Didik Purwanto
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Didik Purwanto has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Wen-Hsien Fang
Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan
3 shared publications - Yie-Tarng Chen
Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan
3 shared publications - Rizard Renanda Adhi Pramono
Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan
2 shared publications
Latest Publications
- 29 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 27 (10709908) , 2188
Corrections to “Three-Stream Network With Bidirectional Self-Attention for Action Recognition in Extreme Low Resolution Videos”
Presents corrections to funding agency information for the above named paper.
- 29 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 27 (10709908) , 2188
Corrections to “Three-Stream Network With Bidirectional Self-Attention for Action Recognition in Extreme Low Resolution Videos”
Presents corrections to funding agency information for the above named paper.
- 19 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 26 (8) , 1187-1191
Three-Stream Network With Bidirectional Self-Attention for Action Recognition in Extreme Low Resolution Videos
This letter presents a novel three-stream network for action recognition in extreme low resolution (LR) videos. In contrast to the existing networks, the new network uses the trajectory-spatial network, which is robust against visual distortion, instead of the pose information to complement the two-stream network. Also, the new three-stream network is combined with the inflated 3D ConvNet (I3D) model pre-trained on kinetics to produce more discriminative spatio-temporal features in blurred LR videos. Moreover, a bidirectional self-attention network is aggregated with the three-stream network to further manifest various temporal dependence among the spatio-temporal features. A new fusion strategy is devised as well to integrate the information from the three different modalities. Simulations show that the new architecture outperforms the main state-of-the-art extreme LR action recognition methods on the HMDB-51 and IXMAS datasets.
- 19 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 26 (8) , 1187-1191
Three-Stream Network With Bidirectional Self-Attention for Action Recognition in Extreme Low Resolution Videos
This letter presents a novel three-stream network for action recognition in extreme low resolution (LR) videos. In contrast to the existing networks, the new network uses the trajectory-spatial network, which is robust against visual distortion, instead of the pose information to complement the two-stream network. Also, the new three-stream network is combined with the inflated 3D ConvNet (I3D) model pre-trained on kinetics to produce more discriminative spatio-temporal features in blurred LR videos. Moreover, a bidirectional self-attention network is aggregated with the three-stream network to further manifest various temporal dependence among the spatio-temporal features. A new fusion strategy is devised as well to integrate the information from the three different modalities. Simulations show that the new architecture outperforms the main state-of-the-art extreme LR action recognition methods on the HMDB-51 and IXMAS datasets.
- 28 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 21 (12) , 3122-3135
First-Person Action Recognition With Temporal Pooling and Hilbert–Huang Transform
This paper presents a convolutional neural network (CNN)-based approach for first-person action recognition with a combination of temporal pooling schemes and the Hilbert-Huang transform (HHT). First, the new approach adaptively selects sub-action intervals, treats each channel of the extracted trajectory pooled CNN features as time series and summarizes the temporal dynamic information in each sub-action interval by temporal pooling. Next, the temporal evolution of different sub-action intervals is modeled by rank pooling. Thereafter, to account for the highly dynamic scene changes in first-person videos, the HHT is employed to decompose the ranked pooling features into finite and often few data-dependent functions, called intrinsic mode functions (IMFs), through empirical mode decomposition (EMD). Hilbert spectral analysis is then applied to each IMF component and four salient descriptors are scrutinized and aggregated into the final video descriptor. Such a framework can not only precisely acquire both long- and short-term tendencies but also address the cumbersome significant camera motion in first-person videos to render better accuracy. Furthermore, it works well for complex actions for limited training samples. Simulations show that the proposed approach outperforms the main state-of-the-art methods when applied to four publicly available first-person video datasets.
- 28 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 21 (12) , 3122-3135
First-Person Action Recognition With Temporal Pooling and Hilbert–Huang Transform
This paper presents a convolutional neural network (CNN)-based approach for first-person action recognition with a combination of temporal pooling schemes and the Hilbert-Huang transform (HHT). First, the new approach adaptively selects sub-action intervals, treats each channel of the extracted trajectory pooled CNN features as time series and summarizes the temporal dynamic information in each sub-action interval by temporal pooling. Next, the temporal evolution of different sub-action intervals is modeled by rank pooling. Thereafter, to account for the highly dynamic scene changes in first-person videos, the HHT is employed to decompose the ranked pooling features into finite and often few data-dependent functions, called intrinsic mode functions (IMFs), through empirical mode decomposition (EMD). Hilbert spectral analysis is then applied to each IMF component and four salient descriptors are scrutinized and aggregated into the final video descriptor. Such a framework can not only precisely acquire both long- and short-term tendencies but also address the cumbersome significant camera motion in first-person videos to render better accuracy. Furthermore, it works well for complex actions for limited training samples. Simulations show that the proposed approach outperforms the main state-of-the-art methods when applied to four publicly available first-person video datasets.