Learning object class detectors from weakly annotated video
2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Alessandro Prest,C. Leistner,J. Civera,C. Schmid,V. Ferrari
Issue Date:June 2012
Object detectors are typically trained on a large set of still images annotated by bounding-boxes. This paper introduces an approach for learning object detectors from real-world web videos known only to contain objects of a target class. We propose a full...