{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T19:37:38Z","timestamp":1773517058062,"version":"3.50.1"},"reference-count":72,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"name":"Shenzhen Medical Research Funds in China","award":["B2302037"],"award-info":[{"award-number":["B2302037"]}]},{"name":"Peking University Shenzhen Graduate School, China"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2026,4,30]]},"abstract":"<jats:p>Text-video retrieval plays a pivotal role in cross-modal tasks, aiming to match textual descriptions with corresponding video content accurately. Existing methods often employ fine-grained feature matching to improve retrieval accuracy, but such approaches consume extensive computational resources. Conversely, coarse-grained feature matching between entire sentences and videos offers computational efficiency but may overlook the heterogeneous semantic concepts embedded within the data. To overcome these challenges, we develop the Disentangled Concept Matching (DCM) framework, designed as an imitation of human semantic perception processes. The framework utilizes Disentangled Representation Learning (DRL) to divide coarse-grained features into distinct semantic concepts represented as latent factors, effectively generating finer-grained features while reducing computational demands. To improve the accuracy of retrieval, we first propose the Composed Spatial-temporal Module (CSTM) to optimize the quality of multimodal feature extraction. Utilizing a branch-structured temporal modeling approach, CSTM effectively enhances the DCM model\u2019s comprehension of video content and temporal information, leading to the extraction of refined video features. Second, building on the optimized features, we propose the Adaptive Pooling Module (APM) to measure the confidence level of each latent factor matching during the process of decoupling concepts. APM enhances the fidelity of text and video concepts, thereby further ensuring the accuracy of matching after decoupling. With CSTM and APM, DCM accurately matches latent factors in lower dimensions, achieving significant improvements in computing efficiency and retrieval performance. Our experimental evaluations across standard datasets, namely MSR-VTT, LSMDC, MSVD, ActivityNet, and DiDeMo, demonstrate that the DCM framework achieves state-of-the-art performance, with Recall@1 scores of 48.7%, 25.6%, 48.4%, 45.0%, and 48.6%, respectively. Compared to our previous model, the DCM framework shows improvements of 2.54%, 0.08%, 2.11%, 6.89%, and 6.35%, respectively.<\/jats:p>","DOI":"10.1145\/3778351","type":"journal-article","created":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T14:15:40Z","timestamp":1766153740000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Disentangled Concept Matching for Text-video Retrieval through Perception Imitation"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2890-8806","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China and Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9287-6410","authenticated-orcid":false,"given":"Peng","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China and Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5728-5287","authenticated-orcid":false,"given":"Chunyu","family":"Zou","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6197-7741","authenticated-orcid":false,"given":"Han","family":"Peng","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0046-6105","authenticated-orcid":false,"given":"Ziyao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9765-4523","authenticated-orcid":false,"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China and Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8894-1806","authenticated-orcid":false,"given":"Wen","family":"Gao","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China and Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,7]]},"reference":[{"key":"e_1_3_1_2_2","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et al. 2023. GPT-4 Technical Report. Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:257532815"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2711011"},{"key":"e_1_3_1_5_2","unstructured":"Max Bain Arsha Nagrani G\u00fcl Varol and Andrew Zisserman. 2022. A CLIP-Hitchhiker\u2019s guide to long video retrieval. arXiv:2205.08508. Retrieved from https:\/\/arxiv.org\/abs\/2205.08508"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00513"},{"key":"e_1_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Tim Brooks Aleksander Holynski and Alexei A. Efros. 2023. InstructPix2Pix: Learning to follow image editing instructions. arXiv:2211.09800. Retrieved from https:\/\/arxiv.org\/abs\/2211.09800","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_1_8_2","first-page":"190","volume-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Chen David","year":"2011","unstructured":"David Chen and William B. Dolan. 2011. Collecting highly parallel data for paraphrase evaluation. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL). Association for Computational Linguistics, 190\u2013200."},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"e_1_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Zesen Cheng Kehan Li Peng Jin Xiangyang Ji Li Yuan Chang Liu and Jie Chen. 2023. Parallel vertex diffusion for unified visual grounding. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) 1326\u20131334.","DOI":"10.1609\/aaai.v38i2.27896"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1038\/srep27755"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"e_1_3_1_13_2","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina N. Toutanova. 2018. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL). Association for Computational Linguistics."},{"key":"e_1_3_1_14_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2021. An image is worth 16\u2009\u00d7\u200916 words: Transformers for image recognition at scale. In Proceedings of the International Conference on Learning Representations (ICLR). IEEE."},{"key":"e_1_3_1_15_2","unstructured":"Han Fang Pengfei Xiong Luhui Xu and Yu Chen. 2021. CLIP2Video: Mastering video-text retrieval via image clip. arXiv:2106.11097. Retrieved from https:\/\/arxiv.org\/abs\/2106.11097"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"e_1_3_1_17_2","unstructured":"Zijian Gao Jingyu Liu Weiqi Sun Sheng Chen Dedan Chang and Lili Zhao. 2021. CLIP2TV: Align match and distill for video-text retrieval. arXiv:2111.05610. Retrieved from https:\/\/arxiv.org\/abs\/2111.05610"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01025"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3483381"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627103"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2017.06.011"},{"key":"e_1_3_1_23_2","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Jiamian Wang","year":"2024","unstructured":"Wang Jiamian, Sun Guohao, Wang Pichao, Liu Dongfang, Dianat Sohail, Rabbani Majid, Rao Raghuveer, and Tao Zhiqiang. 2024. Text is MASS: Modeling as stochastic embedding for text-video retrieval. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE."},{"key":"e_1_3_1_24_2","first-page":"30291","volume-title":"Proceedings of the Neural Information Processing Systems (NeurIPS)","author":"Jin Peng","year":"2022","unstructured":"Peng Jin, Jinfa Huang, Fenglin Liu, Xian Wu, Shen Ge, Guoli Song, David Clifton, and Jie Chen. 2022. Expectation-maximization contrastive learning for compact video-and-language representations. In Proceedings of the Neural Information Processing Systems (NeurIPS). Curran Associates, Inc., 30291\u201330306."},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/104"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00234"},{"key":"e_1_3_1_27_2","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. In International Conference on Learning Representations (ICLR) Vol. 5 No. 6."},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"issue":"11","key":"e_1_3_1_29_2","first-page":"1320","article-title":"Lifting the curse of dimensionality","volume":"52","author":"Kuo Frances Y.","year":"2005","unstructured":"Frances Y. Kuo and Ian H. Sloan. 2005. Lifting the curse of dimensionality. Notices of the AMS 52, 11 (2005), 1320\u20131328.","journal-title":"Notices of the AMS"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06668-3"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aab3050"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"e_1_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Hao Li Jinfa Huang Peng Jin Guoli Song Qi Wu and Jie Chen. 2022. Toward 3D spatial reasoning for human-like text-based visual question answering. arXiv:2209.10326. Retrieved from https:\/\/arxiv.org\/abs\/2209.10326","DOI":"10.1109\/TIP.2023.3276570"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859766"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3538533"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00379"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00634"},{"key":"e_1_3_1_38_2","first-page":"279","volume-title":"Proceedings of the British Machine Vision Conference (BMVC)","author":"Liu Yang","year":"2019","unstructured":"Yang Liu, Samuel Albanie, Arsha Nagrani, and Andrew Zisserman. 2019. Use what you have: Video retrieval using representations from collaborative experts. In Proceedings of the British Machine Vision Conference (BMVC). BMVA Press, 279."},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01471"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"e_1_3_1_41_2","unstructured":"Francesco Locatello Michael Tschannen Stefan Bauer Gunnar R\u00e4tsch Bernhard Sch\u00f6lkopf and Olivier Bachem. 2019. Disentangling factors of variation using few labels. arXiv:1905.01258. Retrieved from https:\/\/arxiv.org\/abs\/1905.01258"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"e_1_3_1_43_2","first-page":"4212","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Ma Jianxin","year":"2019","unstructured":"Jianxin Ma, Peng Cui, Kun Kuang, Xin Wang, and Wenwu Zhu. 2019. Disentangled graph convolutional networks. In Proceedings of the International Conference on Machine Learning (ICML). ACM, 4212\u20134221."},{"key":"e_1_3_1_44_2","doi-asserted-by":"crossref","unstructured":"Yiwei Ma Guohai Xu Xiaoshuai Sun Ming Yan Ji Zhang and Rongrong Ji. 2022. X-CLIP: End-to-end multi-grained contrastive learning for video-text retrieval. In Proceedings of the 30th ACM International Conference on Multimedia 638\u2013647.","DOI":"10.1145\/3503161.3547910"},{"key":"e_1_3_1_45_2","unstructured":"Aaron van den Oord Yazhe Li and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv:1807.03748. Retrieved from https:\/\/arxiv.org\/abs\/1807.03748"},{"key":"e_1_3_1_46_2","first-page":"8748","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","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, et al. 2021. Learning transferable visual models from natural language supervision. In Proceedings of the International Conference on Machine Learning (ICML). PMLR, 8748\u20138763."},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.3629243"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3546828"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3359045"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412679"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"e_1_3_1_53_2","unstructured":"Jianqiao Sun Yudi Su Hao Zhang Ziheng Cheng Zequn Zeng Zhengjue Wang Bo Chen and Xin Yuan. 2024. SnapCap: Efficient snapshot compressive video captioning. arXiv:2401.04903. Retrieved from https:\/\/arxiv.org\/abs\/2401.04903"},{"key":"e_1_3_1_54_2","unstructured":"Yang Suorong Xiao Weikang Zhang Mengcheng Guo Suhan Zhao Jian and Shen Furao. 2022. Image data augmentation for deep learning: A survey. arXiv:2204.08610. Retrieved from https:\/\/arxiv.org\/abs\/2204.08610"},{"key":"e_1_3_1_55_2","article-title":"Self-supervised learning disentangled group representation as feature","author":"Tan Wang","year":"2021","unstructured":"Wang Tan, Yue Zhongqi, Huang Jianqiang, Sun Qianru, and Zhang Hanwang. 2021. Self-supervised learning disentangled group representation as feature. In Proceedings of 35th International Conference on Neural Information Processing Systems (NIPS \u201921).","journal-title":"Proceedings of 35th International Conference on Neural Information Processing Systems (NIPS \u201921)"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"e_1_3_1_57_2","unstructured":"Qiang Wang Yanhao Zhang Yun Zheng Pan Pan and Xian-Sheng Hua. 2022. Disentangled representation learning for text-video retrieval. arXiv:2203.07111. Retrieved from https:\/\/arxiv.org\/abs\/2203.07111"},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"e_1_3_1_59_2","unstructured":"Yimu Wang Shuai Yuan Xiangru Jian Wei Pang Mushi Wang and Ning Yu. 2024. DREAM: Improving video-text retrieval through augmentation using large foundation models. arXiv:2404.05083. Retrieved from https:\/\/arxiv.org\/abs\/2404.05083"},{"key":"e_1_3_1_60_2","doi-asserted-by":"crossref","unstructured":"Michael Wray Gabriela Csurka Diane Larlus and Dima Damen. 2019. Fine-grained action retrieval through multiple parts-of-speech embeddings. In Proceedings of the IEEE International Conference on Computer Vision (ICCV). IEEE 450\u2013459. Sourced from Microsoft Academic.","DOI":"10.1109\/ICCV.2019.00054"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28475"},{"key":"e_1_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_1_63_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Xue Hongwei","year":"2022","unstructured":"Hongwei Xue, Yuchong Sun, Bei Liu, Jianlong Fu, Rui Song, Houqiang Li, and Jiebo Luo. 2022. CLIP-ViP: Adapting pre-trained image-text model to video-language alignment. In Proceedings of the International Conference on Learning Representations (ICLR). Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:252222370"},{"key":"e_1_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26629"},{"key":"e_1_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663571"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539248"},{"key":"e_1_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01610"},{"key":"e_1_3_1_69_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Zhang Shaofeng","year":"2021","unstructured":"Shaofeng Zhang, Feng Zhu, Junchi Yan, Rui Zhao, and Xiaokang Yang. 2021. Zero-CL: Instance and feature decorrelation for negative-free symmetric contrastive learning. In Proceedings of the International Conference on Learning Representations (ICLR). OpenReview.net."},{"key":"e_1_3_1_70_2","unstructured":"Shaofeng Zhang Feng Zhu Rui Zhao and Junchi Yan. 2023. Patch-level contrasting without patch correspondence for accurate and dense contrastive representation learning. arXiv:2306.13337. Retrieved from https:\/\/arxiv.org\/abs\/2306.13337"},{"key":"e_1_3_1_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"e_1_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00979"},{"key":"e_1_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3778351","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T13:24:26Z","timestamp":1773494666000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3778351"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,7]]},"references-count":72,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4,30]]}},"alternative-id":["10.1145\/3778351"],"URL":"https:\/\/doi.org\/10.1145\/3778351","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,7]]},"assertion":[{"value":"2024-09-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-21","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}