Recognizing activities in real-world videos is a difficult problem exacerbated by background clutter, changes in camera angle and zoom, occlusion and rapid camera movements. Large corpora of labeled videos can be used to train automated activity recognition systems, but this requires expensive human labor and time. This thesis explores how closed captions that naturally accompany many videos can act as weak supervision that allows automatically collecting “labeled” data for activity recognition. We show that such an approach can improve activity retrieval in soccer videos. Our system requires no manual labeling of video clips and needs minimal human supervision. We also present a novel caption classifier that uses additional linguistic information to determine whether a specific comment refers to an ongoing activity. We demonstrate that combining linguistic analysis and automatically trained activity recognizers can significantly improve the precision of video retrieval.
Masters Thesis, Department of Computer Sciences, University of Texas at Austin. 64 pages.

Sonal Gupta Masters Alumni sonal [at] cs stanford edu