Visual Descriptors in Methods for Video Hyperlinking

Varování

Publikace nespadá pod Fakultu sportovních studií, ale pod Fakultu informatiky. Oficiální stránka publikace je na webu muni.cz.

Autoři	GALUŠČÁKOVÁ Petra BATKO Michal ČECH Jan MATAS Jiří NOVÁK David PECINA Pavel
Rok publikování	2017
Druh	Článek ve sborníku
Konference	Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval
Fakulta / Pracoviště MU	Fakulta informatiky
Citace
Doi	http://dx.doi.org/10.1145/3078971.3079026
Obor	Informatika
Klíčová slova	Video retrieval; Hyperlinking; Information retrieval; Image processing
Popis	In this paper, we survey different state-of-the-art visual processing methods and utilize them in hyperlinking. Visual information, calculated using Features Signatures, SIMILE descriptors and convolutional neural networks (CNN), is utilized as similarity between video frames and used to find similar faces, objects and setting. Visual concepts in frames are also automatically recognized and textual output of the recognition is combined with search based on subtitles and transcripts. All presented experiments were performed in the Search and Hyperlinking 2014 MediaEval task and Video Hyperlinking 2015 TRECVid task.
Související projekty:	Centrum pro multi-modální interpretaci dat velkého rozsahu