{"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":1774528436783,"version":"3.50.1"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032049674","type":"print"},{"value":"9783032049681","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-04968-1_2","type":"book-chapter","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T08:04:59Z","timestamp":1758009899000},"page":"16-26","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Leveraging Generalist VQA Models to\u00a0Improve Zero-Shot Pedestrian Attribute Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7543-3385","authenticated-orcid":false,"given":"Jos\u00e9","family":"Salas-C\u00e1ceres","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"key":"2_CR1","doi-asserted-by":"publisher","unstructured":"Barra, S., Bisogni, C., De Marsico, M., Ricciardi, S.: Visual question answering: which investigated applications? Pattern Recogn. Lett. 151, 325\u2013331 (2021). https:\/\/doi.org\/10.1016\/j.patrec.2021.09.008. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0167865521003147","DOI":"10.1016\/j.patrec.2021.09.008"},{"key":"2_CR2","unstructured":"Beyer*, L., et al.: PaliGemma: a versatile 3B VLM for transfer. arXiv preprint arXiv:2407.07726 (2024)"},{"key":"2_CR3","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/978-3-031-44237-7_2","volume-title":"Computer Analysis of Images and Patterns","author":"M Castrill\u00f3n-Santana","year":"2023","unstructured":"Castrill\u00f3n-Santana, M., S\u00e1nchez-Nielsen, E., Freire-Obreg\u00f3n, D., Santana, O.J., Hern\u00e1ndez-Sosa, D., Lorenzo-Navarro, J.: Evaluation of a visual question answering architecture for pedestrian attribute recognition. In: Tsapatsoulis, N., et al. (eds.) Computer Analysis of Images and Patterns, pp. 13\u201322. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-44237-7_2"},{"key":"2_CR4","doi-asserted-by":"publisher","unstructured":"Castrill\u00f3n-Santana, M., S\u00e1nchez-Nielsen, E., Freire-Obreg\u00f3n, D., Santana, O.J., Hern\u00e1ndez-Sosa, D., Lorenzo-Navarro, J.: Visual question answering models for zero-shot pedestrian attribute recognition: a comparative study. SN Comput. Sci. 5(6) (2024). https:\/\/doi.org\/10.1007\/s42979-024-02985-0","DOI":"10.1007\/s42979-024-02985-0"},{"key":"2_CR5","doi-asserted-by":"publisher","unstructured":"Deng, Y., Luo, P., Loy, C.C., Tang, X.: Pedestrian attribute recognition at far distance. In: Proceedings of the 22nd ACM International Conference on Multimedia, p. 789\u2013792. Association for Computing Machinery, New York (2014). https:\/\/doi.org\/10.1145\/2647868.2654966","DOI":"10.1145\/2647868.2654966"},{"key":"2_CR6","doi-asserted-by":"publisher","unstructured":"Greco, A., Saggese, A., Sansone, C., Vento, B.: An experimental evaluation of smart sensors for pedestrian attribute recognition using multi-task learning and vision language models. Sensors 25(6) (2025). https:\/\/doi.org\/10.3390\/s25061736. https:\/\/www.mdpi.com\/1424-8220\/25\/6\/1736","DOI":"10.3390\/s25061736"},{"key":"2_CR7","doi-asserted-by":"publisher","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, Heidelberg (2023). https:\/\/doi.org\/10.1007\/978-3-031-44237-7_1","DOI":"10.1007\/978-3-031-44237-7_1"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Greco, A., Vento, B.: Par contest 2025: pedestrian attributes recognition with advanced neural networks. In: 21st International Conference on Computer Analysis of Images and Patterns: CAIP 2025. Springer, Heidelberg (2025)","DOI":"10.1007\/978-3-032-04968-1_1"},{"key":"2_CR9","unstructured":"Greco, A., Vento, B.: Pedestrian attribute recognition (PAR) contest 2023 (2025). https:\/\/mivia.unisa.it\/par2023\/. Accessed 10 June 2025"},{"key":"2_CR10","unstructured":"Greco, A., Vento, B.: Pedestrian attribute recognition (PAR) contest 2025 (2025). https:\/\/mivia.unisa.it\/par2025\/. Accessed 04 June 2025"},{"key":"2_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1007\/978-3-540-25948-0_99","volume-title":"Biometric Authentication","author":"AK Jain","year":"2004","unstructured":"Jain, A.K., Dass, S.C., Nandakumar, K.: Soft biometric traits for personal recognition systems. In: Zhang, D., Jain, A.K. (eds.) ICBA 2004. LNCS, vol. 3072, pp. 731\u2013738. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-25948-0_99"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Li, D., Chen, X., Huang, K.: Multi-attribute learning for pedestrian attribute recognition in surveillance scenarios. In: ACPR, pp. 111\u2013115 (2015)","DOI":"10.1109\/ACPR.2015.7486476"},{"key":"2_CR13","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: 40 International Conference on Machine Learning (ICML) (2022)"},{"key":"2_CR14","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1109\/OJITS.2025.3554387","volume":"6","author":"F Munir","year":"2025","unstructured":"Munir, F., Azam, S., Mihaylova, T., Kyrki, V., Kucner, T.P.: Pedestrian vision language model for intentions prediction. IEEE Open J. Intell. Transport. Syst. 6, 393\u2013406 (2025). https:\/\/doi.org\/10.1109\/OJITS.2025.3554387","journal-title":"IEEE Open J. Intell. Transport. Syst."},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Ngo, B.H., Ngo, S.T., Le, P.D., Phan, Q.M., Tran, M.T., Le, T.N.: Crosspar: enhancing pedestrian attribute recognition with vision-language fusion and human-centric pre-training. In: Proceedings of the Asian Conference on Computer Vision (ACCV), pp. 1301\u20131315 (2024)","DOI":"10.1007\/978-981-96-0960-4_12"},{"key":"2_CR16","unstructured":"Steiner, A., et al.: Paligemma 2: a family of versatile vlms for transfer. arXiv preprint arXiv:2412.03555 (2024)"},{"issue":"1","key":"2_CR17","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41746-024-01029-4","volume":"7","author":"L Wang","year":"2024","unstructured":"Wang, L., et al.: Prompt engineering in consistency and reliability with the evidence-based guideline for LLMs. NPJ Digit. Med. 7(1), 41 (2024)","journal-title":"NPJ Digit. Med."},{"key":"2_CR18","doi-asserted-by":"publisher","unstructured":"Wang, X., et al.: Pedestrian attribute recognition: a survey. Pattern Recogn. 121, 108220 (2022). https:\/\/doi.org\/10.1016\/j.patcog.2021.108220. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0031320321004015","DOI":"10.1016\/j.patcog.2021.108220"},{"issue":"8","key":"2_CR19","doi-asserted-by":"publisher","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","volume":"46","author":"J Zhang","year":"2024","unstructured":"Zhang, J., Huang, J., Jin, S., Lu, S.: Vision-language models for vision tasks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 46(8), 5625\u20135644 (2024). https:\/\/doi.org\/10.1109\/TPAMI.2024.3369699","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"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\/978-3-032-04968-1_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T04:42:03Z","timestamp":1765168923000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04968-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"ISBN":["9783032049674","9783032049681"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04968-1_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,17]]},"assertion":[{"value":"17 September 2025","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":"Las Palmas de Gran Canaria","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"caip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/caip2025.com","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}