Suhua Tang

Dr. Suhua Tang

Graduate School of Informatics and Engineering, The University of Electro-Communications, Tokyo 182-8585, Japan
orcid

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 February 2019 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
PDF file
YYYi Yu
Yi Yu
STSuhua Tang
Suhua Tang
FRFrancisco Raposo
Francisco Raposo
LCLei Chen
Lei Chen
Deep cross-modal learning has successfully demonstrated excellent performance in cross-modal multimedia retrieval, with the aim of learning joint representations between different data modalities. Unfortunately, little research focuses on cross-modal correlation learning where temporal structures of different data modalities, such as audio and lyrics, should be taken into account. Stemming from the characteristic of temporal structures of music in nature, we are motivated to learn the deep sequential correlation between audio and lyrics. In this work, we propose a deep cross-modal correlation learning architecture involving two-branch deep neural networks for audio modality and text modality (lyrics). Data in different modalities are converted to the same canonical space where intermodal canonical correlation analysis is utilized as an objective function to calculate the similarity of temporal structures. This is the first study that uses deep architectures for learning the temporal correlation between audio and lyrics. A pretrained Doc2Vec model followed by fully connected layers is used to represent lyrics. Two significant contributions are made in the audio branch, as follows: (i) We propose an end-to-end network to learn cross-modal correlation between audio and lyrics, where feature extraction and correlation learning are simultaneously performed and joint representation is learned by considering temporal structures. (ii) And, as for feature extraction, we further represent an audio signal by a short sequence of local summaries (VGG16 features) and apply a recurrent neural network to compute a compact feature that better learns the temporal structures of music audio. Experimental results, using audio to retrieve lyrics or using lyrics to retrieve audio, verify the effectiveness of the proposed deep correlation learning architectures in cross-modal music retrieval.

10 August 2018 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
YYYi Yu
Yi Yu
STSuhua Tang
Suhua Tang
KAKiyoharu Aizawa
Kiyoharu Aizawa
AAAkiko Aizawa
Akiko Aizawa
In this work, travel destinations and business locations are taken as venues. Discovering a venue by a photograph is very important for visual context-aware applications. Unfortunately, few efforts paid attention to complicated real images such as venue photographs generated by users. Our goal is fine-grained venue discovery from heterogeneous social multimodal data. To this end, we propose a novel deep learning model, category-based deep canonical correlation analysis. Given a photograph as input, this model performs: 1) exact venue search (find the venue where the photograph was taken) and 2) group venue search (find relevant venues that have the same category as the photograph), by the cross-modal correlation between the input photograph and textual description of venues. In this model, data in different modalities are projected to a same space via deep networks. Pairwise correlation (between different modality data from the same venue) for exact venue search and category-based correlation (between different modality data from different venues with the same category) for group venue search are jointly optimized. Because a photograph cannot fully reflect rich text description of a venue, the number of photographs per venue in the training phase is increased to capture more aspects of a venue. We build a new venue-aware multimodal data set by integrating Wikipedia featured articles and Foursquare venue photographs. Experimental results on this data set confirm the feasibility of the proposed method. Moreover, the evaluation over another publicly available data set confirms that the proposed method outperforms state of the arts for cross-modal retrieval between image and text.

1 September 2016 in Knowledge-Based Systems
Verified
Journal Article
Closed access
RSRajiv Ratn Shah
Rajiv Ratn Shah
YYYi Yu
Yi Yu
AVAkshay Verma
Akshay Verma
STSuhua Tang
Suhua Tang
ASAnwar Dilawar Shaikh
Anwar Dilawar Shaikh
RZRoger Zimmermann
Roger Zimmermann

16 October 2018 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
Junjun JiangJunjun Jiang
Junjun Jiang
YYYi Yu
Yi Yu
STSuhua Tang
Suhua Tang
Jiayi MaJiayi Ma
Jiayi Ma
AAAkiko Aizawa
Akiko Aizawa
KAKiyoharu Aizawa
Kiyoharu Aizawa
Face hallucination is a technique that reconstructs high-resolution (HR) faces from low-resolution (LR) faces, by using the prior knowledge learned from HR/LR face pairs. Most state-of-the-arts leverage position-patch prior knowledge of the human face to estimate the optimal representation coefficients for each image patch. However, they focus only the position information and usually ignore the context information of the image patch. In addition, when they are confronted with misalignment or the small sample size (SSS) problem, the hallucination performance is very poor. To this end, this paper incorporates the contextual information of the image patch and proposes a powerful and efficient context-patch-based face hallucination approach, namely, thresholding locality-constrained representation and reproducing learning (TLcR-RL). Under the context-patch-based framework, we advance a thresholding-based representation method to enhance the reconstruction accuracy and reduce the computational complexity. To further improve the performance of the proposed algorithm, we propose a promotion strategy called reproducing learning. By adding the estimated HR face to the training set, which can simulate the case that the HR version of the input LR face is present in the training set, it thus iteratively enhances the final hallucination result. Experiments demonstrate that the proposed TLcR-RL method achieves a substantial increase in the hallucinated results, both subjectively and objectively. In addition, the proposed framework is more robust to face misalignment and the SSS problem, and its hallucinated HR face is still very good when the LR test face is from the real world. The MATLAB source code is available at https://github.com/junjun-jiang/TLcR-RL.

1 July 2018
Verified
Conference Paper
Closed access
Junjun JiangJunjun Jiang
Junjun Jiang
YYYi Yu
Yi Yu
JHJinhui Hu
Jinhui Hu
STSuhua Tang
Suhua Tang
JMJiayi Ma
Jiayi Ma
Most of the current face hallucination methods, whether they are shallow learning-based or deep learning-based, all try to learn a relationship model between Low-Resolution (LR) and High-Resolution (HR) spaces with the help of a training set. They mainly focus on modeling image prior through either model-based optimization or discriminative inference learning. However, when the input LR face is tiny, the learned prior knowledge is no longer effective and their performance will drop sharply. To solve this problem, in this paper we propose a general face hallucination method that can integrate model-based optimization and discriminative inference. In particular, to exploit the model based prior, the Deep Convolutional Neural Networks (CNN) denoiser prior is plugged into the super-resolution optimization model with the aid of image-adaptive Laplacian regularization. Additionally, we further develop a high-frequency details compensation method by dividing the face image to facial components and performing face hallucination in a multi-layer neighbor embedding manner. Experiments demonstrate that the proposed method can achieve promising super-resolution results for tiny input LR faces.

9 February 2012 in EURASIP Journal on Wireless Communications and Networking
Verified
Journal Article
Open access
PDF file
STSuhua Tang
Suhua Tang
HYHiroyuki Yomo
Hiroyuki Yomo
YKYoshihisa Kondo
Yoshihisa Kondo
SOSadao Obana
Sadao Obana
Recent investigations show that access points (APs) of wireless local area networks (WLANs) are idle during much of the time and that an AP in its idle state still consumes a large percentage of power. Wake-up receivers can be used to realize radio-on-demand WLANs, activating APs from the sleep mode only in times of active data communications. A wake-up receiver, sharing the antenna (and the same ISM band) with its co-located WLAN module and exploiting RF energy detection, can be implemented at low cost and run with low power consumption. In this article, we evaluate the effect of an imperfect RF band pass filter (BPF), and suggest a new soft decision method to (i) resist adjacent channel interference leaked by BPF, and, (ii) distinguish wake-up signals from WLAN signals. Extensive simulation and testbed experimental results confirm that the proposed scheme, at a moderate cost, has good performance in delivering wake-up signals and controlling false wake-up events caused by WLAN signals.