{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T12:33:40Z","timestamp":1774528420599,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"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_1","type":"book-chapter","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T08:04:37Z","timestamp":1758009877000},"page":"3-15","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["An Extended Dataset and\u00a0a\u00a0Baseline for\u00a0Pedestrian Attribute Recognition with\u00a0Advanced Neural Networks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5495-2432","authenticated-orcid":false,"given":"Antonio","family":"Greco","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7687-4929","authenticated-orcid":false,"given":"Bruno","family":"Vento","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"issue":"11","key":"1_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. Multimedia 17(11), 1949\u20131959 (2015)","journal-title":"IEEE Trans. Multimedia"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Bhat, M.H.: A region-aware multi-modal framework for pedestrian attribute recognition via clip and graph neural networks. In: International Conference on Computer Analysis of Images and Patterns (CAIP) (2025)","DOI":"10.1007\/978-3-032-04968-1_4"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Bourdev, L., Maji, S., Malik, J.: Describing people: A poselet-based approach to attribute classification. In: International Conference on Computer Vision, pp. 1543\u20131550 (2011)","DOI":"10.1109\/ICCV.2011.6126413"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Bourdev, L., Malik, J.: Poselets: Body part detectors trained using 3d human pose annotations. In: IEEE International Conference on Computer Vision, pp. 1365\u20131372 (2009)","DOI":"10.1109\/ICCV.2009.5459303"},{"key":"1_CR5","doi-asserted-by":"publisher","first-page":"43905","DOI":"10.1109\/ACCESS.2018.2864672","volume":"6","author":"V Carletti","year":"2018","unstructured":"Carletti, V., Greco, A., Saggese, A., Vento, M.: Multi-object tracking by flying cameras based on a forward-backward interaction. IEEE Access 6, 43905\u201343919 (2018)","journal-title":"IEEE Access"},{"key":"1_CR6","doi-asserted-by":"crossref","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: Computer Analysis of Images and Patterns, pp. 13\u201322 (2023)","DOI":"10.1007\/978-3-031-44237-7_2"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Chen, H., Gallagher, A., Girod, B.: Describing clothing by semantic attributes. In: European Conference on Computer Vision (ECCV), pp. 609\u2013623. Springer (2012)","DOI":"10.1007\/978-3-642-33712-3_44"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Ci, Y., et al.: Unihcp: A unified model for human-centric perceptions. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17840\u201317852 (2023)","DOI":"10.1109\/CVPR52729.2023.01711"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Cormier, M., et al.: Upar challenge 2024: Pedestrian attribute recognition and attribute-based person retrieval-dataset, design, and results. In: IEEE\/CVF WACV, pp. 359\u2013367 (2024)","DOI":"10.1109\/WACVW60836.2024.00044"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Deng, Y., Luo, P., Loy, C.C., Tang, X.: Pedestrian attribute recognition at far distance. In: ACM International Conference on Multimedia, pp. 789\u2013792 (2014)","DOI":"10.1145\/2647868.2654966"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Everingham, M., Van\u00a0Gool, L., Williams, C., Winn, J., Zisserman, A.: The pascal visual object classes challenge (2010)","DOI":"10.1007\/s11263-009-0275-4"},{"issue":"1","key":"1_CR12","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1109\/TCSVT.2023.3285411","volume":"34","author":"X Fan","year":"2024","unstructured":"Fan, X., Zhang, Y., Lu, Y., Wang, H.: Parformer: Transformer-based multi-task network for pedestrian attribute recognition. IEEE Trans. Circuits Syst. Video Technol. 34(1), 411\u2013423 (2024)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Foggia, P., Greco, A., Percannella, G., Vento, M., Vigilante, V.: A system for gender recognition on mobile robots. In: International Conference on Applications of Intelligent Systems, pp.\u00a01\u20136 (2019)","DOI":"10.1145\/3309772.3309781"},{"key":"1_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105651","volume":"118","author":"P Foggia","year":"2023","unstructured":"Foggia, P., Greco, A., Saggese, A., Vento, M.: Multi-task learning on the edge for effective gender, age, ethnicity and emotion recognition. Eng. Appl. Artif. Intell. 118, 105651 (2023)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Gou, M., Karanam, S., Liu, W., Camps, O., Radke, R.J.: Dukemtmc4reid: A large-scale multi-camera person re-identification dataset. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 10\u201319 (2017)","DOI":"10.1109\/CVPRW.2017.185"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Greco, A., Roberto, A., Saggese, A., Vento, M., Vigilante, V.: Emotion analysis from faces for social robotics. In: International Conference on Systems, Man and Cybernetics (SMC), pp. 358\u2013364. IEEE (2019)","DOI":"10.1109\/SMC.2019.8914039"},{"issue":"6","key":"1_CR17","doi-asserted-by":"publisher","first-page":"1736","DOI":"10.3390\/s25061736","volume":"25","author":"A Greco","year":"2025","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), 1736 (2025)","journal-title":"Sensors"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Greco, A., Saggese, A., Vento, B.: A robust and efficient overhead people counting system for retail applications. In: International Conference on Image Analysis and Processing, pp. 139\u2013150. Springer (2022)","DOI":"10.1007\/978-3-031-06430-2_12"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Greco, A., Saggese, A., Vento, M.: Digital signage by real-time gender recognition from face images. In: IEEE International Workshop on Metrology for Industry 4.0 & IoT, pp. 309\u2013313. IEEE (2020)","DOI":"10.1109\/MetroInd4.0IoT48571.2020.9138194"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Greco, A., Saldutti, S., Vento, B.: Fast and effective detection of personal protective equipment on smart cameras. In: International Conference on Pattern Recognition, pp. 95\u2013108. Springer (2022)","DOI":"10.1007\/978-3-031-37660-3_7"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Greco, A., Vento, B.: Par contest 2023: pedestrian attributes recognition with multi-task learning. In: International Conference on Computer Analysis of Images and Patterns, pp. 3\u201312. Springer (2023)","DOI":"10.1007\/978-3-031-44237-7_1"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Hall, D., Perona, P.: Fine-grained classification of pedestrians in video: Benchmark and state of the art. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5482\u20135491 (2015)","DOI":"10.1109\/CVPR.2015.7299187"},{"key":"1_CR23","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1016\/j.patrec.2020.07.018","volume":"138","author":"Z Ji","year":"2020","unstructured":"Ji, Z., Hu, Z., He, E., Han, J., Pang, Y.: Pedestrian attribute recognition based on multiple time steps attention. Pattern Recogn. Lett. 138, 170\u2013176 (2020)","journal-title":"Pattern Recogn. Lett."},{"key":"1_CR24","unstructured":"Jia, J., Huang, H., Chen, X., Huang, K.: Rethinking of pedestrian attribute recognition: A reliable evaluation under zero-shot pedestrian identity setting. arXiv preprint arXiv:2107.03576 (2021)"},{"key":"1_CR25","unstructured":"Jia, J., Huang, H., Yang, W., Chen, X., Huang, K.: Rethinking of pedestrian attribute recognition: realistic datasets with efficient method. arXiv preprint arXiv:2005.11909 (2020)"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Kairanbay, M., Salman, A.: Multi-task pedestrian attribute classification using convnext with advanced data augmentation. In: International Conference on Computer Analysis of Images and Patterns (CAIP) (2025)","DOI":"10.1007\/978-3-032-04968-1_3"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Li, D., Chen, X., Huang, K.: Multi-attribute learning for pedestrian attribute recognition in surveillance scenarios. In: IEEE Asian Conference on Pattern Recognition (ACPR), pp. 111\u2013115 (2015)","DOI":"10.1109\/ACPR.2015.7486476"},{"issue":"4","key":"1_CR28","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1109\/TIP.2018.2878349","volume":"28","author":"D Li","year":"2018","unstructured":"Li, D., Zhang, Z., Chen, X., Huang, K.: A richly annotated pedestrian dataset for person retrieval in real surveillance scenarios. IEEE Trans. Image Process. 28(4), 1575\u20131590 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"1_CR29","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.patcog.2019.06.006","volume":"95","author":"Y Lin","year":"2019","unstructured":"Lin, Y., Zheng, L., Zheng, Z., Wu, Y., Hu, Z., Yan, C., Yang, Y.: Improving person re-identification by attribute and identity learning. Pattern Recogn. 95, 151\u2013161 (2019)","journal-title":"Pattern Recogn."},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Liu, X., Zhao, H., Tian, M., Sheng, L., Shao, J., Yi, S., Yan, J., Wang, X.: Hydraplus-net: Attentive deep features for pedestrian analysis. In: IEEE International Conference on Computer Vision (ICCV), pp. 350\u2013359 (2017)","DOI":"10.1109\/ICCV.2017.46"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Salas-C\u00e1ceres, J.: Leveraging generalist vqa models to improve zero-shot pedestrian attribute recognition. In: International Conference on Computer Analysis of Images and Patterns (CAIP) (2025)","DOI":"10.1007\/978-3-032-04968-1_2"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Sharma, G., Jurie, F.: Learning discriminative spatial representation for image classification. In: British Machine Vision Conference (BMVC), pp. 1\u201311 (2011)","DOI":"10.5244\/C.25.6"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Sooksatra, S., Rujikietgumjorn, S.: Skeleton-based attention mask for pedestrian attribute recognition network. J. Imaging 7(12) (2021)","DOI":"10.3390\/jimaging7120264"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Sudowe, P., Leibe, B.: Patchit: Self-supervised network weight initialization for fine-grained recognition. In: British Machine Vision Conference (BMVC). vol.\u00a01, pp. 24\u201325 (2016)","DOI":"10.5244\/C.30.75"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Sudowe, P., Spitzer, H., Leibe, B.: Person attribute recognition with a jointly-trained holistic cnn model. In: IEEE International Conference on Computer Vision Workshops, pp. 87\u201395 (2015)","DOI":"10.1109\/ICCVW.2015.51"},{"key":"1_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108220","volume":"121","author":"X Wang","year":"2022","unstructured":"Wang, X., Zheng, S., Yang, R., Zheng, A., Chen, Z., Tang, J., Luo, B.: Pedestrian attribute recognition: a survey. Pattern Recogn. 121, 108220 (2022)","journal-title":"Pattern Recogn."},{"key":"1_CR37","unstructured":"Wang, Y., et\u00a0al.: Hulk: A universal knowledge translator for human-centric tasks. arXiv preprint arXiv:2312.01697 (2023)"},{"key":"1_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, J., Liao, S., Lei, Z., Yi, D., Li, S.: Pedestrian attribute classification in surveillance: database and evaluation. In: IEEE International Conference on Computer Vision Workshops, pp. 331\u2013338 (2013)","DOI":"10.1109\/ICCVW.2013.51"}],"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_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T04:42:06Z","timestamp":1765168926000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04968-1_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"ISBN":["9783032049674","9783032049681"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04968-1_1","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"}}]}}