{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:55:14Z","timestamp":1784217314701,"version":"3.55.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"16","license":[{"start":{"date-parts":[[2023,2,23]],"date-time":"2023-02-23T00:00:00Z","timestamp":1677110400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,2,23]],"date-time":"2023-02-23T00:00:00Z","timestamp":1677110400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61801441"],"award-info":[{"award-number":["61801441"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1007\/s11042-023-14589-6","type":"journal-article","created":{"date-parts":[[2023,2,23]],"date-time":"2023-02-23T21:21:09Z","timestamp":1677187269000},"page":"24387-24406","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Text-video retrieval method based on enhanced self-attention and multi-task learning"],"prefix":"10.1007","volume":"82","author":[{"given":"Xiaoyu","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayao","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiantian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,2,23]]},"reference":[{"key":"14589_CR1","doi-asserted-by":"crossref","unstructured":"Brattoli B, Tighe J, Zhdanov F, Perona P, Chalupka K (2020) Rethinking zero-shot video classification: end-to-end training for realistic applications. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4613\u20134623","DOI":"10.1109\/CVPR42600.2020.00467"},{"key":"14589_CR2","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":"14589_CR3","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805"},{"issue":"12","key":"14589_CR4","doi-asserted-by":"publisher","first-page":"3377","DOI":"10.1109\/TMM.2018.2832602","volume":"20","author":"J Dong","year":"2018","unstructured":"Dong J, Li X, Snoek CG (2018) Predicting visual features from text for image and video caption retrieval. IEEE Trans Multimedia 20(12):3377\u20133388","journal-title":"IEEE Trans Multimedia"},{"key":"14589_CR5","doi-asserted-by":"crossref","unstructured":"Dong J, Li X, Xu C, Ji S, He Y, Yang G, Wang X (2019) Dual encoding for zero-example video retrieval. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9346\u20139355","DOI":"10.1109\/CVPR.2019.00957"},{"key":"14589_CR6","unstructured":"Fang H, Xiong P, Xu L, Chen Y (2021) Clip2video: mastering video-text retrieval via image clip. arXiv:2106.11097"},{"key":"14589_CR7","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Fan H, Malik J, He K (2019) Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6202\u20136211","DOI":"10.1109\/ICCV.2019.00630"},{"key":"14589_CR8","doi-asserted-by":"crossref","unstructured":"Gabeur V, Sun C, Alahari K, Schmid C (2020) Multi-modal transformer for video retrieval. In: Computer Vision\u2013ECCV 2020: 16th european conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part IV 16, Springer, pp 214\u2013229","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"14589_CR9","doi-asserted-by":"crossref","unstructured":"Gemmeke J F, Ellis D PW, Freedman D, Jansen A, Lawrence W, Moore R C, Plakal M, Ritter M (2017) Audio set: An ontology and human-labeled dataset for audio events. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 776\u2013780","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"14589_CR10","unstructured":"Gao Z, Liu J, Chen S, Chang D, Zhang H, Yuan J (2021) Clip2tv: an empirical study on transformer-based methods for video-text retrieval. arXiv:2111.05610"},{"key":"14589_CR11","doi-asserted-by":"crossref","unstructured":"Habibian A, Mensink T, Snoek CG (2014) Composite concept discovery for zero-shot video event detection. In: Proceedings of international conference on multimedia retrieval, pp 17\u201324","DOI":"10.1145\/2578726.2578746"},{"key":"14589_CR12","unstructured":"Hernandez R, Perez-Martin J, Bravo N, Barrios JM, Bustos B (2019) IMFD IMPRESEE at TRECVID 2019: Ad-Hoc Video Search and Video To Text. https:\/\/www-nlpir.nist.gov\/projects\/tvpubs\/tv19.papers\/imfd_impresee.pdf Accessed 7 March 2020"},{"key":"14589_CR13","doi-asserted-by":"crossref","unstructured":"Huang L, Wang W, Chen J, Wei X-Y (2019) Attention on attention for image captioning. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 4634\u20134643","DOI":"10.1109\/ICCV.2019.00473"},{"key":"14589_CR14","doi-asserted-by":"crossref","unstructured":"Jiang L, Meng D, Mitamura T, Hauptmann AG (2014) Easy samples first: self-paced reranking for zero-example multimedia search. In: Proceedings of the 22nd ACM international conference on multimedia, pp 547\u2013556","DOI":"10.1145\/2647868.2654918"},{"key":"14589_CR15","doi-asserted-by":"crossref","unstructured":"Krishna R, Hata K, Ren F, Fei-Fei L, Carlos Niebles J (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":"14589_CR16","unstructured":"Li X, Dong J, Xu C, Cao J, Wang X, Yang G (2018) Renmin University of China and Zhejiang Gongshang University at TRECVID 2018: Deep Cross-Modal Embeddings for Video-Text Retrieval. https:\/\/www-nlpir.nist.gov\/projects\/tvpubs\/tv18.papers\/rucmm.pdf. Accessed 13 November 2020"},{"key":"14589_CR17","unstructured":"Liu Y, Albanie S, Nagrani A, Zisserman A (2019) Use what you have: video retrieval using representations from collaborative experts. arXiv:1907.13487"},{"key":"14589_CR18","doi-asserted-by":"crossref","unstructured":"Luo H, Ji L, Zhong M, Chen Y, Lei W, Duan N, Li T (2021) CLIP4Clip: an empirical study of clip for end to end video clip retrieval. arXiv:2104.08860","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"14589_CR19","doi-asserted-by":"crossref","unstructured":"Markatopoulou F, Galanopoulos D, Mezaris V, Patras I (2017) Query and keyframe representations for ad-hoc video search. In: Proceedings of the 2017 ACM on international conference on multimedia retrieval, pp 407\u2013411","DOI":"10.1145\/3078971.3079041"},{"key":"14589_CR20","unstructured":"Miech A, Laptev I, Sivic J (2018) Learning a text-video embedding from incomplete and heterogeneous data. arXiv:1804.02516"},{"key":"14589_CR21","doi-asserted-by":"crossref","unstructured":"Miech A, Zhukov D, Alayrac J-B, Tapaswi M, Laptev I, Sivic J (2019) Howto100m: learning a text-video embedding by watching hundred million narrated video clips. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2630\u20132640","DOI":"10.1109\/ICCV.2019.00272"},{"key":"14589_CR22","unstructured":"Nguyen PA, Wu J, Ngo C-W, Danny F, Benoit H (2019) Vireo-eurecom@ trecvid 2019: Ad-hoc video search. https:\/\/www-nlpir.nist.gov\/projects\/tvpubs\/tv19.papers\/eurecom.pdf Accessed 7 March 2020"},{"key":"14589_CR23","unstructured":"Patrick M, Huang P-Y, Asano Y, Metze F, Hauptmann A, Henriques J, Vedaldi A (2020) Support-set bottlenecks for video-text representation learning. arXiv:2010.02824"},{"key":"14589_CR24","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J et al (2021) Learning transferable visual models from natural language supervision. arXiv:2103.00020"},{"issue":"1","key":"14589_CR25","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1007\/s11263-016-0987-1","volume":"123","author":"A Rohrbach","year":"2017","unstructured":"Rohrbach A, Torabi A, Rohrbach M, Tandon N, Pal C, Larochelle H, Courville A, Schiele B (2017) Movie description. Int J Comput Vis 123(1):94\u2013120","journal-title":"Int J Comput Vis"},{"key":"14589_CR26","unstructured":"Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: Advances in neural information processing systems, pp 3104\u20133112"},{"key":"14589_CR27","unstructured":"Tao Y, Wang T, Machado D, Garcia R, Tu Y, Reyes MP, Chen Y, Tian H, Shyu M-L, Chen S-C (2019) Florida international university-university of miami trecvid 2019. In: TRECVID. NIST, USA"},{"key":"14589_CR28","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":"14589_CR29","unstructured":"Ueki K, Hirakawa K, Kikuchi K, Ogawa T, Kobayashi T (2017) Waseda_Meisei at TRECVID 2017: Ad-hoc Video Search. https:\/\/www-nlpir.nist.gov\/projects\/tvpubs\/tv17.papers\/waseda_meisei.pdf. Accessed 13 November 2020"},{"key":"14589_CR30","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141., Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998\u20136008"},{"key":"14589_CR31","doi-asserted-by":"crossref","unstructured":"Xie S, Sun C, Huang J, Tu Z, Murphy K (2018) Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Proceedings of the European conference on computer vision (ECCV), pp 305\u2013321","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"14589_CR32","doi-asserted-by":"crossref","unstructured":"Xu J, Mei T, Yao T, Rui Y (2016) Msr-vtt: a large video description dataset for bridging video and language. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5288\u20135296","DOI":"10.1109\/CVPR.2016.571"},{"key":"14589_CR33","doi-asserted-by":"crossref","unstructured":"Xie S, Sun C, Huang J, Tu Z, Murphy K (2018) Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification. In: Proceedings of the European conference on computer vision (ECCV), pp 305\u2013321","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"14589_CR34","doi-asserted-by":"crossref","unstructured":"Yu Y, Kim J, Kim G (2018) A joint sequence fusion model for video question answering and retrieval. In: Proceedings of the European conference on computer vision (ECCV), pp 471\u2013487","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"14589_CR35","doi-asserted-by":"crossref","unstructured":"Yu Y, Ko H, Choi J, Kim G (2017) End-to-end concept word detection for video captioning, retrieval, and question answering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3165\u20133173","DOI":"10.1109\/CVPR.2017.347"},{"key":"14589_CR36","doi-asserted-by":"crossref","unstructured":"Zhang B, Hu H, Sha F (2018) Cross-modal and hierarchical modeling of video and text. In: Proceedings of the European conference on computer vision (ECCV), pp 374\u2013390","DOI":"10.1007\/978-3-030-01261-8_23"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-14589-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-14589-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-14589-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T18:52:54Z","timestamp":1687546374000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-14589-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,23]]},"references-count":36,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["14589"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-14589-6","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,23]]},"assertion":[{"value":"28 September 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 January 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 January 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 February 2023","order":4,"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 that there is no conflict of interest regarding the publication of this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}