Z
Zhuolin Jiang
Researcher at BBN Technologies
Publications - 66
Citations - 4145
Zhuolin Jiang is an academic researcher from BBN Technologies. The author has contributed to research in topics: Discriminative model & K-SVD. The author has an hindex of 19, co-authored 65 publications receiving 3783 citations. Previous affiliations of Zhuolin Jiang include University of Maryland, College Park & Huawei.
Papers
More filters
Journal ArticleDOI
Label Consistent K-SVD: Learning a Discriminative Dictionary for Recognition
TL;DR: A label consistent K-SVD (LC-KSVD) algorithm to learn a discriminative dictionary for sparse coding and introduces a new label consistency constraint called "discriminative sparse-code error" to enforce discriminability in sparse codes during the dictionary learning process.
Proceedings ArticleDOI
Learning a discriminative dictionary for sparse coding via label consistent K-SVD
TL;DR: A label consistent K-SVD (LC-KSVD) algorithm to learn a discriminative dictionary for sparse coding is presented, which learns a single over-complete dictionary and an optimal linear classifier jointly and yields dictionaries so that feature points with the same class labels have similar sparse codes.
Proceedings ArticleDOI
Recognizing actions by shape-motion prototype trees
TL;DR: The prototype-based approach enables robust action matching in very challenging situations (such as moving cameras, dynamic backgrounds) and allows automatic alignment of action sequences.
Proceedings ArticleDOI
Learning Structured Low-Rank Representations for Image Classification
TL;DR: A discriminative low-rank representation for images with respect to the constructed dictionary is obtained with semantic structure information and strong identification capability, which is good for classification tasks even using a simple linear multi-classifier.
Proceedings ArticleDOI
Sparse dictionary-based representation and recognition of action attributes
TL;DR: This work unify the class distribution and appearance information into an objective function for learning a sparse dictionary of action attributes and proposes a Gaussian Process (GP) model for sparse representation to optimize the dictionary objective function.