Publication

Publication by type

2017

Mayu Otani, Yuta Nakashima, Esa Rahtu, and Janne Heikkilä
Fine-grained video retrieval for multi-clip video
Proc. Workshop on Closing the Loop Between Vision and Language (CLVL) at ICCV, 2 pages, Nov. 2017
Norihiko Kawai, Tomokazu Sato, Yuta Nakashima, and Naokazu Yokoya
Augmented reality marker hiding with texture deformation
IEEE Transactions on Visualization and Computer Graphics, vol. 23, no. 10, 2288-2300 pages, Oct. 2017
[PDF] DOI: 10.1109/TVCG.2016.2617325
Copyright © 2016 IEEE (Please follow IEEE\\\'s copyright term to reuse this paper)
Yuta Nakashima, Fumio Okura, Norihiko Kawai, Hiroshi Kawasaki, Ambrosio Blanco, and Katsushi Ikeuchi
Realtime novel view synthesis with eigen-texture regression
Proc. British Machine Vision Conference, 12 pages, Sep. 2017
[PDF]
Mayu Otani, Yuta Nakashima, Esa Rahtu, Janne Heikkilä, and Naokazu Yokoya
Unsupervised video summarization using deep video features
画像の認識・理解シンポジウム (MIRU) Extended Abstracts, PS3-35, 4 pages, Aug. 2017
Mayu Otani, Yuta Nakashima, Esa Rahtu, and Janne Heikkilä
Video question answering to find a desired video segment
Proc. Open Knowledge Base and Question Answering Workshop (OKBQA) at SIGIR (demo paper), 2 pages, Aug. 2017
Thiwat Rongsirigul, Yuta Nakashima, Tomokazu Sato, and Naokazu Yokoya
Novel view synthesis with light-weight view-dependent texture mapping for a stereoscopic HMD
Proc. IEEE International Conference on Multimedia and Expo, 6 pages, Jul. 2017
[PDF] DOI: 10.1007/s11042-016-4061-3
Mayu Otani, Yuta Nakashima, Tomokazu Sato, and Naokazu Yokoya
Video summarization using textual descriptions for authoring video blogs
Multimedia Tools and Applications, vol. 76, no. 9, 12097-12115 pages, May 2017
[Project] DOI: 10.1007/s11042-016-4061-3
Fabian Lorenzo Dayrit, Yuta Nakashima, Tomokazu Sato, and Naokazu Yokoya
Increasing pose comprehension through augmented reality reenactment
Multimedia Tools and Applications, vol. 76, no. 1, 1291-1312 pages, Jan. 2017
[Project] DOI: 10.1007/s11042-015-3116-1
The final publication is available at Springer via http://dx.doi.org/10.1007/s11042-015-3116-1
Fabian L. Dayrit, Ryosuke Kimura, Yuta Nakashima, Ambrosio Blanco, Hiroshi Kawasaki, and Katsushi Ikeuchi
ReMagicMirror: Action learning using human reenactment with the mirror metaphor
Proc. International Conference on Multimedia Modeling, 303-315 pages, Jan. 2017
[Project] DOI: 10.1007/978-3-319-51811-4_25

2016

Mayu Otani, Yuta Nakashima, Esa Rahtu, Janne Heikkilä, and Naokazu Yokoya
Video summarization using deep semantic features
arXiv:1609.08758 (to appear in ACCV 2016), 16 pages, Sep. 2016
[PDF] [Project] [arXiv]
Mayu Otani, Yuta Nakashima, Esa Rahtu, Janne Heikkilä, and Naokazu Yokoya
Learning joint representations of videos and sentences with web image search
arXiv:1608.02367 (to appear in VSM in conjunction with ECCV 2016), 16 pages, Aug. 2016
[PDF] [Project] [arXiv]
Antonio Tejero-de-Pablos, Yuta Nakashima, Tomokazu Sato, and Naokazu Yokoya
Human action recognition-based video summarization for RGB-D personal sports video
Proc. IEEE International Conference on Multimedia and Expo (ICME), 6 pages, Jul. 2016
[PDF] [Project]
Antonio Tejero-de-Pablos, Yuta Nakashima, Naokazu Yokoya, Francisco-Javier Díaz-Pernas, and Mario Martínez-Zarzuela
Flexible human action recognition in depth video sequences using masked joint trajectories
EURASIP Journal on Image and Video Processing, Vol. 2016, No. 1, 12 pages, Jul. 2016
[PDF] [Project] DOI: 10.1186/s13640-016-0120-y
Yuta Nakashima, Noboru Babaguchi, and Jianping Fan
Privacy protection for social video via background estimation and CRF-based videographer’s intention modeling
IEICE Transactions on Information and Systems, Vol. E99.D, No. 4, pp. 1221-1233, Apr. 2016
[PDF] [Project] DOI: 10.1587/transinf.2015EDP7378
Copyright © 2016 IEICE
Keita Katagiri, Yuta Nakashima, Tomokazu Sato, and Naokazu Yokoya
Novel view synthesis based on view-dependent texture mapping with geometry-aware color continuity
Transactions of the Virtual Reality Society of Japan, Vol. 21, No. 1, pp. 153-162 , Mar. 2016
[PDF] [Project]
田中 隆寛, 河合 紀彦, 中島 悠太, 佐藤 智和, 横矢 直和
畳み込みニューラルネットワークを用いた修復失敗領域の自動検出による画像修復の反復的適用
電子情報通信学会 技術研究報告, PRMU2015-160, pp. 133-138, Feb. 2016
Hiraki Takehara, Yuta Nakashima, Tomokazu Sato, and Naokazu Yokoya
Generating a 3D shape template of a moving and deforming object from an RGB-D image sequence
IS&T Electronic Imaging (3D Image Processing, Measurement (3DIPM), and Applications 2016), 7 pages, Feb. 2016
[PDF] [Project] DOI: 10.2352/ISSN.2470-1173.2016.21.3DIPM-407
Yuta Nakashima, Tomoaki Ikeno, and Noboru Babaguchi
Evaluating protection capability for visual privacy information
IEEE Security & Privacy, Vol. 14, No. 1, pp. 55-61, Feb. 2016
[PDF] [Project] DOI: 10.1109/MSP.2016.3
Copyright © 2016 IEEE (Please follow IEEE\'s copyright term to reuse this paper)

2015

田中 隆寛, 河合 紀彦, 中島 悠太, 佐藤 智和, 横矢 直和
画像修復における畳み込みニューラルネットワークを用いた修復失敗領域の自動検出
映像情報メディア学会2015年冬季大会講演予稿集, 11B-3, pp. 133-138, Dec. 2015
大谷 まゆ, 中島 悠太, 佐藤 智和, 横矢 直和
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
電気関係学会2015年関西連合大会講演論文集, P-25, pp. 388-389, Nov. 2015
[Project]
武原 光, 中島 悠太, 佐藤 智和, 横矢 直和
単一のRGB-Dカメラを用いた非剛体物体の3次元形状復元
第32回センシングフォーラム, pp. 135-140, Sep. 2015
[Project]
Keita Katagiri, Yuta Nakashima, Tomokazu Sato, and Naokazu Yokoya
View-dependent texture mapping-based novel view synthesis with geometry-aware color continuity
画像の認識・理解シンポジウム(MIRU)講演論文集 Extended Abstract, SS1-12, 2 pages, Jul. 2015
[Project]
Yuta Nakashima and Naokazu Yokoya
Point trajectory-based inference of what the videographer wanted to capture
画像の認識・理解シンポジウム(MIRU)講演論文集 Extended Abstract, SS1-13, 2 pages, Jul. 2015
[Project]
Mayu Otani, Yuta Nakashima, Tomokazu Sato, and Naokazu Yokoya
Textual description-based video summarization for video blogs
Proc. 2015 IEEE International Conference on Multimedia and Expo (ICME), 6 pages, Jun. 2015
[PDF] [Project] DOI: 10.1109/ICME.2015.7177493
Copyright © 2015 IEEE (Please follow IEEE\'s copyright term to reuse this paper)
Yuta Nakashima, Tatsuya Koyama, Naokazu Yokoya, and Noboru Babaguchi
Facial expression preserving privacy protection using image melding
2015 IEEE International Conference on Multimedia and Expo (ICME), 6 pages, Jun. 2015
[PDF] [Project] DOI: 10.1109/ICME.2015.7177394
Copyright © 2015 IEEE (Please follow IEEE\'s copyright term to reuse this paper)