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
Proceedings ArticleDOI
Interactive Spatio-Temporal Visual Map Model for Web Video Retrieval
TL;DR: The use of a spatio-temporal visual map (STVM) model to supplement Web video retrieval is described by employing the spatiospecific visual similarity to rerank the text-retrieval results and find new results.
Posted Content
The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation
TL;DR: This work systematically investigates performance drop of the state-of-the-art two-stage instance segmentation model Mask R-CNN on the recent long-tail LVIS dataset, and unveils that a major cause is the inaccurate classification of object proposals.
Journal ArticleDOI
Semi-supervised learning via sparse model
TL;DR: This paper proposes an structured dictionary learning algorithm to explicitly reveal the cluster structure of the dictionary and develops the SSPA algorithms with the structured dictionary besides non-structured one, and experiments show that the methods are efficient and outperform state-of-the-art graph-based SSL methods.
Proceedings ArticleDOI
Style Separation and Synthesis via Generative Adversarial Networks.
TL;DR: Experiments on CelebA and UT Zappos 50K datasets demonstrate that the S3-GAN has the capacity of style separation and synthesis simultaneously, and could capture various styles in a single model.
Journal ArticleDOI
Ecological niche shift between diploid and tetraploid plants of Fragaria (Rosaceae) in China
J.-Z. Wan,J.-Z. Wan,Luxi Chen,S. Gao,Y.-B. Song,Sheng Tang,Fei-Hai Yu,Jun-Min Li,Ming Dong,Ming Dong +9 more
TL;DR: Novel insights are provided into the role of niche shifts on genome mergers and duplications of Fragaria in China by exploring the variables that best explained niche shifts between diploid and tetraploid plants.