{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T09:06:56Z","timestamp":1742980016585,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031533075"},{"type":"electronic","value":"9783031533082"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-53308-2_13","type":"book-chapter","created":{"date-parts":[[2024,1,27]],"date-time":"2024-01-27T21:37:36Z","timestamp":1706391456000},"page":"170-183","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-head Hashing with\u00a0Orthogonal Decomposition for\u00a0Cross-modal Retrieval"],"prefix":"10.1007","author":[{"given":"Wei","family":"Liu","sequence":"first","affiliation":[]},{"given":"Jun","family":"Li","sequence":"additional","affiliation":[]},{"given":"Zhijian","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Jianhua","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,28]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Bai, C., Zeng, C., Ma, Q., Zhang, J., Chen, S.: Deep adversarial discrete hashing for cross-modal retrieval. In: International Conference on Multimedia Retrieval, pp. 525\u2013531 (2020)","DOI":"10.1145\/3372278.3390711"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Cao, Y., Liu, B., Long, M., Wang, J.: Cross-modal hamming hashing. In: European Conference on Computer Vision, pp. 207\u2013223 (2018)","DOI":"10.1007\/978-3-030-01246-5_13"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Chua, T.S., Tang, J., Hong, R., Li, H., Luo, Z., Zheng, Y.: NUS-WIDE: a real-world web image database from national university of Singapore. In: ACM International Conference on Image and Video Retrieval, pp. 368\u2013375 (2009)","DOI":"10.1145\/1646396.1646452"},{"key":"13_CR4","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: North American Chapter of the Association for Computational Linguistics, pp. 4171\u20134186 (2019)"},{"key":"13_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations, pp. 1\u201322 (2021)"},{"key":"13_CR6","unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: VSE++: improved visual-semantic embeddings with hard negatives. In: British Machine Vision Conference, pp. 1\u201314 (2018)"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Hong, J., Liu, H.: Deep cross-modal hashing retrieval based on semantics preserving and vision transformer. In: International Conference on Electronic Information Technology and Computer Engineering, pp. 52\u201357 (2022)","DOI":"10.1145\/3573428.3573439"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Huo, Y., et al.: Deep semantic-aware proxy hashing for multi-label cross-modal retrieval. IEEE Trans. Circuits Syst. Video Technol. (2023)","DOI":"10.1109\/TCSVT.2023.3307608"},{"key":"13_CR9","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916 (2021)"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, Q.Y., Li, W.J.: Deep cross-modal hashing. IEEE Conference on Computer Vision and Pattern Recognition, pp. 3270\u20133278 (2016)","DOI":"10.1109\/CVPR.2017.348"},{"key":"13_CR11","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference for Learning Representations, pp. 1\u201315 (2015)"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Liang, M., et al.: Semantic structure enhanced contrastive adversarial hash network for cross-media representation learning. In: ACM International Conference on Multimedia, pp. 277\u2013285 (2022)","DOI":"10.1145\/3503161.3548391"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: European Conference on Computer Vision, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"13_CR14","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: petraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Neural Information Processing Systems, pp. 13\u201323 (2019)"},{"key":"13_CR15","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/j.neucom.2018.05.052","volume":"312","author":"L Ma","year":"2018","unstructured":"Ma, L., Li, H., Meng, F., Wu, Q., Ngi Ngan, K.: Global and local semantics-preserving based deep hashing for cross-modal retrieval. Neurocomputing 312, 49\u201362 (2018)","journal-title":"Neurocomputing"},{"key":"13_CR16","doi-asserted-by":"publisher","first-page":"3101","DOI":"10.1109\/TMM.2020.2969792","volume":"22","author":"X Ma","year":"2020","unstructured":"Ma, X., Zhang, T., Xu, C.: Multi-level correlation adversarial hashing for cross-modal retrieval. IEEE Trans. Multimedia 22, 3101\u20133114 (2020)","journal-title":"IEEE Trans. Multimedia"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Mikriukov, G., Ravanbakhsh, M., Demir, B.: Deep unsupervised contrastive hashing for large-scale cross-modal text-image retrieval in remote sensing. arXiv preprint arXiv:2201.08125 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746251"},{"key":"13_CR18","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1109\/TCSVT.2020.2974877","volume":"31","author":"X Nie","year":"2021","unstructured":"Nie, X., Wang, B., Li, J., Hao, F., Jian, M., Yin, Y.: Deep multiscale fusion hashing for cross-modal retrieval. IEEE Trans. Circuits Syst. Video Technol. 31, 401\u2013410 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"13_CR19","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"issue":"8","key":"13_CR20","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Shi, Y., et al.: Deep adaptively-enhanced hashing with discriminative similarity guidance for unsupervised cross-modal retrieval. IEEE Trans. Circuits Syst. Video Technol. 32, 7255\u20137268 (2022)","DOI":"10.1109\/TCSVT.2022.3172716"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: FLAVA: a foundational language and vision alignment model. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 15617\u201315629 (2022)","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Su, S., Zhong, Z., Zhang, C.: Deep joint-semantics reconstructing hashing for large-scale unsupervised cross-modal retrieval. In: IEEE International Conference on Computer Vision, pp. 3027\u20133035 (2019)","DOI":"10.1109\/ICCV.2019.00312"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Tu, J., Liu, X., Lin, Z., Hong, R., Wang, M.: Differentiable cross-modal hashing via multimodal transformers. In: ACM International Conference on Multimedia, pp. 453\u2013461 (2022)","DOI":"10.1145\/3503161.3548187"},{"key":"13_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Neural Information Processing Systems, pp. 6000\u20136010 (2017)"},{"key":"13_CR26","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1007\/s00530-022-01005-6","volume":"29","author":"H Wang","year":"2022","unstructured":"Wang, H., Zhao, K., Zhao, D.: A triple fusion model for cross-modal deep hashing retrieval. Multimedia Syst. 29, 347\u2013359 (2022)","journal-title":"Multimedia Syst."},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Yang, M., et al.: DOLG: single-stage image retrieval with deep orthogonal fusion of local and global features. In: IEEE International Conference on Computer Vision, pp. 11752\u201311761 (2021)","DOI":"10.1109\/ICCV48922.2021.01156"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Yao, H.L., Zhan, Y.W., Chen, Z.D., Luo, X., Xu, X.S.: TEACH: attention-aware deep cross-modal hashing. In: International Conference on Multimedia Retrieval, pp. 376\u2013384 (2021)","DOI":"10.1145\/3460426.3463625"},{"key":"13_CR29","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1007\/s11280-020-00859-y","volume":"24","author":"P Zhang","year":"2021","unstructured":"Zhang, P., Luo, Y., Huang, Z., Xu, X.S., Song, J.: High-order nonlocal hashing for unsupervised cross-modal retrieval. World Wide Web 24, 563\u2013583 (2021)","journal-title":"World Wide Web"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Zhen, L., Hu, P., Wang, X., Peng, D.: Deep supervised cross-modal retrieval. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 10386\u201310395 (2019)","DOI":"10.1109\/CVPR.2019.01064"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Zhu, L., Cai, L., Song, J., Zhu, X., Zhang, C., Zhang, S.: MSSPQ: multiple semantic structure-preserving quantization for cross-modal retrieval. In: International Conference on Multimedia Retrieval, pp. 631\u2013638 (2022)","DOI":"10.1145\/3512527.3531417"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53308-2_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T11:08:26Z","timestamp":1710241706000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53308-2_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031533075","9783031533082"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53308-2_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"28 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 January 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 February 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ConfTool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"297","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"112","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"38% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}