Title
CycleMatch: A Cycle-consistent Embedding Network for Image-Text Matching
Abstract
•A novel deep cycle-consistent embedding network (CycleMatch) for image-text matching.•Maintain both inter-modal correlations and intra-modal consistency.•Late-fusion approaches to efficiently integrate the matching scores of multiple embedding features.•Competitive with the state-of-the-art performance on two well-known multimodal benchmarks.
Year
DOI
Venue
2019
10.1016/j.patcog.2019.05.008
Pattern Recognition
Keywords
Field
DocType
Image-text matching,Embedding,Deep neural networks,Late-fusion inference
Feature vector,Embedding,Network complexity,Video retrieval,Inference,Bridging (networking),Artificial intelligence,Artificial neural network,Semantics,Mathematics,Machine learning
Journal
Volume
Issue
ISSN
93
1
0031-3203
Citations 
PageRank 
References 
3
0.44
0
Authors
5
Name
Order
Citations
PageRank
Yu Liu1121.27
Yanming Guo212813.06
Li Liu373350.04
Erwin M. Bakker437841.20
Michael S. Lew52742166.02