Presentation	2016-12-16 What technology is desired for non-visible concept recognition Atsushi Hashimoto,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	This paper discusses strategies for recognizing non-visible concept recognition. Owing to the recent innovation in deep learning technologies, visible concepts (i.e., objects and simple actions, have been recognizable. On the other hand, non-visible concepts (i.e., human psychological states, adjectives, object conditions) are not well studies due to its difficulty in determination of ground truth. We discuss a strategy that uses a vast amount of multimedia contents on the web.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	weakly supervised learning / non-visible concept recognition / word grounding
Paper #	PRMU2016-119
Date of Issue	2016-12-08 (PRMU)

Conference Information
Committee	PRMU
Conference Date	2016/12/15(2days)
Place (in Japanese)	(See Japanese page)
Place (in English)
Topics (in Japanese)	(See Japanese page)
Topics (in English)
Chair	Eisaku Maeda(NTT)
Vice Chair	Seiichi Uchida(Kyushu Univ.) / Hironobu Fujiyoshi(Chubu Univ.)
Secretary	Seiichi Uchida(Kyoto Univ.) / Hironobu Fujiyoshi(NTT)
Assistant	Masaki Oonishi(AIST) / Takuya Funatomi(NAIST)

Paper Information
Registration To	Technical Committee on Pattern Recognition and Media Understanding
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	What technology is desired for non-visible concept recognition
Sub Title (in English)
Keyword(1)	weakly supervised learning
Keyword(2)	non-visible concept recognition
Keyword(3)	word grounding
1st Author's Name	Atsushi Hashimoto
1st Author's Affiliation	Kyoto University(Kyoto Univ.)
Date	2016-12-16
Paper #	PRMU2016-119
Volume (vol)	vol.116
Number (no)	PRMU-366
Page	pp.pp.27-28(PRMU),
#Pages	2
Date of Issue	2016-12-08 (PRMU)