Publications (2017/01-2017/12)
20032004200520062007200820092010201120122013201420152016201720182019202020212022
Journal Papers
- Cross-View Human Action Recognition from Depth Maps Using Spectral Graph Sequences
- Elsevier Journal of Computer Vision and Image Understanding (CVIU), vol. 154, pp. 108-126, Jan. 1, 2017
Conference Proceedings (peer reviewed)
- A Unified Network for Multi-Speaker Speech Recognition with Multi-Channel Recordings
- Proc. APSIPA, pp. 1304-1307, Dec. 11, 2017
- Multimodal Speech Recognition Using Mouth Images from Depth Camera
- Proc. APSIPA, pp. 1233-1236, Dec. 11, 2017
- User Adaptation of Convolutional Neural Network for Human Activity Recognition
- 2017 25th European Signal Processing Conference (EUSIPCO), pp. 753-757, Oct. 26, 2017
- CTC Network with Statistical Language Modeling for Action Sequence Recognition in Videos
- Proc. ACM Multimedia Thematic Workshop, pp. 393-401, Oct. 23, 2017
- Boredom Recognition based on Users' Spontaneous Behaviors in Multiparty Human-Robot Interactions
- Proc. MultiMedia Modeling (MMM), pp. 677-689, Jan. 4, 2017
Conference Proceedings (non-refereed)
- TokyoTech-AIST at TRECVID 2017: Multimedia Event Detection Using Deep CNNs and Zero-Shot Classifiers
- Proc. TRECVID workshop, pp. 1-6, Nov. 13, 2017
- Development of a cloud detection system utilizing image recognition technology
- V WORKSHOP ON ROBOTIC AUTONOMOUS OBSERVATORIES, Oct., 2017
Domestic Conference Proceedings
- Action Sequence Recognition in Videos by Combining a CTC Network with a Statistical Language Model
- Technical Reports of IEICE PRMU, vol. 117, no. 362, pp. 1-6, Dec. 16, 2017
- Joint training of speaker separation and speech recognit ion based on deep learning
- ASJ 2017 Autumn Meeting, pp. 63-64, Sep. 25, 2017
- Speaker Separation in Multi-Channel Environment Using Deep Learning
- Technical Reports of IPSJ SLP, vol. 115, no. 11, pp. 1-6, Feb. 18, 2017
Invited Talks & Tutorials
- Video Information Retrieval
- The 2017 IEEE SPS Summer School on Visual Image Search and Visual Analytics (VISVA2017), Jul. 5, 2017