{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T07:36:32Z","timestamp":1743060992154,"version":"3.40.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031178481"},{"type":"electronic","value":"9783031178498"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-17849-8_4","type":"book-chapter","created":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T20:19:42Z","timestamp":1664309982000},"page":"40-53","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Deep Vision-Language Model for\u00a0Efficient Multi-modal Similarity Search in\u00a0Fashion Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3663-7877","authenticated-orcid":false,"given":"Gianluca","family":"Moro","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3731-9528","authenticated-orcid":false,"given":"Stefano","family":"Salvatori","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,28]]},"reference":[{"key":"4_CR1","unstructured":"Cerroni, W., Moro, G., Pirini, T., Ramilli, M.: Peer-to-peer data mining classifiers for decentralized detection of network attacks, vol. 137, pp. 101\u2013107, January 2013"},{"key":"4_CR2","unstructured":"Choromanski, K.M., et al.: Rethinking attention with performers. In: ICLR. OpenReview.net (2021)"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Datar, M., Immorlica, N., Indyk, P., Mirrokni, V.S.: Locality-sensitive hashing scheme based on p-stable distributions. In: SCG, pp. 253\u2013262. ACM (2004)","DOI":"10.1145\/997817.997857"},{"key":"4_CR4","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (1), pp. 4171\u20134186. Association for Computational Linguistics (2019)"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Domeniconi, G., Masseroli, M., Moro, G., Pinoli, P.: Discovering new gene functionalities from random perturbations of known gene ontological annotations. In: KDIR, pp. 107\u2013116. SciTePress (2014)","DOI":"10.5220\/0005087801070116"},{"key":"4_CR6","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.cmpb.2015.12.002","volume":"126","author":"G Domeniconi","year":"2016","unstructured":"Domeniconi, G., Masseroli, M., Moro, G., Pinoli, P.: Cross-organism learning method to discover new gene functionalities. Comput. Methods Programs Biomed. 126, 20\u201334 (2016)","journal-title":"Comput. Methods Programs Biomed."},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Domeniconi, G., Moro, G., Pasolini, R., Sartori, C.: Cross-domain text classification through iterative refining of target categories representations. In: KDIR, pp. 31\u201342. SciTePress (2014)","DOI":"10.5220\/0005069400310042"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Domeniconi, G., Semertzidis, K., L\u00f3pez, V., Daly, E.M., Kotoulas, S., Moro, G.: A novel method for unsupervised and supervised conversational message thread detection. In: DATA, pp. 43\u201354. SciTePress (2016)","DOI":"10.5220\/0006001100430054"},{"key":"4_CR9","unstructured":"Endo, M., Krishnan, R., Krishna, V., Ng, A.Y., Rajpurkar, P.: Retrieval-based chest X-ray report generation using a pre-trained contrastive language-image model. In: ML4H@NeurIPS. Proceedings of Machine Learning Research, vol. 158, pp. 209\u2013219. PMLR (2021)"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Fabbri, M., Moro, G.: Dow jones trading with deep learning: the unreasonable effectiveness of recurrent neural networks. In: DATA, pp. 142\u2013153. SciTePress (2018)","DOI":"10.5220\/0006922101420153"},{"key":"4_CR11","unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: VSE++: improving visual-semantic embeddings with hard negatives. In: BMVC, p. 12. BMVA Press (2018)"},{"issue":"1","key":"4_CR12","doi-asserted-by":"publisher","first-page":"3","DOI":"10.3390\/s22010003","volume":"22","author":"G Frisoni","year":"2022","unstructured":"Frisoni, G., Moro, G., Carlassare, G., Carbonaro, A.: Unsupervised event graph representation and similarity learning on biomedical literature. Sensors 22(1), 3 (2022)","journal-title":"Sensors"},{"key":"4_CR13","unstructured":"Frome, A., et al.: Devise: a deep visual-semantic embedding model. In: NIPS, pp. 2121\u20132129 (2013)"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Gao, D., et al.: FashionBERT: text and image matching with adaptive loss for cross-modal retrieval. In: SIGIR, pp. 2251\u20132260. ACM (2020)","DOI":"10.1145\/3397271.3401430"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Goenka, S., et al.: FashionVLP: vision language transformer for fashion retrieval with feedback. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14105\u201314115 (2022)","DOI":"10.1109\/CVPR52688.2022.01371"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: CVPR (2), pp. 1735\u20131742. IEEE Computer Society (2006)","DOI":"10.1109\/CVPR.2006.100"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1007\/978-3-319-24261-3_7","volume-title":"Similarity-Based Pattern Recognition","author":"E Hoffer","year":"2015","unstructured":"Hoffer, E., Ailon, N.: Deep metric learning using triplet network. In: Feragen, A., Pelillo, M., Loog, M. (eds.) SIMBAD 2015. LNCS, vol. 9370, pp. 84\u201392. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24261-3_7"},{"issue":"1","key":"4_CR19","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","volume":"33","author":"H J\u00e9gou","year":"2011","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. IEEE Trans. Pattern Anal. Mach. Intell. 33(1), 117\u2013128 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR20","unstructured":"Kitaev, N., Kaiser, L., Levskaya, A.: Reformer: the efficient transformer. In: ICLR. OpenReview.net (2020)"},{"key":"4_CR21","unstructured":"Laenen, K., Zoghbi, S., Moens, M.F.: Cross-modal search for fashion attributes. In: KDD 2017 (2017)"},{"key":"4_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/978-3-030-01225-0_13","volume-title":"Computer Vision \u2013 ECCV 2018","author":"K-H Lee","year":"2018","unstructured":"Lee, K.-H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 212\u2013228. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_13"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Li, G., Duan, N., Fang, Y., Gong, M., Jiang, D.: Unicoder-VL: a universal encoder for vision and language by cross-modal pre-training. In: AAAI, pp. 11336\u201311344. AAAI Press (2020)","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"4_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-030-58577-8_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Li","year":"2020","unstructured":"Li, X., et al.: Oscar: object-semantics aligned pre-training for vision-language tasks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 121\u2013137. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_8"},{"key":"4_CR25","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: NeurIPS, pp. 13\u201323 (2019)"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Miech, A., Alayrac, J., Laptev, I., Sivic, J., Zisserman, A.: Thinking fast and slow: efficient text-to-visual retrieval with transformers. In: CVPR, pp. 9826\u20139836. Computer Vision Foundation\/IEEE (2021)","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Moro, G., Pagliarani, A., Pasolini, R., Sartori, C.: Cross-domain & in-domain sentiment analysis with memory-based deep neural networks. In: KDIR, pp. 125\u2013136. SciTePress (2018)","DOI":"10.5220\/0007239101270138"},{"issue":"19","key":"4_CR28","doi-asserted-by":"publisher","first-page":"6430","DOI":"10.3390\/s21196430","volume":"21","author":"G Moro","year":"2021","unstructured":"Moro, G., Valgimigli, L.: Efficient self-supervised metric information retrieval: a bibliography based method applied to COVID literature. Sensors 21(19), 6430 (2021)","journal-title":"Sensors"},{"key":"4_CR29","unstructured":"Muja, M., Lowe, D.G.: Fast approximate nearest neighbors with automatic algorithm configuration. In: VISAPP (1), pp. 331\u2013340. INSTICC Press (2009)"},{"key":"4_CR30","volume-title":"Five Balltree Construction Algorithms","author":"SM Omohundro","year":"1989","unstructured":"Omohundro, S.M.: Five Balltree Construction Algorithms. International Computer Science Institute, Berkeley (1989)"},{"key":"4_CR31","unstructured":"Qi, D., Su, L., Song, J., Cui, E., Bharti, T., Sacheti, A.: ImageBERT: cross-modal pre-training with large-scale weak-supervised image-text data. CoRR abs\/2001.07966 (2020)"},{"key":"4_CR32","unstructured":"Rostamzadeh, N.: Fashion-Gen: the generative fashion dataset and challenge. CoRR abs\/1806.08317 (2018)"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Sadegharmaki, S., Kastner, M.A., Satoh, S.: FashionGraph: understanding fashion data using scene graph generation. In: 2020 25th International Conference On Pattern Recognition (ICPR), pp. 7923\u20137929. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412662"},{"key":"4_CR34","unstructured":"Su, W., et al.: VL-BERT: pre-training of generic visual-linguistic representations. In: ICLR. OpenReview.net (2020)"},{"key":"4_CR35","unstructured":"Tay, Y., et al.: Long range arena: a benchmark for efficient transformers. CoRR abs\/2011.04006 (2020)"},{"key":"4_CR36","unstructured":"Tay, Y., Dehghani, M., Bahri, D., Metzler, D.: Efficient transformers: a survey. CoRR:2009.06732 (2020)"},{"key":"4_CR37","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS, pp. 5998\u20136008 (2017)"},{"key":"4_CR38","unstructured":"Wang, J., et al.: GIT: a generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100 (2022)"},{"key":"4_CR39","unstructured":"Wang, L., Li, Y., Lazebnik, S.: Learning two-branch neural networks for image-text matching tasks. CoRR:1704.03470 (2017)"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Position focused attention network for image-text matching. In: IJCAI, pp. 3792\u20133798 (2019). ijcai.org","DOI":"10.24963\/ijcai.2019\/526"},{"key":"4_CR41","unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345 (2020)"},{"key":"4_CR42","unstructured":"Zaheer, M., et al.: Big bird: transformers for longer sequences. In: NeurIPS (2020)"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Zhuge, M., et al.: Kaleido-BERT: vision-language pre-training on fashion domain. In: CVPR, pp. 12647\u201312657. Computer Vision Foundation\/IEEE (2021)","DOI":"10.1109\/CVPR46437.2021.01246"},{"key":"4_CR44","doi-asserted-by":"publisher","first-page":"31","DOI":"10.17706\/IJCEE.2016.8.1.31-43","volume":"8","author":"S Zoghbi","year":"2016","unstructured":"Zoghbi, S., Heyman, G., Gomez, J.C., Moens, M.F.: Fashion meets computer vision and NLP at e-commerce search. Int. J. Comput. Electr. Eng. (IJCEE) 8, 31\u201343 (2016). https:\/\/doi.org\/10.17706\/IJCEE.2016.8.1.31-43","journal-title":"Int. J. Comput. Electr. Eng. (IJCEE)"}],"container-title":["Lecture Notes in Computer Science","Similarity Search and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-17849-8_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,4]],"date-time":"2024-10-04T20:01:58Z","timestamp":1728072118000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-17849-8_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031178481","9783031178498"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-17849-8_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"28 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SISAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Similarity Search and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bologna","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sisap2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.sisap.org\/2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"34","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":"15","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":"8","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":"44% - 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","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":"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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}