Complex event detection using semantic saliency and nearly-isotonic SVM

Publication Type:
Conference Proceeding
32nd International Conference on Machine Learning, ICML 2015, 2015, 2 pp. 1348 - 1357
Issue Date:
Full metadata record
Copyright © 2015 by the author(s). We aim to detect complex events in long Internet videos that may last for hours. A major challenge in this setting is that only a few shots in a long video are relevant to the event of interest while others are irrelevant or even misleading. Instead of indifferently pooling the shots, we first define a novel notion of semantic saliency that assesses the relevance of each shot with the event of interest. We then prioritize the shots according to their saliency scores since shots that are semantically more salient are expected to contribute more to the final event detector. Next, we propose a new isotonic regularizer that is able to exploit the semantic ordering information. The resulting nearly-isotonic SVM classifier exhibits higher discriminative power. Computationally, we develop an efficient implementation using the proximal gradient algorithm, and we prove new, closed-form proximal steps. We conduct extensive experiments on three real-world video datasets and confirm the effectiveness of the proposed approach.
Please use this identifier to cite or link to this item: