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
Book ChapterDOI
The Devil Is in Classification: A Simple Framework for Long-Tail Instance Segmentation
TL;DR: Wang et al. as mentioned in this paper propose a simple calibration framework to more effectively alleviate classification head bias with a bi-level class balanced sampling approach, which significantly boosts the performance of instance segmentation for tail classes on the recent LVIS dataset and our sampled COCO-LT dataset.
Proceedings ArticleDOI
Pornprobe: an LDA-SVM based pornography detection system
Sheng Tang,Jintao Li,Yongdong Zhang,Cheng Xie,Ming Li,Yizhi Liu,Xiufeng Hua,Yan-Tao Zheng,Jinhui Tang,Tat-Seng Chua +9 more
TL;DR: PornProbe, a pornography detection system that detects pornographic contents in videos, is presented, which combines the unsupervised clustering in Latent Dirichlet Allocation and supervised learning in Support Vector Machine to achieve both high precision and recall while ensuring efficiency in both training and testing.
Proceedings ArticleDOI
Logo detection based on spatial-spectral saliency and partial spatial context
TL;DR: A two-stage detection scheme based on spatialspectral saliency (SSS) and partial spatial context (PSC) that speeds up logo location and avoid the impact of cluttered background.
Proceedings Article
Zero-Shot Learning With Attribute Selection.
TL;DR: This work is the first work that notices the influence of attributes themselves and proposes to use a refined attribute set for ZSL, and can be combined to any attribute based ZSL approaches so as to augment their performance.
Journal ArticleDOI
Robust common visual pattern discovery using graph matching
TL;DR: This paper formulate CVPs discovery as a graph matching problem, depending on pairwise geometric compatibility between feature correspondences, which consists of three components: Preliminary Initialization Optimization (PIO), Guided Expansion (GE) and Post Agglomerative Combination (PAC).