{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T17:26:23Z","timestamp":1743009983838,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819984282"},{"type":"electronic","value":"9789819984299"}],"license":[{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"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\/978-981-99-8429-9_34","type":"book-chapter","created":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:02:17Z","timestamp":1703318537000},"page":"422-433","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Pedestrian Attribute Recognition Based on\u00a0Multimodal Transformer"],"prefix":"10.1007","author":[{"given":"Dan","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobing","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,24]]},"reference":[{"issue":"11","key":"34_CR1","doi-asserted-by":"publisher","first-page":"1949","DOI":"10.1109\/TMM.2015.2477680","volume":"17","author":"AH Abdulnabi","year":"2015","unstructured":"Abdulnabi, A.H., Wang, G., Lu, J., Jia, K.: Multi-task CNN model for attribute prediction. IEEE Trans. Multim. 17(11), 1949\u20131959 (2015)","journal-title":"IEEE Trans. Multim."},{"issue":"10","key":"34_CR2","doi-asserted-by":"publisher","first-page":"6994","DOI":"10.1109\/TCSVT.2022.3178144","volume":"32","author":"X Cheng","year":"2022","unstructured":"Cheng, X., Jia, M., Wang, Q., Zhang, J.: A simple visual-textual baseline for pedestrian attribute recognition. IEEE Trans. Circuits Syst. Video Technol. 32(10), 6994\u20137004 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"34_CR3","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"34_CR4","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Li, D., Chen, X., Huang, K.: Multi-attribute learning for pedestrian attribute recognition in surveillance scenarios. In: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), pp. 111\u2013115. IEEE (2015)","DOI":"10.1109\/ACPR.2015.7486476"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Li, D., Chen, X., Zhang, Z., Huang, K.: Pose guided deep model for pedestrian attribute recognition in surveillance scenarios. In: 2018 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136. IEEE (2018)","DOI":"10.1109\/ICME.2018.8486604"},{"key":"34_CR7","unstructured":"Li, D., Zhang, Z., Chen, X., Ling, H., Huang, K.: A richly annotated dataset for pedestrian attribute recognition. arXiv preprint arXiv:1603.07054 (2016)"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Li, Q., Zhao, X., He, R., Huang, K.: Visual-semantic graph reasoning for pedestrian attribute recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8634\u20138641 (2019)","DOI":"10.1609\/aaai.v33i01.33018634"},{"key":"34_CR9","doi-asserted-by":"publisher","unstructured":"Li, W., Cao, Z., Feng, J., Zhou, J., Lu, J.: Label2Label: a language modeling framework for multi-attribute learning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13672, pp. 562\u2013579. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19775-8_33","DOI":"10.1007\/978-3-031-19775-8_33"},{"key":"34_CR10","unstructured":"Liu, P., Liu, X., Yan, J., Shao, J.: Localization guided learning for pedestrian attribute recognition. arXiv preprint arXiv:1808.09102 (2018)"},{"key":"34_CR11","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":"34_CR12","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"34_CR13","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)"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Tang, C., Sheng, L., Zhang, Z., Hu, X.: Improving pedestrian attribute recognition with weakly-supervised multi-scale attribute-specific localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4997\u20135006 (2019)","DOI":"10.1109\/ICCV.2019.00510"},{"key":"34_CR15","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.neucom.2022.05.028","volume":"497","author":"Z Tang","year":"2022","unstructured":"Tang, Z., Huang, J.: Drformer: learning dual relations using transformer for pedestrian attribute recognition. Neurocomputing 497, 159\u2013169 (2022)","journal-title":"Neurocomputing"},{"key":"34_CR16","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Wang, J., Yang, Y., Mao, J., Huang, Z., Huang, C., Xu, W.: Cnn-rnn: a unified framework for multi-label image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2285\u20132294 (2016)","DOI":"10.1109\/CVPR.2016.251"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhu, X., Gong, S., Li, W.: Attribute recognition by joint recurrent learning of context and correlation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 531\u2013540 (2017)","DOI":"10.1109\/ICCV.2017.65"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Xu, P., Zhu, X., Clifton, D.A.: Multimodal learning with transformers: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, N., Paluri, M., Ranzato, M., Darrell, T., Bourdev, L.: Panda: pose aligned networks for deep attribute modeling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1637\u20131644 (2014)","DOI":"10.1109\/CVPR.2014.212"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8429-9_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:21:13Z","timestamp":1703319673000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8429-9_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,24]]},"ISBN":["9789819984282","9789819984299"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8429-9_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,24]]},"assertion":[{"value":"24 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","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":"532","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":"37% - 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":"3,78","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":"3,69","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)"}}]}}