Eye Fixation Assisted Video Saliency Detection via Total Variation-Based Pairwise Interaction

• Published in: IEEE transactions on image processing Vol. 27; no. 10; pp. 4724 - 4739
• Main Authors: Qiu, Wenliang, Gao, Xinbo, Han, Bing
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.10.2018
• Subjects: conditional random fields; Data models; eye fixation; Gaze tracking; geodesic distance; Image color analysis; Optical imaging; pairwise interaction; Saliency detection; total variation; Tracking; Video saliency detection; Visualization; weakly supervised learning

As human visual attention is naturally biased toward foreground objects in a scene, it can be used to extract salient objects in video clips. In this paper, we proposed a weakly supervised learning-based video saliency detection algorithm utilizing eye fixations information from multiple subjects. O...