J
Jingjing Zheng
Researcher at University of Maryland, College Park
Publications - 22
Citations - 486
Jingjing Zheng is an academic researcher from University of Maryland, College Park. The author has contributed to research in topics: Computer science & Domain (software engineering). The author has an hindex of 10, co-authored 13 publications receiving 425 citations. Previous affiliations of Jingjing Zheng include General Electric.
Papers
More filters
Proceedings ArticleDOI
Cross-View Action Recognition via a Transferable Dictionary Pair
TL;DR: This work presents a method for viewinvariant action recognition based on sparse representations using a transferable dictionary pair, and extends the approach to transferring an action model learned from multiple source views to one target view.
Proceedings ArticleDOI
Learning View-Invariant Sparse Representations for Cross-View Action Recognition
Jingjing Zheng,Zhuolin Jiang +1 more
TL;DR: This approach represents videos in each view using both the corresponding view-specific dictionary and the common dictionary, which has the capability to represent actions from unseen views, and makes the approach effective in a semi-supervised setting where no correspondence videos exist and only a few labels exist in the target view.
Journal ArticleDOI
Cross-View Action Recognition via Transferable Dictionary Learning
TL;DR: Two effective approaches to learn dictionaries for robust action recognition across views are presented and it is demonstrated that the proposed approach outperforms recently developed approaches for cross-view action recognition.
Proceedings Article
Submodular Attribute Selection for Action Recognition in Video
TL;DR: Experimental results on the Olympic Sports and UCF101 datasets demonstrate that the proposed attribute-based representation can significantly boost the performance of action recognition algorithms and outperform most recently proposed recognition approaches.
Proceedings Article
A Grassmann manifold-based domain adaptation approach
TL;DR: This work proposes replacing the step of concatenating feature projections on a very few sampled intermediate subspaces by directly integrating the distance between feature projections along the geodesic, a more principled way of quantifying the cross-domain distance.