Semantic Consistency Cross-Modal Retrieval With Semi-Supervised Graph Regularization
Most of the existing cross-modal retrieval methods make use of labeled data to learn projection matrices for different modal data. These methods usually learn the original semantic space to bridge the heterogeneous gap, ignoring the rich semantic information contained in unlabeled data. Accordingly,...
Main Authors: | Gongwen Xu, Xiaomei Li, Zhijun Zhang |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8957531/ |
Similar Items
-
Combination subspace graph learning for cross-modal retrieval
by: Gongwen Xu, et al.
Published: (2020-06-01) -
Semi-Supervised Classification Based on Mixture Graph
by: Lei Feng, et al.
Published: (2015-11-01) -
Semi-Supervised Learning Based Semantic Cross-Media Retrieval
by: Xiyuan Zheng, et al.
Published: (2021-01-01) -
Modal-Dependent Retrieval Based on Mid-Level Semantic Enhancement Space
by: Shunxin Zheng, et al.
Published: (2019-01-01) -
Graph Regularized Variational Ladder Networks for Semi-Supervised Learning
by: Cong Hu, et al.
Published: (2020-01-01)