Y
Ya Zhang
Researcher at Shanghai Jiao Tong University
Publications - 288
Citations - 7597
Ya Zhang is an academic researcher from Shanghai Jiao Tong University. The author has contributed to research in topics: Computer science & Segmentation. The author has an hindex of 34, co-authored 229 publications receiving 5192 citations. Previous affiliations of Ya Zhang include Pennsylvania State University & Lawrence Berkeley National Laboratory.
Papers
More filters
Proceedings ArticleDOI
Expected reciprocal rank for graded relevance
TL;DR: This work presents a new editorial metric for graded relevance which overcomes this difficulty and implicitly discounts documents which are shown below very relevant documents and calls it Expected Reciprocal Rank (ERR).
Proceedings ArticleDOI
Actional-Structural Graph Convolutional Networks for Skeleton-Based Action Recognition
TL;DR: The proposed AS-GCN achieves consistently large improvement compared to the state-of-the-art methods and shows promising results for future pose prediction.
Proceedings ArticleDOI
A dynamic bayesian network click model for web search ranking
Olivier Chapelle,Ya Zhang +1 more
TL;DR: A Dynamic Bayesian Network is proposed which aims at providing us with unbiased estimation of the relevance from the click logs and shows that the proposed click model outperforms other existing click models in predicting both click-through rate and relevance.
Posted Content
Part-Stacked CNN for Fine-Grained Visual Categorization
TL;DR: A novel Part-Stacked CNN architecture that explicitly explains the finegrained recognition process by modeling subtle differences from object parts is proposed, from multiple perspectives of classification accuracy, model interpretability, and efficiency.
Proceedings ArticleDOI
A Fourier-based Framework for Domain Generalization
TL;DR: In this article, a Fourier-based data augmentation strategy called amplitude mix is proposed to force the model to capture phase information, which linearly interpolates between the amplitude spectrums of two images.