{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T12:33:56Z","timestamp":1774528436880,"version":"3.50.1"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031442360","type":"print"},{"value":"9783031442377","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-44237-7_2","type":"book-chapter","created":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T22:01:45Z","timestamp":1695160905000},"page":"13-22","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Evaluation of\u00a0a\u00a0Visual Question Answering Architecture for\u00a0Pedestrian Attribute Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8673-2725","authenticated-orcid":false,"given":"Modesto","family":"Castrill\u00f3n-Santana","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2114-4137","authenticated-orcid":false,"given":"Elena","family":"S\u00e1nchez-Nielsen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2378-4277","authenticated-orcid":false,"given":"David","family":"Freire-Obreg\u00f3n","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7511-5783","authenticated-orcid":false,"given":"Oliverio J.","family":"Santana","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3022-7698","authenticated-orcid":false,"given":"Daniel","family":"Hern\u00e1ndez-Sosa","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2834-2067","authenticated-orcid":false,"given":"Javier","family":"Lorenzo-Navarro","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,20]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, A., et al.: VQA: visual question answering. Int. J. Comput. Vision 123, 4\u201331 (2015)","DOI":"10.1007\/s11263-016-0966-6"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Barra, S., Bisogni, C., De Marsico, M., Ricciardi, S.: Visual question answering: which investigated applications? Pattern Recognit. Lett. 151, 325\u2013331 (2021)","DOI":"10.1016\/j.patrec.2021.09.008"},{"key":"2_CR3","first-page":"1877","volume":"33","author":"TB Brown","year":"2020","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR4","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, 3\u20137 May 2021. OpenReview.net (2021). https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Freire-Obreg\u00f3n, D., De Marsico, M., Barra, P., Lorenzo-Navarro, J., Castrill\u00f3n-Santana, M.: Zero-shot ear cross-dataset transfer for person recognition on mobile devices. Pattern Recogn. Lett. 166, 143\u2013150 (2023)","DOI":"10.1016\/j.patrec.2023.01.012"},{"key":"2_CR6","doi-asserted-by":"publisher","unstructured":"Goyal, Y., Khot, T., Agrawal, A., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. Int. J. Comput. Vision 127(4), 398\u2013414 (2019). https:\/\/doi.org\/10.1007\/s11263-018-1116-0","DOI":"10.1007\/s11263-018-1116-0"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Greco, A., Vento, B.: PAR Contest 2023: pedestrian attributes recognition with multi-task learning. In: 20th International Conference on Computer Analysis of Images and Patterns: CAIP 2023. Springer, Cham (2023)","DOI":"10.1007\/978-3-031-44237-7_1"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Kafle, K., Kanan, C.: An analysis of visual question answering algorithms. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1983\u20131991 (2017)","DOI":"10.1109\/ICCV.2017.217"},{"key":"2_CR9","doi-asserted-by":"publisher","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models (2023). https:\/\/doi.org\/10.48550\/arXiv.2301.12597","DOI":"10.48550\/arXiv.2301.12597"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Competition-level code generation with alphacode. Science 378, 1092\u20131097 (2022)","DOI":"10.1126\/science.abq1158"},{"key":"2_CR11","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event. Proceedings of Machine Learning Research, vol. 139, pp. 8748\u20138763. PMLR (2021). https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"2_CR12","unstructured":"Sridhar, P., Lee, H., Dutta, A., Zisserman, A.: Wise image search engine (WISE). In: Wiki Workshop (2023)"},{"key":"2_CR13","unstructured":"Thoppilan, R., et al.: LaMDA: language models for dialog applications. arXiv abs\/2201.08239 (2022)"},{"key":"2_CR14","doi-asserted-by":"publisher","unstructured":"Toor, A.S., Wechsler, H., Nappi, M.: Biometric surveillance using visual question answering. Pattern Recognit. Lett. 126, 111\u2013118 (2019). https:\/\/doi.org\/10.1016\/j.patrec.2018.02.013. www.sciencedirect.com\/science\/article\/pii\/S0167865518300564. Robustness, Security and Regulation Aspects in Current Biometric Systems","DOI":"10.1016\/j.patrec.2018.02.013"},{"key":"2_CR15","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models. arXiv abs\/2302.13971 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Analysis of Images and Patterns"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44237-7_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T03:03:14Z","timestamp":1703214194000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44237-7_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031442360","9783031442377"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44237-7_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"20 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CAIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Analysis of Images and Patterns","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Limassol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cyprus","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"caip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cyprusconferences.org\/caip2023\/","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":"https:\/\/www.easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"67","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":"54","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":"81% - 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":"2.06","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":"2.09","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)"}}]}}