{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T16:26:00Z","timestamp":1748535960008,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":39,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819786190"},{"type":"electronic","value":"9789819786206"}],"license":[{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"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\/978-981-97-8620-6_32","type":"book-chapter","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:02:10Z","timestamp":1729371730000},"page":"468-481","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multimodal Feature Hierarchical Fusion for Text-Image Person Re-identification"],"prefix":"10.1007","author":[{"given":"Jiaxuan","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Likun","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanhu","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,20]]},"reference":[{"key":"32_CR1","doi-asserted-by":"crossref","unstructured":"An, L., Bhanu, B., Yang, S.: Face recognition in multi-camera surveillance videos. In: Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), pp. 2885\u20132888. IEEE (2012)","DOI":"10.1109\/AVSS.2012.17"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Li, H., Brandt, J., Lin, Z., Shen, X., Hua, G.: A multi-level contextual model for person recognition in photo albums. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1297\u20131305 (2016)","DOI":"10.1109\/CVPR.2016.145"},{"issue":"9","key":"32_CR3","first-page":"1554","volume":"44","author":"Y Li","year":"2018","unstructured":"Li, Y., Zhuo, L., Zhang, J., Li, F., Zhang, H.: A survey of person re-identification. Acta Autom. Sin. 44(9), 1554\u20131568 (2018)","journal-title":"Acta Autom. Sin."},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"Zhang, N., Paluri, M., Taigman, Y., Fergus, R., Bourdev, L.: Beyond frontal faces: Improving person recognition using multiple cues. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4804\u20134813 (2015)","DOI":"10.1109\/CVPR.2015.7299113"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Anguelov, D., Lee, K.c., Gokturk, S.B., Sumengen, B.: Contextual identity recognition in personal photo albums. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20137. IEEE (2007)","DOI":"10.1109\/CVPR.2007.383057"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Joon Oh, S., Benenson, R., Fritz, M., Schiele, B.: Person recognition in personal photo collections. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3862\u20133870 (2015)","DOI":"10.1109\/ICCV.2015.440"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Karanam, S., Li, Y., Radke, R.J.: Person re-identification with discriminatively trained viewpoint invariant dictionaries. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4516\u20134524 (2015)","DOI":"10.1109\/ICCV.2015.513"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Gray, D., Tao, H.: Viewpoint invariant pedestrian recognition with an ensemble of localized features. In: Computer Vision-ECCV 2008: 10th European Conference on Computer Vision, Marseille, France, October 12\u201318, 2008, Proceedings, Part I 10, pp. 262\u2013275. Springer (2008)","DOI":"10.1007\/978-3-540-88682-2_21"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Schmid, C.: Constructing models for content-based image retrieval. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, vol. 2, pp. II\u2013II. IEEE (2001)","DOI":"10.1109\/CVPR.2001.990922"},{"issue":"2","key":"32_CR10","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/BF00204594","volume":"61","author":"I Fogel","year":"1989","unstructured":"Fogel, I., Sagi, D.: Gabor filters as texture discriminator. Biol. Cybern. 61(2), 103\u2013113 (1989)","journal-title":"Biol. Cybern."},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Li, W., Zhao, R., Xiao, T., Wang, X.: Deepreid: deep filter pairing neural network for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 152\u2013159 (2014)","DOI":"10.1109\/CVPR.2014.27"},{"issue":"9","key":"32_CR12","doi-asserted-by":"publisher","first-page":"4500","DOI":"10.1109\/TIP.2019.2910414","volume":"28","author":"L Zheng","year":"2019","unstructured":"Zheng, L., Huang, Y., Lu, H., Yang, Y.: Pose-invariant embedding for deep person re-identification. IEEE Trans. Image Process. 28(9), 4500\u20134509 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, Y., Cavallaro, A., Xiang, T.: Omni-scale feature learning for person re-identification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3702\u20133712 (2019)","DOI":"10.1109\/ICCV.2019.00380"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Yan, Y., Zhang, Q., Ni, B., Zhang, W., Xu, M., Yang, X.: Learning context graph for person search. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2158\u20132167 (2019)","DOI":"10.1109\/CVPR.2019.00226"},{"key":"32_CR15","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: Proceedings of the IEEE International Conference on Computer Vision, pp. 350\u2013359 (2017)","DOI":"10.1109\/ICCV.2017.46"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Li, S., Xiao, T., Li, H., Zhou, B., Yue, D., Wang, X.: 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":"32_CR17","doi-asserted-by":"crossref","unstructured":"Li, S., Xiao, T., Li, H., Yang, W., Wang, X.: 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":"32_CR18","doi-asserted-by":"crossref","unstructured":"Yan, S., Xu, J., Liu, Y., Xu, L.: Hornet: a hierarchical offshoot recurrent network for improving person re-id via image captioning (2019). arXiv:1908.04915","DOI":"10.24963\/ijcai.2019\/742"},{"issue":"5","key":"32_CR19","doi-asserted-by":"publisher","first-page":"2814","DOI":"10.1109\/TCSVT.2021.3099943","volume":"32","author":"H Li","year":"2021","unstructured":"Li, H., Dong, N., Yu, Z., Tao, D., Qi, G.: Triple adversarial learning and multi-view imaginative reasoning for unsupervised domain adaptation person re-identification. IEEE Trans. Circuits Syst. Video Technol. 32(5), 2814\u20132830 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"32_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108287","volume":"122","author":"MV Prasad","year":"2022","unstructured":"Prasad, M.V., Balakrishnan, R., et al.: Spatio-temporal association rule based deep annotation-free clustering (STAR-DAC) for unsupervised person re-identification. Pattern Recogn. 122, 108287 (2022)","journal-title":"Pattern Recogn."},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Zhou, H., Huang, C., Cheng, H.: A relation network design for visible thermal person re-identification. In: 2021 6th International Conference on Intelligent Computing and Signal Processing (ICSP), pp. 511\u2013515. IEEE (2021)","DOI":"10.1109\/ICSP51882.2021.9408949"},{"key":"32_CR22","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1016\/j.neucom.2021.12.047","volume":"492","author":"Y Guo","year":"2022","unstructured":"Guo, Y., Liu, Z., Luo, H., Pu, H., Tan, J.: Multi-person multi-camera tracking for live stream videos based on improved motion model and matching cascade. Neurocomputing 492, 561\u2013571 (2022)","journal-title":"Neurocomputing"},{"issue":"4","key":"32_CR23","doi-asserted-by":"publisher","first-page":"2170","DOI":"10.1109\/TCSVT.2021.3088446","volume":"32","author":"H Jin","year":"2021","unstructured":"Jin, H., Lai, S., Qian, X.: Occlusion-sensitive person re-identification via attribute-based shift attention. IEEE Trans. Circuits Syst. Video Technol. 32(4), 2170\u20132185 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"32_CR24","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1016\/j.neucom.2021.11.013","volume":"470","author":"Y Shi","year":"2022","unstructured":"Shi, Y., Ling, H., Wu, L., Zhang, B., Li, P.: Attribute disentanglement and registration for occluded person re-identification. Neurocomputing 470, 226\u2013235 (2022)","journal-title":"Neurocomputing"},{"key":"32_CR25","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"32_CR26","doi-asserted-by":"crossref","unstructured":"Ye, M., Lan, X., Yuen, P.C.: Robust anchor embedding for unsupervised video person re-identification in the wild. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 170\u2013186 (2018)","DOI":"10.1007\/978-3-030-01234-2_11"},{"key":"32_CR27","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.neucom.2022.04.081","volume":"494","author":"Y Chen","year":"2022","unstructured":"Chen, Y., Zhang, G., Lu, Y., Wang, Z., Zheng, Y.: TIPCB: a simple but effective part-based convolutional baseline for text-based person search. Neurocomputing 494, 171\u2013181 (2022)","journal-title":"Neurocomputing"},{"key":"32_CR28","unstructured":"Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax (2016). arXiv:1611.01144"},{"issue":"3","key":"32_CR29","doi-asserted-by":"publisher","first-page":"1478","DOI":"10.1109\/TCYB.2019.2917713","volume":"51","author":"W Lin","year":"2019","unstructured":"Lin, W., Li, Y., Xiao, H., See, J., Zou, J., Xiong, H., Wang, J., Mei, T.: Group reidentification with multigrained matching and integration. IEEE Trans. Cybern. 51(3), 1478\u20131492 (2019)","journal-title":"IEEE Trans. Cybern."},{"key":"32_CR30","unstructured":"Xiao, T., Li, S., Wang, B., Lin, L., Wang, X.: End-to-end deep learning for person search 2(2), 4 (2016). arXiv:1604.01850"},{"issue":"6","key":"32_CR31","doi-asserted-by":"publisher","first-page":"7001","DOI":"10.1109\/TPAMI.2020.3032542","volume":"45","author":"Y Yan","year":"2020","unstructured":"Yan, Y., Qin, J., Ni, B., Chen, J., Liu, L., Zhu, F., Zheng, W.S., Yang, X., Shao, L.: Learning multi-attention context graph for group-based re-identification. IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 7001\u20137018 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"32_CR32","doi-asserted-by":"crossref","unstructured":"Zhu, A., Wang, Z., Li, Y., Wan, X., Jin, J., Wang, T., Hu, F., Hua, G.: 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"},{"key":"32_CR33","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057. PMLR (2015)"},{"issue":"10","key":"32_CR34","doi-asserted-by":"publisher","first-page":"2597","DOI":"10.1109\/TMM.2019.2958756","volume":"22","author":"H Luo","year":"2019","unstructured":"Luo, H., Jiang, W., Gu, Y., Liu, F., Liao, X., Lai, S., Gu, J.: A strong baseline and batch normalization neck for deep person re-identification. IEEE Trans. Multimedia 22(10), 2597\u20132609 (2019)","journal-title":"IEEE Trans. Multimedia"},{"key":"32_CR35","doi-asserted-by":"crossref","unstructured":"Sun, Y., Zheng, L., Yang, Y., Tian, Q., Wang, S.: Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline). In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 480\u2013496 (2018)","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"32_CR36","unstructured":"Ding, Z., Ding, C., Shao, Z., Tao, D.: Semantically self-aligned network for text-to-image part-aware person re-identification (2021). arXiv:2107.12666"},{"key":"32_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhu, A., Xue, J., Wan, X., Liu, C., Wang, T., Li, Y.: Look before you leap: Improving text-based person retrieval by learning a consistent cross-modal common manifold. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 1984\u20131992 (2022)","DOI":"10.1145\/3503161.3548166"},{"key":"32_CR38","doi-asserted-by":"crossref","unstructured":"Shu, X., Wen, W., Wu, H., Chen, K., Song, Y., Qiao, R., Ren, B., Wang, X.: See finer, see more: Implicit modality alignment for text-based person retrieval. In: European Conference on Computer Vision, pp. 624\u2013641. Springer (2022)","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"32_CR39","doi-asserted-by":"crossref","unstructured":"Yan, S., Dong, N., Zhang, L., Tang, J.: Clip-driven fine-grained text-image person re-identification. IEEE Trans. Image Process. (2023)","DOI":"10.1109\/TIP.2023.3327924"}],"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\/978-981-97-8620-6_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T20:19:03Z","timestamp":1736885943000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8620-6_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,20]]},"ISBN":["9789819786190","9789819786206"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8620-6_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,20]]},"assertion":[{"value":"20 October 2024","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":"Urumqi","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}