A part-based spatial and temporal aggregation method for dynamic scene recognition

Authors

Xiaoming Peng, University of Wollongong
Abdesselam Bouzerdoum, University of WollongongFollow
Son Lam Phung, University of WollongongFollow

RIS ID

146131

Publication Details

X. Peng, A. Bouzerdoum & S. Phung, "A part-based spatial and temporal aggregation method for dynamic scene recognition," Neural Computing and Applications, 2020.

Abstract

© 2020, Springer-Verlag London Ltd., part of Springer Nature. Existing methods for dynamic scene recognition mostly use global features extracted from the entire video frame or a video segment. In this paper, a part-based method is proposed to aggregate local features from video frames.A pre-trained Fast R-CNN model is used to extract local convolutional features from the regions of interest of training images. These features are clustered to locate representative parts. A set cover problem is then formulated to select the discriminative parts, which are further refined by fine-tuning the Fast R-CNN model. Local features from a video segment are extracted at different layers of the fine-tuned Fast R-CNN model and aggregated both spatially and temporally. Extensive experimental results show that the proposed method is very competitive with state-of-the-art approaches.