{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,27]],"date-time":"2025-12-27T18:35:21Z","timestamp":1766860521315,"version":"3.48.0"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"42","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Austrian-Chinese Cooperative R&D Project","award":["171111KYSB20200002"],"award-info":[{"award-number":["171111KYSB20200002"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-025-21135-z","type":"journal-article","created":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T11:30:33Z","timestamp":1759318233000},"page":"50497-50524","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-hierarchical semantic graph learning for video moment retrieval"],"prefix":"10.1007","volume":"84","author":[{"given":"Xing","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"De","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2250-5224","authenticated-orcid":false,"given":"Nan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaochun","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benjamin","family":"Rainer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Priller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,1]]},"reference":[{"issue":"8","key":"21135_CR1","doi-asserted-by":"publisher","first-page":"10443","DOI":"10.1109\/TPAMI.2023.3258628","volume":"45","author":"H Zhang","year":"2023","unstructured":"Zhang H, Sun A, Jing W, Zhou JT (2023) Temporal sentence grounding in videos: a survey and future directions. IEEE Trans Pattern Anal Mach Intell 45(8):10443\u201310465","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"21135_CR2","doi-asserted-by":"crossref","unstructured":"Lan X, Yuan Y, Wang X, Wang Z, Zhu W (2023) A survey on temporal sentence grounding in videos. ACM Trans Multim Comput Commun Appl 19(2):51:1\u201351:33","DOI":"10.1145\/3532626"},{"key":"21135_CR3","doi-asserted-by":"publisher","first-page":"64560","DOI":"10.1109\/ACCESS.2022.3183106","volume":"10","author":"S Yoon","year":"2022","unstructured":"Yoon S, Kim D, Kim J, Yoo CD (2022) Cascaded MPN: cascaded moment proposal network for video corpus moment retrieval. IEEE Access 10:64560\u201364568","journal-title":"IEEE Access"},{"issue":"7","key":"21135_CR4","doi-asserted-by":"publisher","first-page":"4214","DOI":"10.1007\/s10489-020-02057-9","volume":"51","author":"D Varshney","year":"2021","unstructured":"Varshney D, Vishwakarma DK (2021) A unified approach for detection of clickbait videos on youtube using cognitive evidences. Appl Intell 51(7):4214\u20134235","journal-title":"Appl Intell"},{"key":"21135_CR5","doi-asserted-by":"crossref","unstructured":"Gao J, Sun C, Yang Z, Nevatia R (2017) Tall: temporal activity localization via language query. In: Proceedings of the IEEE international conference on computer vision, pp 5267\u20135275","DOI":"10.1109\/ICCV.2017.563"},{"key":"21135_CR6","doi-asserted-by":"crossref","unstructured":"Krishna R, Hata K, Ren F, Fei-Fei L, Niebles JC (2017) Dense-captioning events in videos. In: Proceedings of the IEEE international conference on computer vision, pp 706\u2013715","DOI":"10.1109\/ICCV.2017.83"},{"key":"21135_CR7","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 (2013) Grounding action descriptions in videos. Trans Assoc Comput Linguistics 1:25\u201336","journal-title":"Trans Assoc Comput Linguistics"},{"key":"21135_CR8","doi-asserted-by":"crossref","unstructured":"Hendricks LA, Wang O, Shechtman E, Sivic J, Darrell T, Russell BC (2017) Localizing moments in video with natural language. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp 5804\u20135813","DOI":"10.1109\/ICCV.2017.618"},{"key":"21135_CR9","doi-asserted-by":"crossref","unstructured":"Liu M, Wang X, Nie L, Tian Q, Chen B, Chua T-S (2018) Cross-modal moment localization in videos. In: Proceedings of the 26th ACM international conference on multimedia, pp 843\u2013851","DOI":"10.1145\/3240508.3240549"},{"key":"21135_CR10","doi-asserted-by":"crossref","unstructured":"Chen J, Chen X, Ma L, Jie Z, Chua T-S (2018) Temporally grounding natural sentence in video. In: Proceedings of the 2018 conference on empirical methods in natural language processing, pp 162\u2013171","DOI":"10.18653\/v1\/D18-1015"},{"key":"21135_CR11","doi-asserted-by":"crossref","unstructured":"Zhang Z, Lin Z, Zhao Z, Xiao Z (2019) Cross-modal interaction networks for query-based moment retrieval in videos. In: Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval, pp 655\u2013664","DOI":"10.1145\/3331184.3331235"},{"key":"21135_CR12","doi-asserted-by":"crossref","unstructured":"Mun J, Cho M, Han B (2020) Local-global video-text interactions for temporal grounding. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10810\u201310819","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"21135_CR13","doi-asserted-by":"crossref","unstructured":"Liu D, Qu X, Dong J, Zhou P, Cheng Y, Wei W, Xu Z, Xie Y (2021) Context-aware biaffine localizing network for temporal sentence grounding. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11235\u201311244","DOI":"10.1109\/CVPR46437.2021.01108"},{"key":"21135_CR14","doi-asserted-by":"crossref","unstructured":"Zhao Y, Zhao Z, Zhang Z, Lin Z (2021) Cascaded prediction network via segment tree for temporal video grounding. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4197\u20134206","DOI":"10.1109\/CVPR46437.2021.00418"},{"key":"21135_CR15","doi-asserted-by":"crossref","unstructured":"Nan G, Qiao R, Xiao Y, Liu J, Leng S, Zhang H, Lu W (2021) Interventional video grounding with dual contrastive learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2765\u20132775","DOI":"10.1109\/CVPR46437.2021.00279"},{"key":"21135_CR16","doi-asserted-by":"crossref","unstructured":"Ding X, Wang N, Zhang S, Cheng D, Li X, Huang Z, Tang M, Gao X (2021) Support-set based cross-supervision for video grounding. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 11573\u201311582","DOI":"10.1109\/ICCV48922.2021.01137"},{"issue":"3","key":"21135_CR17","doi-asserted-by":"publisher","first-page":"1646","DOI":"10.1109\/TCSVT.2021.3075470","volume":"32","author":"J Gao","year":"2022","unstructured":"Gao J, Xu C (2022) Learning video moment retrieval without a single annotated video. IEEE Trans Circuits Syst Video Technol 32(3):1646\u20131657","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"21135_CR18","doi-asserted-by":"crossref","unstructured":"Zhang S, Peng H, Fu J, Luo J (2020) Learning 2d temporal adjacent networks for moment localization with natural language. In: The thirty-fourth AAAI conference on artificial intelligence, AAAI 2020, the thirty-second innovative applications of artificial intelligence conference, IAAI 2020, the tenth AAAI symposium on educational advances in artificial intelligence, EAAI 2020, New York, NY, USA, February 7-12, 2020. AAAI Press, pp 12870\u201312877","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"21135_CR19","doi-asserted-by":"crossref","unstructured":"Zeng R, Xu H, Huang W, Chen P, Tan M, Gan C (2020) Dense regression network for video grounding. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10287\u201310296","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"21135_CR20","doi-asserted-by":"crossref","unstructured":"Wang J, Ma L, Jiang W (2020) Temporally grounding language queries in videos by contextual boundary-aware prediction. In: The thirty-fourth AAAI conference on artificial intelligence, AAAI 2020, the thirty-second innovative applications of artificial intelligence conference, IAAI 2020, the tenth AAAI symposium on educational advances in artificial intelligence, EAAI 2020, New York, NY, USA, February 7-12, 2020. AAAI Press, pp 12168\u201312175","DOI":"10.1609\/aaai.v34i07.6897"},{"issue":"12","key":"21135_CR21","doi-asserted-by":"publisher","first-page":"9073","DOI":"10.1109\/TPAMI.2021.3120745","volume":"44","author":"S Zhang","year":"2022","unstructured":"Zhang S, Peng H, Fu J, Lu Y, Luo J (2022) Multi-scale 2d temporal adjacency networks for moment localization with natural language. IEEE Trans Pattern Anal Mach Intell 44(12):9073\u20139087","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"21135_CR22","doi-asserted-by":"crossref","unstructured":"Gao J, Xu C (2021) Fast video moment retrieval. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 1523\u20131532","DOI":"10.1109\/ICCV48922.2021.00155"},{"key":"21135_CR23","doi-asserted-by":"crossref","unstructured":"Wang Z, Wang L, Wu T, Li T, Wu G (2022) Negative sample matters: a renaissance of metric learning for temporal grounding. In: Thirty-Sixth AAAI conference on artificial intelligence, AAAI 2022, thirty-fourth conference on innovative applications of artificial intelligence, IAAI 2022, the twelveth symposium on educational advances in artificial intelligence, EAAI 2022 Virtual Event, February 22 - March 1, 2022. AAAI Press, pp 2613\u20132623","DOI":"10.1609\/aaai.v36i3.20163"},{"issue":"10","key":"21135_CR24","doi-asserted-by":"publisher","first-page":"6900","DOI":"10.1109\/TCSVT.2022.3174136","volume":"32","author":"J Gao","year":"2022","unstructured":"Gao J, Sun X, Ghanem B, Zhou X, Ge S (2022) Efficient video grounding with which-where reading comprehension. IEEE Trans Circuits Syst Video Technol 32(10):6900\u20136913","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"10","key":"21135_CR25","doi-asserted-by":"publisher","first-page":"7190","DOI":"10.1109\/TCSVT.2022.3179314","volume":"32","author":"H Zhou","year":"2022","unstructured":"Zhou H, Zhang C, Luo Y, Hu C, Zhang W (2022) Thinking inside uncertainty: interest moment perception for diverse temporal grounding. IEEE Trans Circuits Syst Video Technol 32(10):7190\u20137203","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"21135_CR26","doi-asserted-by":"crossref","unstructured":"Han D, Cheng X, Guo N, Ye X, Rainer B, Priller P (2023) Momentum cross-modal contrastive learning for video moment retrieval. IEEE Trans Circuits Syst Video Technol, 1\u20131","DOI":"10.1109\/TCSVT.2023.3344097"},{"key":"21135_CR27","first-page":"4116","volume-title":"Dual path interaction network for video moment localization","author":"H Wang","year":"2020","unstructured":"Wang H, Zha Z-J, Chen X, Xiong Z, Luo J (2020) Dual path interaction network for video moment localization. Association for Computing Machinery, New York, NY, USA, pp 4116\u20134124"},{"key":"21135_CR28","doi-asserted-by":"crossref","unstructured":"Xiao S, Chen L, Zhang S, Ji W, Shao J, Ye L, Xiao J (2021) Boundary proposal network for two-stage natural language video localization. In: Thirty-fifth AAAI conference on artificial intelligence, AAAI 2021, thirty-third conference on innovative applications of artificial intelligence, IAAI 2021, the eleventh symposium on educational advances in artificial intelligence, EAAI 2021, Virtual Event, February 2-9, 2021. AAAI Press, pp 2986\u20132994","DOI":"10.1609\/aaai.v35i4.16406"},{"key":"21135_CR29","doi-asserted-by":"crossref","unstructured":"Zhang H, Sun A, Jing W, Nan G, Zhen L, Zhou JT, Goh RSM (2021) Video corpus moment retrieval with contrastive learning. In: Diaz F, Shah C, Suel T, Castells P, Jones R, Sakai v (eds) SIGIR \u201921: the 44th international ACM SIGIR conference on research and development in information retrieval, virtual vent, Canada, July 11-15, 2021. ACM, pp 685\u2013695","DOI":"10.1145\/3404835.3462874"},{"key":"21135_CR30","doi-asserted-by":"crossref","unstructured":"Xiao S, Chen L, Shao J, Zhuang Y, Xiao J (2021) Natural language video localization with learnable moment proposals. In: Moens M-F, Huang X, Specia L, Yih SW-t (eds) Proceedings of the 2021 conference on empirical methods in natural language processing, EMNLP 2021, virtual event \/ Punta Cana, Dominican Republic, 7-11 November, 2021. Association for Computational Linguistics, pp 4008\u20134017","DOI":"10.18653\/v1\/2021.emnlp-main.327"},{"key":"21135_CR31","doi-asserted-by":"crossref","unstructured":"Liu D, Qu X, Dong J, Zhou P (2021) Adaptive proposal generation network for temporal sentence localization in videos. In: Moens M-F, Huang X, Specia L, Yih SW-t (eds) Proceedings of the 2021 conference on empirical methods in natural language processing, EMNLP 2021, virtual event \/ Punta Cana, Dominican Republic, 7-11 November, 2021. Association for Computational Linguistics, pp 9292\u20139301","DOI":"10.18653\/v1\/2021.emnlp-main.732"},{"issue":"9","key":"21135_CR32","doi-asserted-by":"publisher","first-page":"5281","DOI":"10.1109\/TCSVT.2023.3250518","volume":"33","author":"X Sun","year":"2023","unstructured":"Sun X, Gao J, Zhu Y, Wang X, Zhou X (2023) Video moment retrieval via comprehensive relation-aware network. IEEE Trans Circuits Syst Video Technol 33(9):5281\u20135295","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"21135_CR33","doi-asserted-by":"crossref","unstructured":"Chen Y, Xia R, Yang K, Zou K (2023) Dgca: high resolution image inpainting via dr-gan and contextual attention. Multimed Tools Appl, 1\u201321","DOI":"10.1007\/s11042-023-15313-0"},{"key":"21135_CR34","doi-asserted-by":"crossref","unstructured":"Chen Y, Xia R, Yang K, Zou K (2023) Mffn: image super-resolution via multi-level features fusion network. Visual Comput, 1\u201316","DOI":"10.1007\/s00371-023-02795-0"},{"issue":"8","key":"21135_CR35","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"21135_CR36","doi-asserted-by":"crossref","unstructured":"Tran D, Bourdev L, Fergus R, Torresani L, Paluri M (2015) Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp 4489\u20134497","DOI":"10.1109\/ICCV.2015.510"},{"key":"21135_CR37","unstructured":"Liu H, Liu T, Chen Y, Zhang Z, Li Y-F (2022) Ehpe: skeleton cues-based gaussian coordinate encoding for efficient human pose estimation. IEEE Trans Multimed, 1\u201312"},{"key":"21135_CR38","doi-asserted-by":"crossref","unstructured":"Lin T, Liu X, Li X, Ding E, Wen S (2019) Bmn: boundary-matching network for temporal action proposal generation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3889\u20133898","DOI":"10.1109\/ICCV.2019.00399"},{"key":"21135_CR39","doi-asserted-by":"crossref","unstructured":"Ur Rehman S, Tu S, Huang Y, Yang Z (2016) Face recognition: a novel un-supervised convolutional neural network method. In: 2016 IEEE International Conference of Online Analysis and Computing Science (ICOACS). IEEE, pp 139\u2013144","DOI":"10.1109\/ICOACS.2016.7563066"},{"issue":"8","key":"21135_CR40","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1109\/TPAMI.2019.2913372","volume":"42","author":"J Hu","year":"2020","unstructured":"Hu J, Shen L, Albanie S, Sun G, Wu E (2020) Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell 42(8):2011\u20132023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"21135_CR41","unstructured":"Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: Bengio Y, LeCun Y (eds) 3rd international conference on learning representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings"},{"key":"21135_CR42","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Bengio Y, LeCun Y (eds) 3rd international conference on learning representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings"},{"key":"21135_CR43","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6299\u20136308","DOI":"10.1109\/CVPR.2017.502"},{"key":"21135_CR44","doi-asserted-by":"crossref","unstructured":"Hendricks LA, Wang O, Shechtman E, Sivic J, Darrell T, Russell B (2017) Localizing moments in video with natural language. In: Proceedings of the IEEE international conference on computer vision, pp 5803\u20135812","DOI":"10.1109\/ICCV.2017.618"},{"key":"21135_CR45","doi-asserted-by":"crossref","unstructured":"Lu C, Chen L, Tan C, Li X, Xiao J (2019) Debug: a dense bottom-up grounding approach for natural language video localization. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp 5144\u20135153","DOI":"10.18653\/v1\/D19-1518"},{"key":"21135_CR46","doi-asserted-by":"crossref","unstructured":"Zhang D, Dai X, Wang X, Wang Y-F, Davis LS (2019) Man: moment alignment network for natural language moment retrieval via iterative graph adjustment. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1247\u20131257","DOI":"10.1109\/CVPR.2019.00134"},{"key":"21135_CR47","doi-asserted-by":"crossref","unstructured":"Hahn M, Kadav A, Rehg JM, Graf HP (2020) Tripping through time: efficient localization of activities in videos. In: 31st British machine vision conference 2020, BMVC 2020, virtual event, UK, September 7-10, 2020. BMVA Press","DOI":"10.5244\/C.34.135"},{"key":"21135_CR48","doi-asserted-by":"crossref","unstructured":"Wu J, Li G, Liu S, Lin L (2020) Tree-structured policy based progressive reinforcement learning for temporally language grounding in video. In: The thirty-fourth AAAI conference on artificial intelligence, AAAI 2020, the thirty-second innovative applications of artificial intelligence conference, IAAI 2020, the tenth AAAI symposium on educational advances in artificial intelligence, EAAI 2020, New York, NY, USA, February 7-12, 2020. AAAI Press, pp 12386\u201312393","DOI":"10.1609\/aaai.v34i07.6924"},{"key":"21135_CR49","doi-asserted-by":"crossref","unstructured":"Chen S, Jiang Y-G (2019) Semantic proposal for activity localization in videos via sentence query. In: The thirty-third AAAI conference on artificial intelligence, AAAI 2019, the thirty-first innovative applications of artificial intelligence conference, IAAI 2019, the ninth AAAI symposium on educational advances in artificial intelligence, EAAI 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019. AAAI Press, pp 8199\u20138206","DOI":"10.1609\/aaai.v33i01.33018199"},{"issue":"5","key":"21135_CR50","first-page":"2725","volume":"44","author":"Y Yuan","year":"2022","unstructured":"Yuan Y, Ma L, Wang J, Liu W, Zhu W (2022) Semantic conditioned dynamic modulation for temporal sentence grounding in videos. IEEE Trans Pattern Anal Mach Intell 44(5):2725\u20132741","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"21135_CR51","doi-asserted-by":"publisher","first-page":"1221","DOI":"10.1109\/TMM.2022.3142420","volume":"24","author":"G Wang","year":"2022","unstructured":"Wang G, Xu X, Shen F, Lu H, Ji Y, Shen HT (2022) Cross-modal dynamic networks for video moment retrieval with text query. IEEE Trans Multimedia 24:1221\u20131232","journal-title":"IEEE Trans Multimedia"},{"key":"21135_CR52","doi-asserted-by":"crossref","unstructured":"Zhang H, Sun A, Jing W, Zhou JT (2020) Span-based localizing network for natural language video localization. In: Jurafsky D, Chai J, Schluter N, Tetreault JR (eds) Proceedings of the 58th annual meeting of the association for computational linguistics, ACL 2020, Online, July 5-10, 2020. Association for Computational Linguistics, pp 6543\u20136554","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"21135_CR53","doi-asserted-by":"publisher","first-page":"5933","DOI":"10.1109\/TIP.2021.3090521","volume":"30","author":"Y Hu","year":"2021","unstructured":"Hu Y, Nie L, Liu M, Wang K, Wang Y, Hua X-S (2021) Coarse-to-fine semantic alignment for cross-modal moment localization. IEEE Trans Image Process 30:5933\u20135943","journal-title":"IEEE Trans Image Process"},{"key":"21135_CR54","doi-asserted-by":"crossref","unstructured":"Rodriguez C, Marrese-Taylor E, Saleh FS, Li H, Gould S (2020) Proposal-free temporal moment localization of a natural-language query in video using guided attention. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 2464\u20132473","DOI":"10.1109\/WACV45572.2020.9093328"},{"key":"21135_CR55","unstructured":"Ghosh S, Agarwal A, Parekh Z, Hauptmann AG (2019) Excl: extractive clip localization using natural language descriptions. In: Burstein J, Doran C, Solorio T (eds) Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers). Association for Computational Linguistics, pp 1984\u20131990"},{"key":"21135_CR56","doi-asserted-by":"crossref","unstructured":"Wang W, Huang Y, Wang L (2019) Language-driven temporal activity localization: a semantic matching reinforcement learning model. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 334\u2013343","DOI":"10.1109\/CVPR.2019.00042"},{"key":"21135_CR57","doi-asserted-by":"crossref","unstructured":"Jin W, Zhao Z, Zhang P, Zhu J, He X, Zhuang Y (2021) Hierarchical cross-modal graph consistency learning for video-text retrieval. In: Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval, pp 1114\u20131124","DOI":"10.1145\/3404835.3462974"},{"key":"21135_CR58","doi-asserted-by":"crossref","unstructured":"Bao W, Yu Q, Kong Y (2020) Uncertainty-based traffic accident anticipation with spatio-temporal relational learning. In: Proceedings of the 28th ACM international conference on multimedia, MM \u201920, New York, NY, USA. Association for Computing Machinery, pp 2682\u20132690","DOI":"10.1145\/3394171.3413827"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-025-21135-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-025-21135-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-025-21135-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,27]],"date-time":"2025-12-27T18:34:56Z","timestamp":1766860496000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-025-21135-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,1]]},"references-count":58,"journal-issue":{"issue":"42","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["21135"],"URL":"https:\/\/doi.org\/10.1007\/s11042-025-21135-z","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2025,10,1]]},"assertion":[{"value":"3 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 July 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 October 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This paper uses open source data, which meets the requirements of data usage.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent for data used"}},{"value":"There are no potential financial conflicts of interest in this paper.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}