{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T08:47:27Z","timestamp":1770799647363,"version":"3.50.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Beijing Natural Science Foundation","award":["4244082"],"award-info":[{"award-number":["4244082"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62402034"],"award-info":[{"award-number":["62402034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s00530-025-02095-8","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T08:53:27Z","timestamp":1764838407000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Select and assign: anchor-guided proposals for temporal sentence grounding"],"prefix":"10.1007","volume":"32","author":[{"given":"Ziyi","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyue","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongmin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,4]]},"reference":[{"key":"2095_CR1","first-page":"11846","volume":"34","author":"J Lei","year":"2021","unstructured":"Lei, J., Berg, T.L., Bansal, M.: Detecting moments and highlights in videos via natural language queries. Adv. Neural Inf. Process. Syst. 34, 11846\u201311858 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2095_CR2","unstructured":"Woo, S., Park, J., Koo, I., Lee, S., Jeong, M., Kim, C.: Explore and match: end-to-end video grounding with transformer. arXiv preprint arXiv:2201.101681(4) (2022)"},{"key":"2095_CR3","doi-asserted-by":"publisher","first-page":"3263","DOI":"10.1109\/TMM.2023.3309551","volume":"26","author":"X Fang","year":"2023","unstructured":"Fang, X., Liu, D., Zhou, P., Xu, Z., Li, R.: Hierarchical local-global transformer for temporal sentence grounding. IEEE Trans. Multimed. 26, 3263\u20133277 (2023)","journal-title":"IEEE Trans. Multimed."},{"key":"2095_CR4","doi-asserted-by":"crossref","unstructured":"Xu, Y., Sun, Y., Zhai, B., Jia, Y., Du, S.: Mh-detr: Video moment and highlight detection with cross-modal transformer. In: 2024 International joint conference on neural networks (IJCNN), pp. 1\u20138 (2024)","DOI":"10.1109\/IJCNN60899.2024.10650814"},{"issue":"1","key":"2095_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-024-01639-8","volume":"31","author":"C Zhu","year":"2025","unstructured":"Zhu, C., Zhang, Y., Jia, Q., Wang, W., Liu, Y.: Temporal refinement and multi-grained matching for moment retrieval and highlight detection. Multimed. Syst. 31(1), 46 (2025)","journal-title":"Multimed. Syst."},{"issue":"4","key":"2095_CR6","doi-asserted-by":"publisher","first-page":"2181","DOI":"10.1007\/s00530-023-01091-0","volume":"29","author":"Y Zhao","year":"2023","unstructured":"Zhao, Y., Tan, Z., Bao, B.-K., Tu, Z.: Centralized sub-critic based hierarchical-structured reinforcement learning for temporal sentence grounding. Multimed. Syst. 29(4), 2181\u20132191 (2023)","journal-title":"Multimed. Syst."},{"key":"2095_CR7","doi-asserted-by":"crossref","unstructured":"He, D., Zhao, X., Huang, J., Li, F., Liu, X., Wen, S.: Read, watch, and move: Reinforcement learning for temporally grounding natural language descriptions in videos. In: Proceedings of the AAAI conference on artificial intelligence, pp. 8393\u20138400 (2019)","DOI":"10.1609\/aaai.v33i01.33018393"},{"key":"2095_CR8","doi-asserted-by":"crossref","unstructured":"Sun, X., Shi, L., Wang, L., Zhou, S., Xia, K., Wang, Y., Hua, G.: Diversifying query: Region-guided transformer for temporal sentence grounding. In: Proceedings of the AAAI conference on artificial intelligence, pp. 7131\u20137139 (2025)","DOI":"10.1609\/aaai.v39i7.32766"},{"key":"2095_CR9","doi-asserted-by":"crossref","unstructured":"Jang, J., Park, J., Kim, J., Kwon, H., Sohn, K.: Knowing where to focus: Event-aware transformer for video grounding. In: Proceedings of the IEEE international conference on computer vision, pp. 13846\u201313856 (2023)","DOI":"10.1109\/ICCV51070.2023.01273"},{"key":"2095_CR10","doi-asserted-by":"crossref","unstructured":"Zheng, M., Huang, Y., Chen, Q., Peng, Y., Liu, Y.: Weakly supervised temporal sentence grounding with gaussian-based contrastive proposal learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 15555\u201315564 (2022)","DOI":"10.1109\/CVPR52688.2022.01511"},{"key":"2095_CR11","doi-asserted-by":"crossref","unstructured":"Ji, W., Shi, R., Wei, Y., Zhao, S., Zimmermann, R.: Weakly supervised video moment retrieval via location-irrelevant proposal learning. In: Companion proceedings of the ACM web conference 2024, pp. 1595\u20131603 (2024)","DOI":"10.1145\/3589335.3651942"},{"key":"2095_CR12","doi-asserted-by":"publisher","first-page":"3252","DOI":"10.1109\/TIP.2021.3058614","volume":"30","author":"W Yang","year":"2021","unstructured":"Yang, W., Zhang, T., Zhang, Y., Wu, F.: Local correspondence network for weakly supervised temporal sentence grounding. IEEE Trans. Image Process. 30, 3252\u20133262 (2021)","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"2095_CR13","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1007\/s44267-023-00032-9","volume":"1","author":"A Zheng","year":"2023","unstructured":"Zheng, A., Liu, J., Wang, Z., Huang, L., Li, C., Yin, B.: Visible-infrared person re-identification via specific and shared representations learning. Vis. Intell. 1(1), 29 (2023)","journal-title":"Vis. Intell."},{"issue":"1","key":"2095_CR14","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/s44267-023-00029-4","volume":"1","author":"J Chen","year":"2023","unstructured":"Chen, J., Gao, C., Sun, L., Sang, N.: Ccsd: cross-camera self-distillation for unsupervised person re-identification. Vis. Intell. 1(1), 27 (2023)","journal-title":"Vis. Intell."},{"key":"2095_CR15","doi-asserted-by":"crossref","unstructured":"Liu, M., Wang, X., Nie, L., Tian, Q., Chen, B., Chua, T.-S.: Cross-modal moment localization in videos. In: Proceedings of the 26th ACM international conference on multimedia, pp. 843\u2013851 (2018)","DOI":"10.1145\/3240508.3240549"},{"key":"2095_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, S., Peng, H., Fu, J., Luo, J.: Learning 2d temporal adjacent networks for moment localization with natural language. In: Proceedings of the AAAI conference on artificial intelligence, pp. 12870\u201312877 (2020)","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"2095_CR17","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, L., Wu, T., Li, T., Wu, G.: Negative sample matters: a renaissance of metric learning for temporal grounding. In: Proceedings of the AAAI conference on artificial intelligence, pp. 2613\u20132623 (2022)","DOI":"10.1609\/aaai.v36i3.20163"},{"key":"2095_CR18","doi-asserted-by":"crossref","unstructured":"Sun, X., Wang, X., Gao, J., Liu, Q., Zhou, X.: You need to read again: Multi-granularity perception network for moment retrieval in videos. In: Proceedings of the 45th international ACM SIGIR conference on research and development in information retrieval, pp. 1022\u20131032 (2022)","DOI":"10.1145\/3477495.3532083"},{"key":"2095_CR19","doi-asserted-by":"crossref","unstructured":"Chen, L., Lu, C., Tang, S., Xiao, J., Zhang, D., Tan, C., Li, X.: Rethinking the bottom-up framework for query-based video localization. In: Proceedings of the AAAI conference on artificial intelligence, pp. 10551\u201310558 (2020)","DOI":"10.1609\/aaai.v34i07.6627"},{"key":"2095_CR20","doi-asserted-by":"crossref","unstructured":"Yang, S., Wu, X.: Entity-aware and motion-aware transformers for language-driven action localization. In: Proceedings of the thirty-first international joint conference on artificial intelligence, LD Raedt, Ed, pp. 1552\u20131558 (2022)","DOI":"10.24963\/ijcai.2022\/216"},{"key":"2095_CR21","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Mei, T., Zhu, W.: To find where you talk: Temporal sentence localization in video with attention based location regression. In: Proceedings of the AAAI conference on artificial intelligence, pp. 9159\u20139166 (2019)","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"2095_CR22","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European conference on computer vision, pp. 213\u2013229 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2095_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, X., Yang, T., Sun, J.: Anchor detr: Query design for transformer-based detector. In: Proceedings of the AAAI conference on artificial intelligence, pp. 2567\u20132575 (2022)","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"2095_CR24","unstructured":"Liu, S., Li, F., Zhang, H., Yang, X., Qi, X., Su, H., Zhu, J., Zhang, L.: DAB-DETR: Dynamic anchor boxes are better queries for DETR. In: International conference on learning representations, pp. 1\u201311 (2022)"},{"key":"2095_CR25","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L., Shum, H.-Y.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. In: International conference on learning representations, pp. 1\u201312 (2023)"},{"key":"2095_CR26","doi-asserted-by":"crossref","unstructured":"Lin, L., Lin, X., Lin, T., Huang, L., Xiong, R., Wang, Y.: Eda: Evolving and distinct anchors for multimodal motion prediction. In: Proceedings of the AAAI conference on artificial intelligence, pp. 3432\u20133440 (2024)","DOI":"10.1609\/aaai.v38i4.28130"},{"key":"2095_CR27","unstructured":"Chai, Y., Sapp, B., Bansal, M., Anguelov, D.: Multipath: Multiple probabilistic anchor trajectory hypotheses for behavior prediction. In: Conference on robot learning, pp. 86\u201399 (2020)"},{"key":"2095_CR28","first-page":"6531","volume":"35","author":"S Shi","year":"2022","unstructured":"Shi, S., Jiang, L., Dai, D., Schiele, B.: Motion transformer with global intention localization and local movement refinement. Adv. Neural Inf. Process. Syst. 35, 6531\u20136543 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"6","key":"2095_CR29","doi-asserted-by":"publisher","first-page":"3096","DOI":"10.1109\/TPAMI.2021.3050494","volume":"44","author":"X Zhang","year":"2022","unstructured":"Zhang, X., Wan, F., Liu, C., Ji, X., Ye, Q.: Learning to match anchors for visual object detection. IEEE Trans. Pattern Anal. Mach. Intell. 44(6), 3096\u20133109 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2095_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 9759\u20139768 (2020)","DOI":"10.1109\/CVPR42600.2020.00978"},{"issue":"05","key":"2095_CR31","first-page":"2725","volume":"44","author":"Y Yuan","year":"2022","unstructured":"Yuan, Y., Ma, L., Wang, J., Liu, W., Zhu, W.: Semantic conditioned dynamic modulation for temporal sentence grounding in videos. IEEE Trans. Pattern Anal. Mach. Intell. 44(05), 2725\u20132741 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2095_CR32","doi-asserted-by":"crossref","unstructured":"Moon, W., Hyun, S., Park, S., Park, D., Heo, J.-P.: Query-dependent video representation for moment retrieval and highlight detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 23023\u201323033 (2023)","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"2095_CR33","unstructured":"Li, P., Xie, C.-W., Xie, H., Zhao, L., Zhang, L., Zheng, Y., Zhao, D., Zhang, Y.: Momentdiff: Generative video moment retrieval from random to real. In: Advances in neural information processing systems, pp. 65948\u201365966 (2024)"},{"key":"2095_CR34","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., : Learning transferable visual models from natural language supervision. In: International conference on machine learning, pp. 8748\u20138763 (2021)"},{"key":"2095_CR35","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE International conference on computer vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"2095_CR36","doi-asserted-by":"crossref","unstructured":"Sun, H., Zhou, M., Chen, W., Xie, W.: Tr-detr: Task-reciprocal transformer for joint moment retrieval and highlight detection. In: Proceedings of the AAAI conference on artificial intelligence, pp. 4998\u20135007 (2024)","DOI":"10.1609\/aaai.v38i5.28304"},{"key":"2095_CR37","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, S., Wu, Y., Chen, C.-W., Shan, Y., Qie, X.: Umt: Unified multi-modal transformers for joint video moment retrieval and highlight detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 3042\u20133051 (2022)","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"2095_CR38","doi-asserted-by":"crossref","unstructured":"Lin, K.Q., Zhang, P., Chen, J., Pramanick, S., Gao, D., Wang, A.J., Yan, R., Shou, M.Z.: Univtg: Towards unified video-language temporal grounding. In: Proceedings of the IEEE international conference on computer vision, pp. 2794\u20132804 (2023)","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"2095_CR39","doi-asserted-by":"crossref","unstructured":"Yang, J., Wei, P., Li, H., Ren, Z.: Task-driven exploration: Decoupling and inter-task feedback for joint moment retrieval and highlight detection. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp. 18308\u201318318 (2024)","DOI":"10.1109\/CVPR52733.2024.01733"},{"key":"2095_CR40","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Luo, Z., Liu, Y., Ma, Y., Bian, H., Ji, Y., Yang, Y., Li, X.: Bridging the gap: a unified video comprehension framework for moment retrieval and highlight detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 18709\u201318719 (2024)","DOI":"10.1109\/CVPR52733.2024.01770"},{"key":"2095_CR41","unstructured":"Moon, W., Hyun, S., Lee, S.B., Heo, J.-P.: Correlation-guided query-dependency calibration in video representation learning for temporal grounding. CoRR arXiv:2311.08835 (2023)"},{"key":"2095_CR42","unstructured":"Li, P., Xie, C.-W., Xie, H., Zhao, L., Zhang, L., Zheng, Y., Zhao, D., Zhang, Y.: Momentdiff: Generative video moment retrieval from random to real. In: Advances in neural information processing systems, pp. 65948\u201365966 (2023)"},{"key":"2095_CR43","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Yang, Z., Nevatia, R.: Tall: Temporal activity localization via language query. In: Proceedings of the IEEE international conference on computer vision, pp. 5267\u20135275 (2017)","DOI":"10.1109\/ICCV.2017.563"},{"key":"2095_CR44","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1162\/tacl_a_00207","volume":"1","author":"M Regneri","year":"2013","unstructured":"Regneri, M., Rohrbach, M., Wetzel, D., Thater, S., Schiele, B., Pinkal, M.: Grounding action descriptions in videos. Trans. Assoc. Comput. Linguist. 1, 25\u201336 (2013)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"2095_CR45","unstructured":"Wang, Y., Liu, Z., Sun, X., Wang, J., Liu, H.: Length matters: Length-aware transformer for temporal sentence grounding. arXiv preprint arXiv:2508.04299 (2025)"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02095-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-02095-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02095-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T04:18:09Z","timestamp":1770783489000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-02095-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,4]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["2095"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-02095-8","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,4]]},"assertion":[{"value":"29 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"31"}}