J
Jindong Wang
Researcher at Microsoft
Publications - 26
Citations - 2120
Jindong Wang is an academic researcher from Microsoft. The author has contributed to research in topics: Transfer of learning & Domain (software engineering). The author has an hindex of 12, co-authored 26 publications receiving 773 citations. Previous affiliations of Jindong Wang include Chinese Academy of Sciences.
Papers
More filters
Proceedings ArticleDOI
Visual Domain Adaptation with Manifold Embedded Distribution Alignment
TL;DR: This paper proposes a Manifold Embedded Distribution Alignment (MEDA) approach, which learns a domain-invariant classifier in Grassmann manifold with structural risk minimization, while performing dynamic distribution alignment to quantitatively account for the relative importance of marginal and conditional distributions.
Journal ArticleDOI
FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare
TL;DR: FedHealth is proposed, the first federated transfer learning framework for wearable healthcare that performs data aggregation through federated learning, and then builds relatively personalized models by transfer learning.
Posted Content
Transfer Learning with Dynamic Adversarial Adaptation Network.
TL;DR: This paper proposes a novel Dynamic Adversarial Adaptation Network (DAAN) to dynamically learn domain-invariant representations while quantitatively evaluate the relative importance of global and local domain distributions.
Proceedings ArticleDOI
Transfer Learning with Dynamic Adversarial Adaptation Network
TL;DR: Zhang et al. as mentioned in this paper proposed a Dynamic Adversarial Adaptation Network (DAAN) to dynamically learn domain-invariant representations while quantitatively evaluating the relative importance of global and local domain distributions.
Proceedings ArticleDOI
Deep Transfer Learning for Cross-domain Activity Recognition
TL;DR: An effective Unsupervised Source Selection algorithm for Activity Recognition (USSAR) that is able to select the most similar K source domains from a list of available domains is proposed and an effective Transfer Neural Network to perform knowledge transfer for Activity recognition (TNNAR).