A fusion architecture based on TBM for camera motion classification
Image and Vision Computing
Efficient spatiotemporal-attention-driven shot matching
Proceedings of the 15th international conference on Multimedia
Towards efficient context-specific video coding based on gaze-tracking analysis
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
Automatic Labeling of Colonoscopy Video for Cancer Detection
IbPRIA '07 Proceedings of the 3rd Iberian conference on Pattern Recognition and Image Analysis, Part I
Attention-driven action retrieval with DTW-based 3d descriptor matching
MM '08 Proceedings of the 16th ACM international conference on Multimedia
Place retrieval with graph-based place-view model
MIR '08 Proceedings of the 1st ACM international conference on Multimedia information retrieval
Object motion detection using information theoretic spatio-temporal saliency
Pattern Recognition
A multicue Bayesian state estimator for gaze prediction in open signed video
IEEE Transactions on Multimedia
An approach to intelligently crop and scale video for broadcast applications
Proceedings of the 2010 ACM Symposium on Applied Computing
Travelmedia: An intelligent management system for media captured in travel
Journal of Visual Communication and Image Representation
Contextual cropping and scaling of TV productions
Multimedia Tools and Applications
Spatiotemporal saliency detection and salient region determination for H.264 videos
Journal of Visual Communication and Image Representation
Hi-index | 0.00 |
This paper presents a framework for automatic video region-of-interest determination based on visual attention model. We view this work as a preliminary step towards the solution of high-level semantic video analysis. Facing such a challenging issue, in this work, a set of attempts on using video attention features and knowledge of computational media aesthetics are made. The three types of visual attention features we used are intensity, color, and motion. Referring to aesthetic principles, these features are combined according to camera motion types on the basis of a new proposed video analysis unit, frame-segment. We conduct subjective experiments on several kinds of video data and demonstrate the effectiveness of the proposed framework.