Presentation | 2018-03-20 [Invited Talk] Progress of Research on Cross-modal Scene Analysis Kunio Kashino, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The problem of scene analysis means to understand, or describe, various external objects or events associated with spatial and temporal information based on sensory input. It has been a major research topic over the past decades in multiple fields. In the engineering context, as symbolically shown in the terms such as computer vision and computational auditory scene analysis, a major approach has been defining the problem within a single modality and seeking its solutions by mathematical or heuristic means, and many multimodal approaches that use multiple types of sensory input in parallel have also been reported. However, it is still a hard problem when we consider, for example, understanding the scene as well as we humans do in the natural environment in our daily life, and it is likely that a breakthrough is needed to solve it. Against this background, another type of approach taking advantages of multiple modalities has emerged in recent years, supported by the rapid progress of deep learning technologies. In this talk, we call it cross-modal scene analysis. We review some of such works, and discuss potential implications and possibilities of this new research direction. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | scene analysis / hashing / multi-modality / cross-modality / deep learning |
Paper # | EA2017-166,SIP2017-175,SP2017-149 |
Date of Issue | 2018-03-12 (EA, SIP, SP) |
Conference Information | |
Committee | SIP / EA / SP / MI |
---|---|
Conference Date | 2018/3/19(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Speech, Engineering/Electro Acoustics, Signal Processing, and Related Topics [SIP, EA, SP]/ Medical Image Engineering, Analysis, Recognition, etc. [MI] |
Chair | Masahiro Okuda(Univ. of Kitakyushu) / Suehiro Shimauchi(NTT) / Yoichi Yamashita(Ritsumeikan Univ.) / Kensaku Mori(Nagoya Univ.) |
Vice Chair | Shogo Muramatsu(Niigata Univ.) / Naoyuki Aikawa(TUS) / Mitsunori Mizumachi(Kyutech) / Hiroki Mori(Utsunomiya Univ.) / Yoshiki Kawata(Tokushima Univ.) / Yuichi Kimura(Kinki Univ.) |
Secretary | Shogo Muramatsu(Chiba Inst. of Tech.) / Naoyuki Aikawa(Takushoku Univ.) / Mitsunori Mizumachi(Akita Pref. Univ.) / Hiroki Mori(Shizuoka Inst. of Science and Tech.) / Yoshiki Kawata(Shizuoka Univ.) / Yuichi Kimura(Meijo Univ.) |
Assistant | Masayoshi Nakamoto(Hiroshima Univ.ひろ) / TREVINO Jorge(Tohoku Univ.) / Nobutaka Ito(NTT) / Kei Hashimoto(Nagoya Inst. of Tech.) / Satoshi Kobashikawa(NTT) / Ryo Haraguchi(Univ. of Hyogo) / Yasushi Hirano(Yamaguchi Univ.) |
Paper Information | |
Registration To | Technical Committee on Signal Processing / Technical Committee on Engineering Acoustics / Technical Committee on Speech / Technical Committee on Medical Imaging |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | [Invited Talk] Progress of Research on Cross-modal Scene Analysis |
Sub Title (in English) | |
Keyword(1) | scene analysis |
Keyword(2) | hashing |
Keyword(3) | multi-modality |
Keyword(4) | cross-modality |
Keyword(5) | deep learning |
1st Author's Name | Kunio Kashino |
1st Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
Date | 2018-03-20 |
Paper # | EA2017-166,SIP2017-175,SP2017-149 |
Volume (vol) | vol.117 |
Number (no) | EA-515,SIP-516,SP-517 |
Page | pp.pp.353-353(EA), pp.353-353(SIP), pp.353-353(SP), |
#Pages | 1 |
Date of Issue | 2018-03-12 (EA, SIP, SP) |