Discriminative Segment Annotation in Weakly Labeled Video

• Published in: 2013 IEEE Conference on Computer Vision and Pattern Recognition pp. 2483 - 2490
• Main Authors: Tang, Kevin, Sukthankar, Rahul, Yagnik, Jay, Li Fei-Fei
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2013
• Subjects: Cranes; Image segmentation; Lead; Noise; Spatiotemporal phenomena; Training

The ubiquitous availability of Internet video offers the vision community the exciting opportunity to directly learn localized visual concepts from real-world imagery. Unfortunately, most such attempts are doomed because traditional approaches are ill-suited, both in terms of their computational cha...