Proceedings of the 30th ACM International Conference on Multimedia · 2022 · 27 citations · 42 references
ComputingComputer ScienceData MiningFeature EngineeringMachine LearningGraph-based LearningHash TablesMetric LearningRepresentation LearningUnsupervised LearningAdjacency RelationsContinuous Space RepresentationHashingMultimodal Representation LearningSemantic HashingSemantic Knowledge RepresentationSimilarity LearningStructural Representation
Cross-modal hashing is an important approach for multimodal data management and application. Existing unsupervised cross-modal hashing algorithms mainly rely on data features in pre-trained models to mine their similarity relationships. However, their optimization objectives are based on the static metric between the original uni-modal features, without further exploring data correlations during the training. In addition, most of them mainly focus on association mining and alignment among pairwise instances in continuous space but ignore the latent structural correlations contained in the semantic hashing space. In this paper, we propose an unsupervised hash learning framework ASSPH to solve the above problems. Firstly, we propose an adaptive learning scheme, with limited data and training batches, to enrich semantic correlations of unlabeled instances during the training process and meanwhile to ensure a smooth convergence of the training process. Secondly, we present an asymmetric structural semantic representation learning scheme. We introduce structural semantic metrics based on graph adjacency relations and meanwhile align the inter- and intra-modal semantics in the hash space with an asymmetric binary optimization process. Finally, we conduct extensive experiments to validate the enhancements of our work in comparison with existing works.
42
Momentum Contrast for Unsupervised Visual Representation Learning
Kaiming He, Haoqi Fan, Yuxin Wu et al. · 2020 · 12K citations
Tat‐Seng Chua, Jinhui Tang, Richang Hong et al. · 2009 · 3K citations
The MIR flickr retrieval evaluation
Mark J. Huiskes, Michael S. Lew · 2008 · 1.8K citations
Qing-Yuan Jiang, Wu-Jun Li · 2017 · 871 citations