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

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-tube detector can temporally p...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Le, Duan, Xuhuan, Zhang, Qilin, Niu, Zhenxing, Hua, Gang, Zheng, Nanning
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2018
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5982167/
https://www.ncbi.nlm.nih.gov/pubmed/29789447
http://dx.doi.org/10.3390/s18051657

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5982167/
https://www.ncbi.nlm.nih.gov/pubmed/29789447
http://dx.doi.org/10.3390/s18051657

Ejemplares similares