Matches in SemOpenAlex for { <https://semopenalex.org/work/W4361010245> ?p ?o ?g. }
- W4361010245 endingPage "3439" @default.
- W4361010245 startingPage "3439" @default.
- W4361010245 abstract "With the proliferation of multi-modal data generated by various sensors, unsupervised multi-modal hashing retrieval has been extensively studied due to its advantages in storage, retrieval efficiency, and label independence. However, there are still two obstacles to existing unsupervised methods: (1) As existing methods cannot fully capture the complementary and co-occurrence information of multi-modal data, existing methods suffer from inaccurate similarity measures. (2) Existing methods suffer from unbalanced multi-modal learning and data semantic structure being corrupted in the process of hash codes binarization. To address these obstacles, we devise an effective CLIP-based Adaptive Graph Attention Network (CAGAN) for large-scale unsupervised multi-modal hashing retrieval. Firstly, we use the multi-modal model CLIP to extract fine-grained semantic features, mine similar information from different perspectives of multi-modal data and perform similarity fusion and enhancement. In addition, this paper proposes an adaptive graph attention network to assist the learning of hash codes, which uses an attention mechanism to learn adaptive graph similarity across modalities. It further aggregates the intrinsic neighborhood information of neighboring data nodes through a graph convolutional network to generate more discriminative hash codes. Finally, this paper employs an iterative approximate optimization strategy to mitigate the information loss in the binarization process. Extensive experiments on three benchmark datasets demonstrate that the proposed method significantly outperforms several representative hashing methods in unsupervised multi-modal retrieval tasks." @default.
- W4361010245 created "2023-03-30" @default.
- W4361010245 creator A5003880699 @default.
- W4361010245 creator A5009327506 @default.
- W4361010245 creator A5042186913 @default.
- W4361010245 creator A5063575625 @default.
- W4361010245 creator A5076589173 @default.
- W4361010245 date "2023-03-24" @default.
- W4361010245 modified "2023-09-26" @default.
- W4361010245 title "CLIP-Based Adaptive Graph Attention Network for Large-Scale Unsupervised Multi-Modal Hashing Retrieval" @default.
- W4361010245 cites W1861492603 @default.
- W4361010245 cites W2007972815 @default.
- W4361010245 cites W2049993534 @default.
- W4361010245 cites W2086958058 @default.
- W4361010245 cites W2155803963 @default.
- W4361010245 cites W2194775991 @default.
- W4361010245 cites W2266728343 @default.
- W4361010245 cites W2512032049 @default.
- W4361010245 cites W2618530766 @default.
- W4361010245 cites W2733636222 @default.
- W4361010245 cites W2808243243 @default.
- W4361010245 cites W2895249671 @default.
- W4361010245 cites W2953037339 @default.
- W4361010245 cites W2963288100 @default.
- W4361010245 cites W2963446712 @default.
- W4361010245 cites W2966146145 @default.
- W4361010245 cites W3012050760 @default.
- W4361010245 cites W3033276647 @default.
- W4361010245 cites W3033587904 @default.
- W4361010245 cites W3034851464 @default.
- W4361010245 cites W3034890701 @default.
- W4361010245 cites W3035747010 @default.
- W4361010245 cites W3093291618 @default.
- W4361010245 cites W3122091215 @default.
- W4361010245 cites W3135808071 @default.
- W4361010245 cites W3155230099 @default.
- W4361010245 cites W3171119100 @default.
- W4361010245 cites W3175740157 @default.
- W4361010245 cites W3176445421 @default.
- W4361010245 cites W3177806915 @default.
- W4361010245 cites W3198047460 @default.
- W4361010245 cites W3207267030 @default.
- W4361010245 cites W3207668481 @default.
- W4361010245 cites W4206706211 @default.
- W4361010245 cites W4220857054 @default.
- W4361010245 cites W4224214654 @default.
- W4361010245 cites W4225149736 @default.
- W4361010245 cites W4226144405 @default.
- W4361010245 cites W4226172762 @default.
- W4361010245 cites W4283379644 @default.
- W4361010245 cites W4285288078 @default.
- W4361010245 cites W4312639100 @default.
- W4361010245 doi "https://doi.org/10.3390/s23073439" @default.
- W4361010245 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37050499" @default.
- W4361010245 hasPublicationYear "2023" @default.
- W4361010245 type Work @default.
- W4361010245 citedByCount "0" @default.
- W4361010245 crossrefType "journal-article" @default.
- W4361010245 hasAuthorship W4361010245A5003880699 @default.
- W4361010245 hasAuthorship W4361010245A5009327506 @default.
- W4361010245 hasAuthorship W4361010245A5042186913 @default.
- W4361010245 hasAuthorship W4361010245A5063575625 @default.
- W4361010245 hasAuthorship W4361010245A5076589173 @default.
- W4361010245 hasBestOaLocation W43610102451 @default.
- W4361010245 hasConcept C119857082 @default.
- W4361010245 hasConcept C124101348 @default.
- W4361010245 hasConcept C132525143 @default.
- W4361010245 hasConcept C153180895 @default.
- W4361010245 hasConcept C154945302 @default.
- W4361010245 hasConcept C185592680 @default.
- W4361010245 hasConcept C188027245 @default.
- W4361010245 hasConcept C38652104 @default.
- W4361010245 hasConcept C41008148 @default.
- W4361010245 hasConcept C59404180 @default.
- W4361010245 hasConcept C71139939 @default.
- W4361010245 hasConcept C8038995 @default.
- W4361010245 hasConcept C80444323 @default.
- W4361010245 hasConcept C81363708 @default.
- W4361010245 hasConcept C97931131 @default.
- W4361010245 hasConcept C99138194 @default.
- W4361010245 hasConceptScore W4361010245C119857082 @default.
- W4361010245 hasConceptScore W4361010245C124101348 @default.
- W4361010245 hasConceptScore W4361010245C132525143 @default.
- W4361010245 hasConceptScore W4361010245C153180895 @default.
- W4361010245 hasConceptScore W4361010245C154945302 @default.
- W4361010245 hasConceptScore W4361010245C185592680 @default.
- W4361010245 hasConceptScore W4361010245C188027245 @default.
- W4361010245 hasConceptScore W4361010245C38652104 @default.
- W4361010245 hasConceptScore W4361010245C41008148 @default.
- W4361010245 hasConceptScore W4361010245C59404180 @default.
- W4361010245 hasConceptScore W4361010245C71139939 @default.
- W4361010245 hasConceptScore W4361010245C8038995 @default.
- W4361010245 hasConceptScore W4361010245C80444323 @default.
- W4361010245 hasConceptScore W4361010245C81363708 @default.
- W4361010245 hasConceptScore W4361010245C97931131 @default.
- W4361010245 hasConceptScore W4361010245C99138194 @default.
- W4361010245 hasIssue "7" @default.
- W4361010245 hasLocation W43610102451 @default.