Minimum-risk temporal alignment of videos

Publication Type:
Journal Article
Multimedia Tools and Applications, 2018, 77 (12), pp. 14891 - 14906
Issue Date:
Full metadata record
© 2017, Springer Science+Business Media, LLC. Temporal alignment of videos is an important requirement of tasks such as video comparison, analysis and classification. Most of the approaches proposed to date for video alignment leverage dynamic programming algorithms whose parameters are manually tuned. Conversely, this paper proposes a model that can learn its parameters automatically by minimizing a meaningful loss function over a given training set of videos and alignments. For learning, we exploit the effective framework of structural SVM and we extend it with an original scoring function that suitably scores the alignment of two given videos, and a loss function that quantifies the accuracy of a predicted alignment. The experimental results from four video action datasets show that the proposed model has been able to outperform a baseline and a state-of-the-art algorithm by a large margin in terms of alignment accuracy.
Please use this identifier to cite or link to this item: