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

Article English OPEN
Le Wang ; Xuhuan Duan ; Qilin Zhang ; Zhenxing Niu ; Gang Hua ; Nanning Zheng (2018)
  • Publisher: MDPI AG
  • Journal: Sensors, volume 18, issue 5 (issn: 1424-8220, eissn: 1424-8220)
  • Related identifiers: doi: 10.3390/s18051657, pmc: PMC5982167
  • Subject: LSTM | action localization | 3D ConvNets | TP1-1185 | Chemical technology | action segmentation | Article

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