S
Sheng Tang
Researcher at Chinese Academy of Sciences
Publications - 143
Citations - 3507
Sheng Tang is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Visual Word & TRECVID. The author has an hindex of 25, co-authored 131 publications receiving 2431 citations. Previous affiliations of Sheng Tang include National University of Singapore & Dalian University of Technology.
Papers
More filters
TRECVID 2007 High-Level Feature Extraction By MCG-ICT-CAS *
Sheng Tang,Yongdong Zhang,Jintao Li,Ming Li Na Cai,Xu Zhang,Kun Tao,Li Tan,Shao-Xi Xu,Yuan-Yuan Ran +8 more
TL;DR: An EMD-based bag-of-feature method is proposed to exploit visual/spatial information, and WordNet is utilized to expand semantic meanings of text to boost up the generalization of detectors.
Journal ArticleDOI
Asymmetric GAN for Unpaired Image-to-image Translation
TL;DR: Asymmetric GAN (AsymGAN) as mentioned in this paper introduces an auxiliary variable to learn the extra information for transferring from the informationpoor domain to the information-rich domain, which improves the performance of state-of-the-art approaches.
Proceedings ArticleDOI
Global-residual and local-boundary refinement networks for rectifying scene parsing predictions
TL;DR: This work proposes a Global-residual Refinement Network (GRN) through exploiting global contextual information to predict the parsing residuals and iteratively smoothen the inconsistent parsing labels, and proposes a Localboundary Refinement network (LRN) to learn the position-adaptive propagation coefficients so that local contextual information from neighbors can be optimally captured for refining object boundaries.
Journal ArticleDOI
Localized Multiple Kernel Learning for Realistic Human Action Recognition in Videos
TL;DR: A localized multiple kernel learning (L-MKL) algorithm to tackle the issues above and develops a locality gating model to partition the input space of heterogeneous representations to a set of localities of simpler data structure.
Proceedings ArticleDOI
Attention Model Based SIFT Keypoints Filtration for Image Retrieval
TL;DR: Experiments demonstrate that the attention model based SIFT keypoints filtration algorithm provides significant benefits both in retrieval accuracy and matching speed.