Compressed-domain visual saliency models: A comparative study
This study addresses the problem of efficient visual saliency modeling for applications like video compression and quality estimation, but it is incremental as it focuses on comparative analysis rather than introducing new methods.
The paper compared eleven compressed-domain visual saliency models and two pixel-domain models on eye-tracking datasets, finding that accurate saliency estimation is possible using partially decoded video bitstreams.
Computational modeling of visual saliency has become an important research problem in recent years, with applications in video quality estimation, video compression, object tracking, retargeting, summarization, and so on. While most visual saliency models for dynamic scenes operate on raw video, several models have been developed for use with compressed-domain information such as motion vectors and transform coefficients. This paper presents a comparative study of eleven such models as well as two high-performing pixel-domain saliency models on two eye-tracking datasets using several comparison metrics. The results indicate that highly accurate saliency estimation is possible based only on a partially decoded video bitstream. The strategies that have shown success in compressed-domain saliency modeling are highlighted, and certain challenges are identified as potential avenues for further improvement.