← Search

Xueya Zhang

2 accepted papers

2021

Wasserstein Coupled Graph Learning for Cross-Modal Retrieval

ICCV 2021poster

Graphs play an important role in cross-modal image-text understanding as they characterize the intrinsic structure which is robust and crucial for the measurement of cross-modal similarity. In this work, we propose a Wasserstein Coupled Graph Learning (WCGL) method to deal with the cross-modal retri…

Cited by 29PDF ↗Scholar ↗
2020

Graph Wasserstein Correlation Analysis for Movie Retrieval

ECCV 2020poster

Movie graphs play an important role to bridge heterogenous modalities of videos and texts in human-centric retrieval. In this work, we propose Graph Wasserstein Correlation Analysis (GWCA) to deal with the core issue therein, i.e, cross heterogeneous graph comparison. Spectral graph filtering is int…