{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:59:10Z","timestamp":1742914750585,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819601189"},{"type":"electronic","value":"9789819601196"}],"license":[{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"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\/978-981-96-0119-6_22","type":"book-chapter","created":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T18:16:11Z","timestamp":1731780971000},"page":"220-231","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["False Positive Detection for\u00a0Text-Based Person Retrieval"],"prefix":"10.1007","author":[{"given":"Yan","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,12]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Jiang, D., Ye, M.: Cross-modal implicit relation reasoning and aligning for text-to-image person retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2787\u20132797 (2023)","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Li, S., et al.: Person search with natural language description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1970\u20131979 (2017)","DOI":"10.1109\/CVPR.2017.551"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Shen, F., et al.: Pedestrian-specific bipartite-aware similarity learning for text-based person retrieval. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 8922\u20138931 (2023)","DOI":"10.1145\/3581783.3612009"},{"key":"22_CR4","unstructured":"Li, J., Socher, R., Hoi, S.C.H.: Dividemix: learning with noisy labels as semi-supervised learning. arXiv preprint arXiv:2002.07394 (2020)"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Li, S., et al.: Identity-aware textual-visual matching with latent co-attention. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1890\u20131899 (2017)","DOI":"10.1109\/ICCV.2017.209"},{"key":"22_CR6","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Feng, Y., et al.: RONO: robust discriminative learning with noisy labels for 2D-3D cross-modal retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11610\u201311619 (2023)","DOI":"10.1109\/CVPR52729.2023.01117"},{"key":"22_CR8","unstructured":"Lin, Y., et al.: Revive: regional visual representation matters in knowledge based visual question answering. In: Advances in Neural Information Processing Systems, vol. 35, pp. 10560\u201310571 (2022)"},{"issue":"4","key":"22_CR9","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1109\/TETCI.2019.2892755","volume":"3","author":"S Li","year":"2019","unstructured":"Li, S., et al.: Visual to text: survey of image and video captioning. IEEE Trans. Emerg. Top. Comput. Intell. 3(4), 297\u2013312 (2019)","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"22_CR10","unstructured":"Han, X., et al.: Text-based person search with limited data. arXiv preprint arXiv:2110.10807 (2021)"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Yan, S., et al.: Clip-driven fine-grained text-image person re-identification. IEEE Trans. Image Process. (2023)","DOI":"10.1109\/TIP.2023.3327924"},{"key":"22_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Qin, Y., et al.: Noisy-Correspondence Learning for Text-to-Image Person Re-identification. arXiv preprint arXiv:2308.09911 (2023)","DOI":"10.1109\/CVPR52733.2024.02568"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: Bicro: noisy correspondence rectification for multi-modality data via bi-directional cross-modal similarity consistency. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19883\u201319892 (2023)","DOI":"10.1109\/CVPR52729.2023.01904"},{"issue":"8","key":"22_CR15","doi-asserted-by":"publisher","first-page":"9595","DOI":"10.1109\/TPAMI.2023.3247939","volume":"45","author":"P Hu","year":"2023","unstructured":"Hu, P., et al.: Cross-modal retrieval with partially mismatched pairs. IEEE Trans. Pattern Anal. Mach. Intell. 45(8), 9595\u20139610 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, X., Li, H., Ye, M.: Negative pre-aware for noisy cross-modal matching. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 7, pp. 7341\u20137349 (2024)","DOI":"10.1609\/aaai.v38i7.28564"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Bai, Y., et al.: Rasa: relation and sensitivity aware representation learning for text-based person search. arXiv preprint arXiv:2305.13653 (2023)","DOI":"10.24963\/ijcai.2023\/62"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Cao, M., et al.: An empirical study of clip for text-based person search. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 1, pp. 465\u2013473 (2024)","DOI":"10.1609\/aaai.v38i1.27801"},{"key":"22_CR19","unstructured":"Eom, C., Ham, B.: Learning disentangled representation for robust person re-identification. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Wu, Y., et al.: LapsCore: language-guided person search via color reasoning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1624\u20131633 (2021)","DOI":"10.1109\/ICCV48922.2021.00165"},{"key":"22_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-58610-2_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Wang","year":"2020","unstructured":"Wang, Z., Fang, Z., Wang, J., Yang, Y.: ViTAA: visual-textual attributes alignment in person search by natural language. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 402\u2013420. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_24"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, H.: Deep cross-modal projection learning for image-text matching. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 686\u2013701 (2018)","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Lu, Y., Bo, Y., He, W.: An ensemble model for combating label noise. In: Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, pp. 608\u2013617 (2022)","DOI":"10.1145\/3488560.3498376"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Multi-level fusion for person re-identification with incomplete marks. In: Proceedings of the 23rd ACM International Conference on Multimedia, pp. 1267\u20131270 (2015)","DOI":"10.1145\/2733373.2806400"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Zhou, Y., et al.: Tigan: text-based interactive image generation and manipulation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 3, pp. 3580\u20133588 (2022)","DOI":"10.1609\/aaai.v36i3.20270"},{"key":"22_CR26","unstructured":"Lin, Y., et al.: Multi-granularity Correspondence Learning from Long-term Noisy Videos. arXiv preprint arXiv:2401.16702 (2024)"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Yang, M., et al.: Learning with twin noisy labels for visible-infrared person re-identification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14308\u201314317 (2022)","DOI":"10.1109\/CVPR52688.2022.01391"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Qin, Y., et al.: Deep evidential learning with noisy correspondence for cross-modal retrieval. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4948\u20134956 (2022)","DOI":"10.1145\/3503161.3547922"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Zhu, H., et al.: Dual cross-attention learning for fine-grained visual categorization and object re-identification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4692\u20134702 (2022)","DOI":"10.1109\/CVPR52688.2022.00465"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: Learning the best pooling strategy for visual semantic embedding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15789\u201315798 (2021)","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"22_CR31","unstructured":"Ding, Z., et al.: Semantically self-aligned network for text-to-image part- aware person re-identification. arXiv preprint arXiv:2107.12666 (2021)"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Zhu, A., et al.: DSSL: deep surroundings-person separation learning for text-based person retrieval. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 209\u2013217 (2021)","DOI":"10.1145\/3474085.3475369"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2024: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0119-6_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T12:37:13Z","timestamp":1737635833000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0119-6_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,12]]},"ISBN":["9789819601189","9789819601196"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0119-6_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,12]]},"assertion":[{"value":"12 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"19 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2024","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":"pricai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}