Bogdan-Andrei Morosanu, Camelia Lemnaru. From image captioning to video summary using deep recurrent networks and unsupervised segmentation. In Antanas Verikas, Petia Radeva, Dmitry P. Nikolaev, Jianhong Zhou, editors, Tenth International Conference on Machine Vision, ICMV 2017, Vienna, Austria, 13-15 November 2017. Volume 10696 of SPIE Proceedings, SPIE, 2017. [doi]
Abstract is missing.