Learning unsupervised video object segmentation through visual attention

• Main Authors: WANG, Wenguan, SONG, Hongmei, ZHAO, Shuyang, SHEN, Jianbing, ZHAO, Sanyuan, HOI, Steven C. H., LING, Haibin
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2019
• Subjects: Segmentation; Grouping and Shape; Image and Video Synthesis; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sol_research/3162; https://ink.library.smu.edu.sg/context/sol_research/article/5120/viewcontent/UVOS_cvpr19_av.pdf
• Institution: Singapore Management University

This paper conducts a systematic study on the role of visual attention in Unsupervised Video Object Segmentation (UVOS) tasks. By elaborately annotating three popular video segmentation datasets (DAVIS, Youtube-Objects and SegTrack V2) with dynamic eye-tracking data in the UVOS setting, for the firs...