because I feel like it could be a great tool for personal scientific conversations outside of conferences.Anonymousnoreply@blogger.com