Weakly supervised visual-auditory fixation prediction with multigranularity perception

Video saliency detection models have been achieving steady, significant improvements thanks to rapid advances indeep learning and the wide availability of large-scale training sets. However, deep learning-based visual-audio fixationprediction is still in its infancy. At present, only a few visual-audio sequences have been furnished, with real fixationsbeing recorded in real visual-audio environments. Hence, it would neither be efficient nor necessary to recollect realfixations under the same visual-audio circumstances. To address this problem, this paper promotes a novel weaklysupervised approach that alleviates the demand for large-scale training sets for visual-audio model training. By usingonly the video category tags, we propose the selectivec