M
Ming Shao
Researcher at University of Massachusetts Dartmouth
Publications - 125
Citations - 4061
Ming Shao is an academic researcher from University of Massachusetts Dartmouth. The author has contributed to research in topics: Facial recognition system & Feature extraction. The author has an hindex of 31, co-authored 121 publications receiving 3298 citations. Previous affiliations of Ming Shao include Northeastern University & University of Massachusetts Amherst.
Papers
More filters
Proceedings ArticleDOI
Transfer learning for image classification with incomplete multiple sources
Zhengming Ding,Ming Shao,Yun Fu +2 more
TL;DR: A Bi-directional Low-Rank Transfer learning framework (BLRT) is proposed that can successfully inherit knowledge from incomplete multiple sources and adapt to the target data successfully and an iterative structure learning is proposed to better use prior knowledge for transfer learning coefficients matrix.
Posted Content
What Will Your Child Look Like? DNA-Net: Age and Gender Aware Kin Face Synthesizer
TL;DR: This paper proposes a two-stage kin-face generation model to predict the appearance of a child given a pair of parents, and demonstrates the effectiveness of the proposed method quantitatively and qualitatively.
Proceedings Article
Consensus style centralizing auto-encoder for weak style classification
TL;DR: A consensus style centralizing auto-encoder (CSCAE) to extract robust style features to facilitate weak style classification is proposed and applied in fashion style classification and manga style classification.
Posted Content
Family in the Wild (FIW): A Large-scale Kinship Recognition Database.
TL;DR: A large-scale dataset for visual kin-based problems, the Family in the Wild (FIW) dataset is introduced, with only a small team and an efficient labelling tool designed to optimize the process of marking complex hierarchical relationships, attributes, and local label information in family photos.
Proceedings ArticleDOI
A super-resolution based method to synthesize visual images from near infrared
TL;DR: A new method to enhance the quality of near infrared face image using tensorface, super-resolution and image fusion to synthesize an image under visible light environment by building multiple factors training tensors and super-resolving its high-resolution visible light reconstructions across different modalities.