Journal
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
Volume -, Issue -, Pages 6345-6353Publisher
IEEE
DOI: 10.1109/CVPR.2017.672
Keywords
-
Categories
Funding
- National Key Technology RD Program [2016YFB1001503]
- Nature Science Foundation of China [61422210, 61373076, 61402388, 61572410]
Ask authors/readers for more resources
Binary code learning has recently been emerging topic in large-scale cross-modality retrieval. It aims to map features from multiple modalities into a common Hamming space, where the cross-modality similarity can be approximated efficiently via Hamming distance. To this end, most existing works learn binary codes directly from data instances in multiple modalities, which preserve both intra-and inter-modal similarities respectively. Few methods consider to preserve the fusion similarity among multi-modal instances instead, which can explicitly capture their heterogeneous correlation in cross-modality retrieval. In this paper, we propose a hashing scheme, termed Fusion Similarity Hashing (FSH), which explicitly embeds the graphbased fusion similarity across modalities into a common Hamming space. Inspired by the fusion by diffusion, our core idea is to construct an undirected asymmetric graph to model the fusion similarity among different modalities, upon which a graph hashing scheme with alternating optimization is introduced to learn binary codes that embeds such fusion similarity. Quantitative evaluations on three widely used benchmarks, i.e., UCI Handwritten Digit, MIR-Flickr25K and NUS-WIDE, demonstrate that the proposed FSH approach can achieve superior performance over the state-of-the-art methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available