{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T13:17:35Z","timestamp":1743081455135,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031773884"},{"type":"electronic","value":"9783031773891"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-77389-1_5","type":"book-chapter","created":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T18:31:55Z","timestamp":1737484315000},"page":"56-69","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["VLPSR: Enhancing Zero-Shot Object ReID with\u00a0Vision-Language Model"],"prefix":"10.1007","author":[{"given":"Mingzhe","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,22]]},"reference":[{"key":"5_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"5_CR2","unstructured":"Bao, L., Wei, L., Qiu, X., Zhou, W., Li, H., Tian, Q.: Learning transferable pedestrian representation from multimodal information supervision. arXiv preprint arXiv:2304.05554 (2023)"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Dai, Y., Li, X., Liu, J., Tong, Z., Duan, L.Y.: Generalizable person re-identification with relevance-aware mixture of experts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16145\u201316154 (2021)","DOI":"10.1109\/CVPR46437.2021.01588"},{"key":"5_CR4","unstructured":"Dai, Z., Wang, G., Yuan, W., Zhu, S., Tan, P.: Cluster contrast for unsupervised person re-identification. In: Proceedings of the Asian Conference on Computer Vision, pp. 1142\u20131160 (2022)"},{"key":"5_CR5","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16\u00a0$$\\times \\,$$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Fu, D., et al.: Unsupervised pre-training for person re-identification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14750\u201314759 (2021)","DOI":"10.1109\/CVPR46437.2021.01451"},{"key":"5_CR7","unstructured":"Gong, Y., Zeng, Z., Chen, L., Luo, Y., Weng, B., Ye, F.: A person re-identification data augmentation method with adversarial defense effect. arXiv preprint arXiv:2101.08783 (2021)"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"He, S., Luo, H., Wang, P., Wang, F., Li, H., Jiang, W.: TransReID: transformer-based object re-identification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15013\u201315022 (2021)","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Rasheed, H., Maaz, M., Khan, S., Khan, F.S.: MaPLe: multi-modal prompt learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19113\u201319122 (2023)","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Wasim, S.T., Naseer, M., Khan, S., Yang, M.H., Khan, F.S.: Self-regulating prompts: Foundational model adaptation without forgetting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15190\u201315200 (2023)","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"5_CR12","unstructured":"Li, J., Gong, X.: Prototypical contrastive learning-based clip fine-tuning for object re-identification. arXiv preprint arXiv:2310.17218 (2023)"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Li, S., Sun, L., Li, Q.: CLIP-ReID: exploiting vision-language model for image re-identification without concrete text labels. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 1405\u20131413 (2023)","DOI":"10.1609\/aaai.v37i1.25225"},{"key":"5_CR14","first-page":"1992","volume":"34","author":"S Liao","year":"2021","unstructured":"Liao, S., Shao, L.: TransMatcher: deep image matching through transformers for generalizable person re-identification. Adv. Neural. Inf. Process. Syst. 34, 1992\u20132003 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.06.006","author":"Y Lin","year":"2019","unstructured":"Lin, Y., et al.: Improving person re-identification by attribute and identity learning. Pattern Recogn. (2019). https:\/\/doi.org\/10.1016\/j.patcog.2019.06.006","journal-title":"Pattern Recogn."},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Liu, H., Tian, Y., Yang, Y., Pang, L., Huang, T.: Deep relative distance learning: tell the difference between similar vehicles. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2167\u20132175 (2016)","DOI":"10.1109\/CVPR.2016.238"},{"key":"5_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"869","DOI":"10.1007\/978-3-319-46475-6_53","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Liu","year":"2016","unstructured":"Liu, X., Liu, W., Mei, T., Ma, H.: A deep learning-based approach to progressive vehicle re-identification for urban surveillance. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 869\u2013884. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_53"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Luo, H., Gu, Y., Liao, X., Lai, S., Jiang, W.: Bag of tricks and a strong baseline for deep person re-identification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp.\u00a00\u20130 (2019)","DOI":"10.1109\/CVPRW.2019.00190"},{"key":"5_CR19","unstructured":"Luo, H., et al.: Self-supervised pre-training for transformer-based person re-identification. arXiv preprint arXiv:2111.12084 (2021)"},{"key":"5_CR20","unstructured":"Lv, K., et al.: Style variable and irrelevant learning for generalizable person re-identification. ACM Trans. Multimedia Comput. Commun. Appl. (2022)"},{"key":"5_CR21","doi-asserted-by":"publisher","unstructured":"Naphade, M., et al.: The 6th AI city challenge. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 3346\u20133355. IEEE Computer Society, June 2022. https:\/\/doi.org\/10.1109\/CVPRW56347.2022.00378","DOI":"10.1109\/CVPRW56347.2022.00378"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Naphade, M., et al.: The 7th AI city challenge. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2023","DOI":"10.1109\/CVPRW59228.2023.00586"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Ni, H., Song, J., Luo, X., Zheng, F., Li, W., Shen, H.T.: Meta distribution alignment for generalizable person re-identification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2487\u20132496 (2022)","DOI":"10.1109\/CVPR52688.2022.00252"},{"key":"5_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1007\/978-3-030-01225-0_29","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Pan","year":"2018","unstructured":"Pan, X., Luo, P., Shi, J., Tang, X.: Two at once: enhancing learning and generalization capacities via IBN-Net. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 484\u2013500. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_29"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Pratt, S., Covert, I., Liu, R., Farhadi, A.: What does a platypus look like? Generating customized prompts for zero-shot image classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15691\u201315701 (2023)","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Ristani, E., Solera, F., Zou, R.S., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: ECCV Workshops (2016)","DOI":"10.1007\/978-3-319-48881-3_2"},{"issue":"3","key":"5_CR27","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","volume":"8","author":"W Wang","year":"2022","unstructured":"Wang, W., et al.: PVT V2: improved baselines with pyramid vision transformer. Comput. Visual Media 8(3), 415\u2013424 (2022)","journal-title":"Comput. Visual Media"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Wei, L., Zhang, S., Gao, W., Tian, Q.: Person transfer GAN to bridge domain gap for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 79\u201388 (2018)","DOI":"10.1109\/CVPR.2018.00016"},{"key":"5_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1007\/978-3-319-46478-7_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Y Wen","year":"2016","unstructured":"Wen, Y., Zhang, K., Li, Z., Qiao, Yu.: A discriminative feature learning approach for deep face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 499\u2013515. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_31"},{"key":"5_CR30","unstructured":"Xiang, S., et al.: Learning robust visual-semantic embedding for generalizable person re-identification. arXiv preprint arXiv:2304.09498 (2023)"},{"key":"5_CR31","unstructured":"Xu, H., et al.: Demystifying clip data. arXiv preprint arXiv:2309.16671 (2023)"},{"key":"5_CR32","unstructured":"Yang, S., Zhang, Y.: MLLMReID: multimodal large language model-based person re-identification. arXiv preprint arXiv:2401.13201 (2024)"},{"issue":"6","key":"5_CR33","doi-asserted-by":"publisher","first-page":"2872","DOI":"10.1109\/TPAMI.2021.3054775","volume":"44","author":"M Ye","year":"2021","unstructured":"Ye, M., Shen, J., Lin, G., Xiang, T., Shao, L., Hoi, S.C.: Deep learning for person re-identification: a survey and outlook. IEEE Trans. Pattern Anal. Mach. Intell. 44(6), 2872\u20132893 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5_CR34","doi-asserted-by":"crossref","unstructured":"Yi, D., Lei, Z., Li, S.: Deep metric learning for practical person re-identification. arXiv e-prints 89 (2014)","DOI":"10.1109\/ICPR.2014.16"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Zheng, K., Lan, C., Zeng, W., Zhang, Z., Zha, Z.J.: Exploiting sample uncertainty for domain adaptive person re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 3538\u20133546 (2021)","DOI":"10.1609\/aaai.v35i4.16468"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Zheng, K., Liu, W., He, L., Mei, T., Luo, J., Zha, Z.J.: Group-aware label transfer for domain adaptive person re-identification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5310\u20135319 (2021)","DOI":"10.1109\/CVPR46437.2021.00527"},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: IEEE International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.133"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Yang, X., Yu, Z., Zheng, L., Yang, Y., Kautz, J.: Joint discriminative and generative learning for person re-identification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2138\u20132147 (2019)","DOI":"10.1109\/CVPR.2019.00224"},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), October 2017","DOI":"10.1109\/ICCV.2017.405"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Cao, D., Li, S.: Re-ranking person re-identification with k-reciprocal encoding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1318\u20131327 (2017)","DOI":"10.1109\/CVPR.2017.389"},{"issue":"9","key":"5_CR41","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"},{"issue":"9","key":"5_CR42","first-page":"5056","volume":"44","author":"K Zhou","year":"2021","unstructured":"Zhou, K., Yang, Y., Cavallaro, A., Xiang, T.: Learning generalisable omni-scale representations for person re-identification. IEEE Trans. Pattern Anal. Mach. Intell. 44(9), 5056\u20135069 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5_CR43","unstructured":"Zuo, J., Yu, C., Sang, N., Gao, C.: PLIP: language-image pre-training for person representation learning. arXiv preprint arXiv:2305.08386 (2023)"}],"container-title":["Lecture Notes in Computer Science","Advances in Visual Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-77389-1_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T18:32:09Z","timestamp":1737484329000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-77389-1_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031773884","9783031773891"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-77389-1_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"22 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISVC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Visual Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lake Tahoe, NV","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","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":"21 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isvc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isvc.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}