Imperial College London > Talks@ee.imperial > Featured talks > Learning object class detectors from consumer video
Log inImperial users Other users No account?Information onFinding a talk Adding a talk Syndicating talks Who we are Everything else |
Learning object class detectors from consumer videoAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Patrick Kelly. Object class detectors are traditionally trained from still images with bounding-boxes marking the location of objects, which are time-consuming to annotate. In this talk I will present techniques for learning detectors from real-world web videos known only to contain objects of a target class. Because of the temporal continuity, video enables to segment the object from the background more easily, relieving the need for location annotations. Because frames extracted from web videos are often of lower quality than still images taken by a good camera, we formulate the learning problem as a domain adaptation task. We experimentally demonstrate that training a detector from a combination of weakly annotated videos and fully annotated still images leads to better performance compared to training from still images alone. http://groups.inf.ed.ac.uk/calvin/ Vittorio Ferrari is a Reader at the School of Informatics of the University of Edinburgh which he joined in December 2011. He leads the CALVIN research group on visual learning. He received his PhD from ETH Zurich in 2004 and was a post-doctoral researcher at INRIA Grenoble in 2006-2007 and at the University of Oxford in 2007-2008. Between 2008 and 2012 he was Assistant Professor at ETH Zurich, funded by a Swiss National Science Foundation Professorship grant. In 2012 he received the prestigious ERC Starting Grant, and the best paper award from the European Conference in Computer Vision for his work on large-scale image auto-annotation. He is the author of over 60 technical publications, most of them in the highest ranked conferences and journals in computer vision and machine learning. He regularly serves as an Area Chair for the major vision conferences. This talk is part of the Featured talks series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsCAS Talks Experimental Solid State Group Seminars (Dept. of Physics) IEEE Magnetics Society Distinguished Lecturer VisitsOther talksAdvanced Speech-Audio Processing in Mobile Phones and Hearing Aids: Synergies and Distinctions TV white spaces in the UK: The first steps to dynamic spectrum access Degree-Based Network Models ISCAS Practce Talk |