G
Guiguang Ding
Researcher at Tsinghua University
Publications - 191
Citations - 12042
Guiguang Ding is an academic researcher from Tsinghua University. The author has contributed to research in topics: Computer science & Convolutional neural network. The author has an hindex of 45, co-authored 173 publications receiving 7627 citations. Previous affiliations of Guiguang Ding include University of California, Berkeley & Hong Kong Baptist University.
Papers
More filters
Proceedings ArticleDOI
Transfer Feature Learning with Joint Distribution Adaptation
TL;DR: JDA aims to jointly adapt both the marginal distribution and conditional distribution in a principled dimensionality reduction procedure, and construct new feature representation that is effective and robust for substantial distribution difference.
Proceedings ArticleDOI
Transfer Joint Matching for Unsupervised Domain Adaptation
TL;DR: This paper aims to reduce the domain difference by jointly matching the features and reweighting the instances across domains in a principled dimensionality reduction procedure, and construct new feature representation that is invariant to both the distribution difference and the irrelevant instances.
Journal ArticleDOI
Adaptation Regularization: A General Framework for Transfer Learning
TL;DR: A novel transfer learning framework, referred to as Adaptation Regularization based Transfer Learning (ARTL), to model adaptive classifiers in a unified way based on the structural risk minimization principle and the regularization theory, and can significantly outperform state-of-the-art learning methods on several public text and image datasets.
Proceedings ArticleDOI
Collective Matrix Factorization Hashing for Multimodal Data
TL;DR: This paper puts forward a novel hashing method, which is referred to Collective Matrix Factorization Hashing (CMFH), which learns unified hash codes by collective matrix factorization with latent factor model from different modalities of one instance, which can not only supports cross-view search but also increases the search accuracy by merging multiple view information sources.
Proceedings ArticleDOI
Semantics-preserving hashing for cross-view retrieval
TL;DR: This paper proposes an effective Semantics-Preserving Hashing method, termed SePH, which transforms semantic affinities of training data as supervised information into a probability distribution and approximates it with to-be-learnt hash codes in Hamming space via minimizing the Kullback-Leibler divergence.