{"id":1199,"date":"2012-06-07T19:17:46","date_gmt":"2012-06-07T19:17:46","guid":{"rendered":"http:\/\/eccv2012.unifi.it\/?page_id=1199"},"modified":"2012-10-05T06:36:38","modified_gmt":"2012-10-05T06:36:38","slug":"additive-kernels-and-explicit-embeddings-for-large-scale-computer-vision-problems","status":"publish","type":"page","link":"http:\/\/eccv2012.unifi.it\/program\/tutorials\/additive-kernels-and-explicit-embeddings-for-large-scale-computer-vision-problems\/","title":{"rendered":"Additive Kernels and Explicit Embeddings for Large Scale Computer Vision Problems"},"content":{"rendered":"

Organizers<\/strong>:\u00a0Jianxin Wu\u00a0(Nanyang Technological University, Singapore)<\/em>,\u00a0Andrea Vedaldi\u00a0(Univ. of Oxford, UK)<\/em>,\u00a0Subhransu Maji\u00a0(TTI Chicago, USA)<\/em>,\u00a0Florent Perronnin\u00a0(Xerox Research Center Europe)
\n<\/em>Duration<\/strong>: half day
\nAbstract<\/strong>:\u00a0It is generally accepted in our community that: in many vision tasks, more training images will usually lead\u00a0to better performance. Furthermore, recent advances have shown that additive kernel and explicit\u00a0embeddings are the best performers in most visual classification tasks\u2013a fact that has been repeatedly\u00a0verified by various papers and research-oriented public contests (e.g., the ImageNet Large Scale Visual\u00a0Recognition Challenge.) In this tutorial, we will introduce the theories, applications, algorithms, software,\u00a0and practical issues of using additive kernels and explicit embeddings in various computer vision\u00a0domains, especially when the problem scale is very large.<\/p>\n

Outline:<\/p>\n