Segment-Tube: Spatio-Temporal Action Localization in Untrimmed Videos with Per-Frame Segmentation

Article English OPEN
Wang, Le; Duan, Xuhuan; Zhang, Qilin; Niu, Zhenxing; Hua, Gang; Zheng, Nanning;
(2018)

Inspired by the recent spatio-temporal action localization efforts with tubelets (sequences of bounding boxes), we present a new spatio-temporal action localization detector Segment-tube, which consists of sequences of per-frame segmentation masks. The proposed Segment-... View more
Share - Bookmark