Learning and Recognition in Vision

LEAR is a joint team of INRIA Grenoble - RhôneAlpes and the LJK laboratory, a joint research unit of the Centre National de Recherche Scientifique (CNRS), the Institut National Polytechnique de Grenoble (INPG), the Université Joseph Fourier (UJF) and Université Pierre-Mendès-France (UPMF).

LEAR's main focus is learning based approaches to visual object recognition and scene interpretation, particularly for object category detection, image retrieval, video indexing and the analysis of humans and their movements. Understanding the content of everyday images and videos is one of the fundamental challenges of computer vision and we believe that significant advances will be made over the next few years by combining state of the art image analysis tools with emerging machine learning and statistical modeling techniques. For more information see our annual report and research page.

Highlights

ImageCLEF picture For both the Photo Annotation and Image Retrieval tasks of ImageCLEF'09 Lear obtained a second place among the 19 participating teams for each task. The methods that were used are described in this paper.
iccv'09 logo Recent publications in major computer vision conferences: 4 ICCV'09 papers (2 orals), 3 BMVC'09 papers (2 orals), and 3 CVPR'09 papers. See publications web page for details.
bottle detection Lear got excellent results on Trecvid 2008. The method used is described in this paper.
bottle detection In the PASCAL VOC 2008 Lear won the detection contest for 11 out of 20 classes (see example detections here) and the classification contest for 7 out of 20 classes.
cvpr eccv 2008 Recent publications in the major computer vision conferences: 4 ECCV'08 and 4 CVPR'08 papers. See publications web page for details.
images Development of an image indexing system that searches in real time for similar images in very large databases. It is currently transferred and tested by the Start-Up MilPix.

Our image search demo on 10,000,000 images: Bigimbaz.

come Organization of an International Workshop on Object Recognition, Como, May 2008.
logo moutons Winner of PASCAL VOC 2007 image classification competition. LEAR's approach won the classification contest for 19 of the 20 object classes.