An Efficient Spatiotemporal Attention Model and Its Application to Shot Matching

Authors:
Shan Li;Moon-Chuen Lee
Affiliations:
Chinese Univ. of Hong Kong, Hong Kong;-
Venue:
IEEE Transactions on Circuits and Systems for Video Technology
Year:
2007

Citing 0
Cited 6

Object motion detection using information theoretic spatio-temporal saliency

Pattern Recognition
Content-aware video resizing based on salient visual cubes

Journal of Visual Communication and Image Representation
Modelling salient visual dynamics in videos

Multimedia Tools and Applications
Modelling of content-aware indicators for effective determination of shot boundaries in compressed MPEG videos

Multimedia Tools and Applications
The co-attention model for tiny activity analysis

Neurocomputing
Spatiotemporal saliency detection and salient region determination for H.264 videos

Journal of Visual Communication and Image Representation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Within the framework of spatiotemporal attention detection, this paper proposes an efficient method for focus of attention (FOA) detection which involves combining adaptively the spatial and motion attention to form an overall attention map. Without computing motion explicitly, it detects motion attention using the rank deficiency of grayscale gradient tensors. We also propose an attention-driven shot matching method using primarily FOA. Experimental results demonstrate the effectiveness of the proposed FOA detection method and the proposed shot matching approach outperforms other published methods.