Mayu Otani

View My GitHub Profile

Email: otani.mayu.ob9[at]is.naist.jp

Cybernetics and Reality Engineering (CARE) Lab. at Nara Institute of Science and Technology (NAIST)

Vision and Media Computing Lab. at NAIST (closed)

I'm a third year Ph.D. student advised by Professor Naokazu Yokoya and Professor Kiyoshi Kiyokawa. I'm also a visiting student at Institute for Datability Science, Osaka University. I visited Machine Vision Group, Univ. of Oulu from April 2015 to March 2016. My research interest is video understanding and machine learning. Especially, I'm interested in video summarization using user-generated text.

Aug. 2017 - presenting at Open Knowledge Base and Question Answering Workshop (OKBQA) at SIGIR. Demo: "Video Question Answering to Find a Desired Video Segment"
Aug. 2017 - presenting at The 20th Meeting on Image Recognition and Understanding (MIRU) . Poster: "Unsupervised Video Summarization using Deep Video Features"
Apr. 2017 - joined Institute for Datability Science, Osaka University.
Apr. 2017 - joined Cybernetics and Reality Engineering (CARE) Laboratory, NAIST
Oct. 2016 - accepted to Multimed Tools Appl. "Video Summarization using Textual Descriptions for Authoring Video Blogs"
Aug. 2016 - accepted to ACCV 2016. Poster: "Video Summarization using Deep Semantic Features"
Aug. 2016 - accepted to 4th Workshop on Web-scale Vision and Social Media (VSM) in conjunction with ECCV 2016. Oral + Poster: "Learning Joint Representations of Videos and Sentences with Web Image Search"
Jun. 2015 - presenting at The 2015 IEEE International Conference on Multimedia and Expo (ICME 2015) Poster: "Textual-Description Based Video Summarization for Video Blogs"
Apr. 2015 - at Machine Vision Group, University of Oulu for a year
Apr. 2015 - won encouragement award of the 2015 Kansai Joint Convention of Institutes of Electrical Engineering
Jan. 2015 - won Special Research Award of the Creative and International Competitiveness Project (International Priority Graduate Program)​ "Multimedia abnormal detection for elders via action and pulse recognition"​

Publication

Video Question Answering to Find a Desired Video Segment
M. Otani, Y. Nakashima, E. Rahtu, J. Heikkilä
Open Knowledge Base and Question Answering Workshop (OKBQA) at SIGIR, Aug. 2017
Video Summarization using Textual Descriptions for Authoring Video Blogs
M. Otani, Y. Nakashima, T. Sato, N. Yokoya
Multimedia Tools and Applications, Oct. 2016
Video Summarization using Deep Semantic Features
M. Otani, Y. Nakashima, E. Rahtu, J. Heikkilä, N. Yokoya
Asian Conference on Computer Vision (ACCV), Nov. 2016
Learning Joint Representations of Videos and Sentences with Web Image Search
M. Otani, Y. Nakashima, E. Rahtu, J. Heikkilä, N. Yokoya
Workshop on Web-scale Vision and Social Media (VSM), ECCV 2016
Texture-description based Video Summarization for Video Blogs
M. Otani, Y. Nakashima, T. Sato, N. Yokoya
IEEE International Conference on Multimedia and Expo (ICME), Jul. 2015.
Video Colorization based on Optical Flow and Edge-oriented Color Propagation
M. Otani, H. Hioki.
In Proc. SPIE Computational Imaging XII, vol. 9020, 9 pages , Fob. 2014.

Domestic

Unsupervised Video Summarization using Deep Video Features
Mayu Otani, Yuta Nakashima, Esa Rahtu, Janne Heikkiä, Naokazu Yokoya
画像の認識・理解シンポジウム(MIRU) Extended Abstracts, PS3-35, Aug. 2017.
テキストの内容に沿った重要箇所抽出による映像要約
大谷 まゆ, 中島 悠太, 佐藤 智和, 横矢 直和.
画像の認識・理解シンポジウム(MIRU) Extended Abstracts, PS2-39, Aug. 2016.
ユーザ意図反映のためのテキストに基づく映像要約手法
大谷 まゆ,中島 悠太,佐藤 智和,横矢 直和.
電気関係学会関西連合大会講演論文集, pp. 388-389, Nov. 2015.
テキスト記述を用いてユーザ意図を反映する映像要約
大谷 まゆ,中島 悠太,佐藤 智和,横矢 直和.
電気関係学会関西連合大会講演論文集, pp. 384-385, Nov. 2014.
テキストと映像の類似度を用いた映像要約
大谷 まゆ,中島 悠太,佐藤 智和,横矢 直和.
電子情報通信 学会 技術研究報告, PRMU2014-95, vol. 114, no. 409, pp.99-104, Jan. 2015.
動きベクトル推定とエッジを考慮した色伝播に基づく動画カラリゼーション
大谷 まゆ,日置尋久.
第六回マルチメディア情報ハイディング・エンリッチメント研究会,vol. 112, no. 467, pp. 13-18, Mar. 2013.