{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T14:58:29Z","timestamp":1781621909899,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222203, 61976049, 62072080, U20B2063"],"award-info":[{"award-number":["62222203, 61976049, 62072080, U20B2063"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612244","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"6292-6300","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":43,"title":["DCEL: Deep Cross-modal Evidential Learning for Text-Based Person Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6340-012X","authenticated-orcid":false,"given":"Shenshen","family":"Li","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5685-3123","authenticated-orcid":false,"given":"Xing","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5070-4511","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7303-3231","authenticated-orcid":false,"given":"Fumin","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0991-3597","authenticated-orcid":false,"given":"Yijun","family":"Mo","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3402-1742","authenticated-orcid":false,"given":"Yujie","family":"Li","sequence":"additional","affiliation":[{"name":"Kyushu Institute of Technology, Kitakyushu, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-2088","authenticated-orcid":false,"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China & Peng Cheng Laboratory, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093640"},{"key":"e_1_3_2_1_2_1","unstructured":"Alexander Amini Wilko Schwarting Ava Soleimany and Daniela Rus. 2020. Deep Evidential Regression. In NeurIPS."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Wentao Bao Qi Yu and Yu Kong. 2021. Evidential Deep Learning for Open Set Action Recognition. In ICCV. 13329--13338.","DOI":"10.1109\/ICCV48922.2021.01310"},{"key":"e_1_3_2_1_4_1","first-page":"192","article-title":"Dual-Evidential Learning for Weakly-supervised Temporal Action Localization","volume":"13664","author":"Chen Mengyuan","year":"2022","unstructured":"Mengyuan Chen, Junyu Gao, Shicai Yang, and Changsheng Xu. 2022. Dual-Evidential Learning for Weakly-supervised Temporal Action Localization. In ECCV, Vol. 13664. 192--208.","journal-title":"ECCV"},{"key":"e_1_3_2_1_5_1","volume-title":"OH-Former: Omni-Relational High-Order Transformer for Person Re-Identification. CoRR","author":"Chen Xianing","year":"2021","unstructured":"Xianing Chen, Jialang Xu, Jiale Xu, and Shenghua Gao. 2021. OH-Former: Omni-Relational High-Order Transformer for Person Re-Identification. CoRR, Vol. abs\/2109.11159 (2021)."},{"key":"e_1_3_2_1_6_1","volume-title":"Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification. CoRR","author":"Ding Zefeng","year":"2021","unstructured":"Zefeng Ding, Changxing Ding, Zhiyin Shao, and Dacheng Tao. 2021. Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification. CoRR, Vol. abs\/2107.12666 (2021)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Ammarah Farooq Muhammad Awais Josef Kittler and Syed Safwan Khalid. 2022. AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification. In AAAI. 4477--4485.","DOI":"10.1609\/aaai.v36i4.20370"},{"key":"e_1_3_2_1_8_1","unstructured":"Yarin Gal. 2016. Uncertainty in Deep Learning. In PhD thesis University of Cambridge."},{"key":"e_1_3_2_1_9_1","volume-title":"International conference on machine learning. 1321--1330","author":"Guo Chuan","year":"2017","unstructured":"Chuan Guo, Geoff Pleiss, Yu Sun, and Kilian Q Weinberger. 2017. On calibration of modern neural networks. In International conference on machine learning. 1321--1330."},{"key":"e_1_3_2_1_10_1","volume-title":"BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification. In IEEE Conference on Computer Vision and Pattern Recognition. 2014--2023","author":"Hou Ruibing","year":"2021","unstructured":"Ruibing Hou, Hong Chang, Bingpeng Ma, Rui Huang, and Shiguang Shan. 2021. BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification. In IEEE Conference on Computer Vision and Pattern Recognition. 2014--2023."},{"key":"e_1_3_2_1_11_1","volume-title":"Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval. CoRR","author":"Jiang Ding","year":"2023","unstructured":"Ding Jiang and Mang Ye. 2023. Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval. CoRR, Vol. abs\/2303.12501 (2023)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Ya Jing Chenyang Si Junbo Wang Wei Wang Liang Wang and Tieniu Tan. 2020. Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search. In AAAI. 11189--11196.","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"e_1_3_2_1_13_1","volume-title":"Subjective Logic - A Formalism for Reasoning Under Uncertainty","author":"J\u00f8sang Audun","unstructured":"Audun J\u00f8sang. 2016. Subjective Logic - A Formalism for Reasoning Under Uncertainty. Springer."},{"key":"e_1_3_2_1_14_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR."},{"key":"e_1_3_2_1_15_1","volume-title":"Person Search with Natural Language Description. In IEEE Conference on Computer Vision and Pattern Recognition. 5187--5196","author":"Li Shuang","year":"2017","unstructured":"Shuang Li, Tong Xiao, Hongsheng Li, Bolei Zhou, Dayu Yue, and Xiaogang Wang. 2017. Person Search with Natural Language Description. In IEEE Conference on Computer Vision and Pattern Recognition. 5187--5196."},{"key":"e_1_3_2_1_16_1","volume-title":"DC-Former: Diverse and Compact Transformer for Person Re-Identification. CoRR","author":"Li Wen","year":"2023","unstructured":"Wen Li, Cheng Zou, Meng Wang, Furong Xu, Jianan Zhao, Ruobing Zheng, Yuan Cheng, and Wei Chu. 2023. DC-Former: Diverse and Compact Transformer for Person Re-Identification. CoRR, Vol. abs\/2302.14335 (2023)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413895"},{"key":"e_1_3_2_1_20_1","volume-title":"Deep Evidential Learning with Noisy Correspondence for Cross-modal Retrieval. In The ACM International Conference on Multimedia. ACM, 4948--4956","author":"Qin Yang","year":"2022","unstructured":"Yang Qin, Dezhong Peng, Xi Peng, Xu Wang, and Peng Hu. 2022. Deep Evidential Learning with Noisy Correspondence for Cross-modal Retrieval. In The ACM International Conference on Multimedia. ACM, 4948--4956."},{"key":"e_1_3_2_1_21_1","first-page":"8748","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume":"139","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In ICML, Vol. 139. 8748--8763.","journal-title":"ICML"},{"key":"e_1_3_2_1_22_1","volume-title":"Adversarial Representation Learning for Text-to-Image Matching. In IEEE\/CVF International Conference on Computer Vision. 5813--5823","author":"Sarafianos Nikolaos","unstructured":"Nikolaos Sarafianos, Xiang Xu, and Ioannis A. Kakadiaris. 2019. Adversarial Representation Learning for Text-to-Image Matching. In IEEE\/CVF International Conference on Computer Vision. 5813--5823."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Murat Sensoy Lance M. Kaplan Federico Cerutti and Maryam Saleki. 2020. Uncertainty-Aware Deep Classifiers Using Generative Models. In AAAI. 5620--5627.","DOI":"10.1609\/aaai.v34i04.6015"},{"key":"e_1_3_2_1_24_1","unstructured":"Murat Sensoy Lance M. Kaplan and Melih Kandemir. 2018. Evidential Deep Learning to Quantify Classification Uncertainty. In NeurIPS. 3183--3193."},{"key":"e_1_3_2_1_25_1","volume-title":"Learning Granularity-Unified Representations for Text-to-Image Person Re-identification. In The ACM International Conference on Multimedia. 5566--5574","author":"Shao Zhiyin","year":"2022","unstructured":"Zhiyin Shao, Xinyu Zhang, Meng Fang, Zhifeng Lin, Jian Wang, and Changxing Ding. 2022. Learning Granularity-Unified Representations for Text-to-Image Person Re-identification. In The ACM International Conference on Multimedia. 5566--5574."},{"key":"e_1_3_2_1_26_1","volume-title":"More: Implicit Modality Alignment for Text-Based Person Retrieval. In ECCV Workshops","volume":"13805","author":"Shu Xiujun","year":"2022","unstructured":"Xiujun Shu, Wei Wen, Haoqian Wu, Keyu Chen, Yiran Song, Ruizhi Qiao, Bo Ren, and Xiao Wang. 2022. See Finer, See More: Implicit Modality Alignment for Text-Based Person Retrieval. In ECCV Workshops, Vol. 13805. 624--641."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Nina Shvetsova Brian Chen Andrew Rouditchenko Samuel Thomas Brian Kingsbury Rog\u00e9rio Feris David Harwath James R. Glass and Hilde Kuehne. 2022. Everything at Once - Multi-modal Fusion Transformer for Video Retrieval. In CVPR. 19988--19997.","DOI":"10.1109\/CVPR52688.2022.01939"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Wei Suo Mengyang Sun Kai Niu Yiqi Gao Peng Wang Yanning Zhang and Qi Wu. 2022. A Simple and Robust Correlation Filtering Method for Text-Based Person Search. In ECCV. 726--742.","DOI":"10.1007\/978-3-031-19833-5_42"},{"key":"e_1_3_2_1_29_1","volume-title":"Exploiting the Textual Potential from Vision-Language Pre-training for Text-based Person Search. CoRR","author":"Wang Guanshuo","year":"2023","unstructured":"Guanshuo Wang, Fufu Yu, Junjie Li, Qiong Jia, and Shouhong Ding. 2023. Exploiting the Textual Potential from Vision-Language Pre-training for Text-based Person Search. CoRR, Vol. abs\/2303.04497 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"UK","volume":"12357","author":"Wang Zhe","year":"2020","unstructured":"Zhe Wang, Zhiyuan Fang, Jun Wang, and Yezhou Yang. 2020. ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language. In Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XII, Vol. 12357. 402--420."},{"key":"e_1_3_2_1_31_1","volume-title":"CAIBC: Capturing All-round Information Beyond Color for Text-based Person Retrieval. In ACM International Conference on Multimedia. 5314--5322","author":"Wang Zijie","year":"2022","unstructured":"Zijie Wang, Aichun Zhu, Jingyi Xue, Xili Wan, Chao Liu, Tian Wang, and Yifeng Li. 2022a. CAIBC: Capturing All-round Information Beyond Color for Text-based Person Retrieval. In ACM International Conference on Multimedia. 5314--5322."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548166"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00165"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3251104"},{"key":"e_1_3_2_1_35_1","volume-title":"Yager and Liping Liu","author":"Ronald","year":"2008","unstructured":"Ronald R. Yager and Liping Liu. 2008. Classic Works of the Dempster-Shafer Theory of Belief Functions. Vol. 219. Springer."},{"key":"e_1_3_2_1_36_1","volume-title":"CLIP-Driven Fine-grained Text-Image Person Re-identification. CoRR","author":"Yan Shuanglin","year":"2022","unstructured":"Shuanglin Yan, Neng Dong, Liyan Zhang, and Jinhui Tang. 2022a. CLIP-Driven Fine-grained Text-Image Person Re-identification. CoRR, Vol. abs\/2210.10276 (2022)."},{"key":"e_1_3_2_1_37_1","volume-title":"Image-Specific Information Suppression and Implicit Local Alignment for Text-based Person Search. CoRR","author":"Yan Shuanglin","year":"2022","unstructured":"Shuanglin Yan, Hao Tang, Liyan Zhang, and Jinhui Tang. 2022b. Image-Specific Information Suppression and Implicit Local Alignment for Text-based Person Search. CoRR, Vol. abs\/2208.14365 (2022)."},{"key":"e_1_3_2_1_38_1","volume-title":"Li","author":"Yi Dong","year":"2014","unstructured":"Dong Yi, Zhen Lei, Shengcai Liao, and Stan Z. Li. 2014. Deep Metric Learning for Person Re-identification. In ICPR. 34--39."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Shizhen Zhao Changxin Gao Yuanjie Shao Wei-Shi Zheng and Nong Sang. 2021. Weakly Supervised Text-based Person Re-Identification. In ICCV. 11375--11384.","DOI":"10.1109\/ICCV48922.2021.01120"},{"key":"e_1_3_2_1_40_1","volume-title":"Hierarchical Gumbel Attention Network for Text-based Person Search. In ACM International Conference on Multimedia. 3441--3449","author":"Zheng Kecheng","year":"2020","unstructured":"Kecheng Zheng, Wu Liu, Jiawei Liu, Zheng-Jun Zha, and Tao Mei. 2020a. Hierarchical Gumbel Attention Network for Text-based Person Search. In ACM International Conference on Multimedia. 3441--3449."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612244","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612244","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:58:02Z","timestamp":1755820682000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612244"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":42,"alternative-id":["10.1145\/3581783.3612244","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612244","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}