{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T08:10:19Z","timestamp":1783930219973,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234318","type":"print"},{"value":"9789819234325","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-981-92-3432-5_46","type":"book-chapter","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T07:40:14Z","timestamp":1783928414000},"page":"565-575","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Lightweight Temporal-Structural Enhancement for CLIP-Based Video-Text Retrieval"],"prefix":"10.1007","author":[{"given":"Yan","family":"Wan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"46_CR1","doi-asserted-by":"publisher","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. arXiv arXiv:2104.00650 (2021). https:\/\/doi.org\/10.48550\/arXiv.2104.00650","DOI":"10.48550\/arXiv.2104.00650"},{"key":"46_CR2","unstructured":"Chen, D.L., Dolan, W.B.: Collecting highly parallel data for paraphrase evaluation. In: 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT), pp. 190\u2013200. Portland, OR, USA (2011), https:\/\/aclanthology.org\/P11-1020"},{"key":"46_CR3","doi-asserted-by":"crossref","unstructured":"Croitoru, I., Bogolin, S.V., Liu, Y., Albanie, S., Leordeanu, M., Zisserman, A.: Teachtext: crossmodal generalized distillation for text-video retrieval. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11583\u201311593. Montreal, QC, Canada (2021)","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"46_CR4","unstructured":"Dong, J., et al.: Dual encoding for zero-example video retrieval. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9346\u20139355. Nashville, TN, USA (2021)"},{"key":"46_CR5","doi-asserted-by":"publisher","unstructured":"Dzabraev, M., Kalashnikov, M., Komkov, S., Petiushko, A.: MDMMT: multidomain multimodal transformer for video retrieval. arXiv arXiv:2103.10699 (2021). https:\/\/doi.org\/10.48550\/arXiv.2103.10699","DOI":"10.48550\/arXiv.2103.10699"},{"key":"46_CR6","doi-asserted-by":"publisher","unstructured":"Fang, H., Xiong, P., Xu, L., Chen, Y.: CLIP2Video: mastering video-text retrieval via image CLIP. arXiv arXiv:2106.11097 (2021). https:\/\/doi.org\/10.48550\/arXiv.2106.11097","DOI":"10.48550\/arXiv.2106.11097"},{"key":"46_CR7","doi-asserted-by":"crossref","unstructured":"Gabeur, V., Sun, C., Alahari, K., Schmid, C.: Multi-modal transformer for video retrieval. In: European Conference on Computer Vision (ECCV), vol. 5, pp. 214\u2013229. Springer, Glasgow, UK (2020)","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"46_CR8","doi-asserted-by":"publisher","unstructured":"Gao, Z., Liu, J., Sun, W., Chen, S., Chang, D., Zhao, L.: CLIP2TV: align, match and distill for video-text retrieval. arXiv arXiv:2111.05610 (2022). https:\/\/doi.org\/10.48550\/arXiv.2111.05610","DOI":"10.48550\/arXiv.2111.05610"},{"key":"46_CR9","doi-asserted-by":"crossref","unstructured":"Ge, Y., et al.: Bridging video-text retrieval with multiple choice questions. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16167\u201316176. New Orleans, LA, USA (2022)","DOI":"10.1109\/CVPR52688.2022.01569"},{"key":"46_CR10","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Niebles, J.C.: Dense-captioning events in videos. In: IEEE International Conference on Computer Vision (ICCV), pp. 706\u2013715. Venice, Italy (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"46_CR11","doi-asserted-by":"publisher","unstructured":"Lei, J., et al.: Less is more: ClipBERT for video-and-language learning via sparse sampling. arXiv arXiv:2102.06183 (2021). https:\/\/doi.org\/10.48550\/arXiv.2102.06183","DOI":"10.48550\/arXiv.2102.06183"},{"key":"46_CR12","doi-asserted-by":"publisher","unstructured":"Liu, S., Fan, H., Qian, S., Chen, Y., Ding, W., Wang, Z.: HiT: hierarchical transformer with momentum contrast for video-text retrieval. arXiv arXiv:2103.15049 (2021). https:\/\/doi.org\/10.48550\/arXiv.2103.15049","DOI":"10.48550\/arXiv.2103.15049"},{"key":"46_CR13","doi-asserted-by":"publisher","unstructured":"Liu, Y., Albanie, S., Nagrani, A., Zisserman, A.: Use what you have: video retrieval using representations from collaborative experts. arXiv arXiv:1907.13487 (2019). https:\/\/doi.org\/10.48550\/arXiv.1907.13487","DOI":"10.48550\/arXiv.1907.13487"},{"key":"46_CR14","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.neucom.2022.07.028","volume":"508","author":"H Luo","year":"2022","unstructured":"Luo, H., et al.: CLIP4Clip: an empirical study of CLIP for end-to-end video clip retrieval and captioning. Neurocomputing 508, 293\u2013304 (2022). https:\/\/doi.org\/10.1016\/j.neucom.2022.07.028","journal-title":"Neurocomputing"},{"key":"46_CR15","doi-asserted-by":"publisher","unstructured":"Ma, Y., Xu, G., Sun, X., Yan, M., Zhang, J., Ji, R.: X-CLIP: end-to-end multi-grained contrastive learning for video-text retrieval. In: 30th ACM International Conference on Multimedia (ACM MM), pp. 638\u2013647. Lisbon, Portugal (2022). https:\/\/doi.org\/10.1145\/3503161.3547910","DOI":"10.1145\/3503161.3547910"},{"key":"46_CR16","doi-asserted-by":"publisher","unstructured":"Miech, A., Zhukov, D., Alayrac, J.B., Tapaswi, M., Laptev, I., Sivic, J.: HowTo100M: learning a text-video embedding by watching hundred million narrated video clips. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2630\u20132640. Seoul, South Korea (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00272","DOI":"10.1109\/ICCV.2019.00272"},{"key":"46_CR17","doi-asserted-by":"publisher","unstructured":"Patrick, M., et al.: Support-set bottlenecks for video-text representation learning. arXiv arXiv:2010.02824 (2021). https:\/\/doi.org\/10.48550\/arXiv.2010.02824","DOI":"10.48550\/arXiv.2010.02824"},{"key":"46_CR18","doi-asserted-by":"publisher","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: 38th International Conference on Machine Learning (ICML), pp. 8748\u20138763. Virtual (2021). https:\/\/doi.org\/10.48550\/arXiv.2103.00020","DOI":"10.48550\/arXiv.2103.00020"},{"key":"46_CR19","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: All in one: Exploring unified video-language pre-training. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6598\u20136608. Vancouver, BC, Canada (2023)","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"46_CR20","doi-asserted-by":"publisher","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5288\u20135296. Las Vegas, NV, USA (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.571","DOI":"10.1109\/CVPR.2016.571"},{"key":"46_CR21","doi-asserted-by":"publisher","unstructured":"Yu, Y., Kim, J., Kim, G.: A joint sequence fusion model for video question answering and retrieval. In: European Conference on Computer Vision (ECCV), pp. 471\u2013487. Munich, Germany (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_29","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"46_CR22","unstructured":"Zhang, C., Zou, Y., Chen, G., Gan, L.: Frame-level sequence encoder and semantic preserving embedding for video retrieval. In: ACM International Conference on Multimedia Retrieval (ICMR), pp. 426\u2013433. Yokohama, Japan (2018)"},{"key":"46_CR23","doi-asserted-by":"publisher","unstructured":"Zhao, S., Zhu, L., Wang, X., Yang, Y.: CenterCLIP: token clustering for efficient text-video retrieval. In: 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 970\u2013981. Madrid, Spain (2022). https:\/\/doi.org\/10.1145\/3477495.3531950","DOI":"10.1145\/3477495.3531950"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3432-5_46","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T07:40:17Z","timestamp":1783928417000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3432-5_46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"ISBN":["9789819234318","9789819234325"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3432-5_46","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]},"assertion":[{"value":"14 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}