Y. Bai, L. Jie, V. Chandrasekhar, Y. Lou, S. Wang, L. Duan, T. Huang, A. Kot, "Deep Regional Feature Pooling for Video Matching", Proceedings of the IEEE Conference on Image Processing 2017, Beijing, China
Abstract:
In this work, we study the problem of deep global descriptors for video matching with regional feature pooling. We aim to analyze the joint effect of ROI (Region of Interest) size and pooling mo- ment on video matching performance. To this end, we propose to mathematically model the distribution of video matching function with a pooling function nested in. Matching performance can be es- timated by the separability of these class-conditional distributions between matching and non-matching pairs. Empirical studies on the challenging MPEG CDVA dataset demonstrate that performance trends are consistent between the estimation and experimental re- sults, though the theoretical model is largely simplified compared to video matching and retrieval in practice.