{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T16:24:03Z","timestamp":1747153443682,"version":"3.40.5"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031801358"},{"type":"electronic","value":"9783031801365"}],"license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-80136-5_13","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T10:01:52Z","timestamp":1733047312000},"page":"185-197","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Missing Person Recognition Algorithms Based on\u00a0Image Captioning and\u00a0Visual Grounding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9258-1323","authenticated-orcid":false,"given":"Ayeong","family":"Jeong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4632-6873","authenticated-orcid":false,"given":"Yeongju","family":"Woo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8824-3788","authenticated-orcid":false,"given":"Han-young","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8316-997X","authenticated-orcid":false,"given":"Gayun","family":"Suh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1510-452X","authenticated-orcid":false,"given":"Chae-yeon","family":"Heo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0497-5660","authenticated-orcid":false,"given":"Yeong-jun","family":"Cho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8135-8252","authenticated-orcid":false,"given":"Hieyong","family":"Jeong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,1]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"13_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","unstructured":"Chen, Y.-C., et al.: UNITER: UNiversal image-TExt representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"key":"13_CR3","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.cviu.2019.01.003","volume":"180","author":"YJ Cho","year":"2019","unstructured":"Cho, Y.J., Kim, S.A., Park, J.H., Lee, K., Yoon, K.J.: Joint person re-identification and camera network topology inference in multiple cameras. Comput. Vis. Image Underst. 180, 34\u201346 (2019)","journal-title":"Comput. Vis. Image Underst."},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Cho, Y.J., Yoon, K.J.: Improving person re-identification via pose-aware multi-shot matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1354\u20131362 (2016)","DOI":"10.1109\/CVPR.2016.151"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10578\u201310587 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"13_CR6","unstructured":"Layne, R., Hospedales, T.M., Gong, S., Mary, Q.: Person re-identification by attributes. In: BMVC. vol. 2, pp. 8 (2012)"},{"key":"13_CR7","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":"13_CR8","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: HydraPlus-Net: attentive deep features for pedestrian analysis. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 350\u2013359 (2017)","DOI":"10.1109\/ICCV.2017.46"},{"key":"13_CR9","unstructured":"Matuszek, C., FitzGerald, N., Zettlemoyer, L., Bo, L., Fox, D.: A joint model of language and perception for grounded attribute learning. arXiv preprint arXiv:1206.6423 (2012)"},{"key":"13_CR10","unstructured":"Mokady, R., Hertz, A., Bermano, A.H.: ClipCap: clip prefix for image captioning. arXiv preprint arXiv:2111.09734 (2021)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Park, C., Kim, J., Chae, J., Lee, J.: A pilot study on intelligent surveillance system based on fashionpedia dataset. In: 2024 IEEE International Conference on Big Data and Smart Computing (BigComp), pp. 313\u2013316. IEEE (2024)","DOI":"10.1109\/BigComp60711.2024.00056"},{"key":"13_CR12","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"13_CR13","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"13_CR14","unstructured":"Sarfraz, M.S., Schumann, A., Wang, Y., Stiefelhagen, R.: Deep view-sensitive pedestrian attribute inference in an end-to-end model. arXiv preprint arXiv:1707.06089 (2017)"},{"issue":"1","key":"13_CR15","first-page":"3276704","volume":"2022","author":"R Ullah","year":"2022","unstructured":"Ullah, R., et al.: A real-time framework for human face detection and recognition in CCTV images. Math. Probl. Eng. 2022(1), 3276704 (2022)","journal-title":"Math. Probl. Eng."},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"13_CR17","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057. PMLR (2015)"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Yang, S., Zhou, Y., Zheng, Z., Wang, Y., Zhu, L., Wu, Y.: Towards unified text-based person retrieval: a large-scale multi-attribute and language search benchmark. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 4492\u20134501 (2023)","DOI":"10.1145\/3581783.3611709"},{"key":"13_CR19","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1016\/j.imavis.2016.07.004","volume":"58","author":"J Zhu","year":"2017","unstructured":"Zhu, J., Liao, S., Lei, Z., Li, S.Z.: Multi-label convolutional neural network based pedestrian attribute classification. Image Vis. Comput. 58, 224\u2013229 (2017)","journal-title":"Image Vis. Comput."},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Zhu, J., Jin, J., Yang, Z., Wu, X., Wang, X.: Learning clip guided visual-text fusion transformer for video-based pedestrian attribute recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2626\u20132629 (2023)","DOI":"10.1109\/CVPRW59228.2023.00261"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-80136-5_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T10:03:33Z","timestamp":1733047413000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-80136-5_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,1]]},"ISBN":["9783031801358","9783031801365"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-80136-5_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,1]]},"assertion":[{"value":"1 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}