Alessandro Prest Christian Leistner Javier Civera 0001 Cordelia Schmid Vittorio Ferrari Learning object class detectors from weakly annotated video. 3282-3289 2012 CVPR https://doi.org/10.1109/CVPR.2012.6248065 https://doi.ieeecomputersociety.org/10.1109/CVPR.2012.6248065 conf/cvpr/2012 db/conf/cvpr/cvpr2012.html#PrestLCSF12