{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T04:04:13Z","timestamp":1750737853741,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819670048","type":"print"},{"value":"9789819670055","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-7005-5_3","type":"book-chapter","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T14:25:10Z","timestamp":1750688710000},"page":"31-46","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EPRVR: Efficient Partially Relevant Video Retrieval with\u00a0Disentangled Video Representation Learning"],"prefix":"10.1007","author":[{"given":"Zhaoxing","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongqin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yesheng","family":"Chai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiao","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bibo","family":"Tu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jizhong","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,24]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: A joint video and image encoder for end-to-end retrieval. In: ICCV, pp. 1728\u20131738 (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Chen, S., Zhao, Y., Jin, Q., Wu, Q.: Fine-grained video-text retrieval with hierarchical graph reasoning. In: CVPR, pp. 10638\u201310647 (2020)","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Dong, J., et al.: Dual encoding for zero-example video retrieval. In: CVPR, pp. 9346\u20139355 (2019)","DOI":"10.1109\/CVPR.2019.00957"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Dong, J., et al.: Dual encoding for video retrieval by text. TPAMI (2021)","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Dong, J., et al.: Reading-strategy inspired visual representation learning for text-to video retrieval. TCSVT (2022)","DOI":"10.1109\/TCSVT.2022.3150959"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Dong, J., et al.: Partially relevant video retrieval. In: ACM MM, pp. 246\u2013257 (2022)","DOI":"10.1145\/3503161.3547976"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Dong, J., et al.: Dual learning with dynamic knowledge distillation for partially relevant video retrieval. In: ICCV, pp. 11302\u201311312 (2023)","DOI":"10.1109\/ICCV51070.2023.01038"},{"key":"3_CR8","unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: Vse++: improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612 (2017)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Gao, J., Xu, C.: Fast video moment retrieval. In: ICCV, pp. 1523\u20131532 (2021)","DOI":"10.1109\/ICCV48922.2021.00155"},{"key":"3_CR10","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":"3_CR11","doi-asserted-by":"crossref","unstructured":"Hou, D., Pang, L., Shen, H., Cheng, X.: Improving video corpus moment retrieval with partial relevance enhancement. In: Proceedings of the 2024 International Conference on Multimedia Retrieval, pp. 394\u2013403 (2024)","DOI":"10.1145\/3652583.3658088"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Jiang, X., Xu, X., Zhang, J., Shen, F., Cao, Z., Cai, X.: Gtlr: graph based transformer with language reconstruction for video paragraph grounding. In: ICME, pp.\u00a01\u20136 (2022)","DOI":"10.1109\/ICME52920.2022.9859847"},{"key":"3_CR13","unstructured":"Jiang, X., Xu, X., Zhang, J., Shen, F., Cao, Z., Shen, H.T.: Sdn: semantic decoupling network for temporal language grounding. IEEE TNNLS, pp. 1\u201315 (2022)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Jiang, X., Xu, X., Zhang, J., Shen, F., Cao, Z., Shen, H.T.: Semi supervised video paragraph grounding with contrastive encoder. In: CVPR, pp. 2466\u20132475 (2022)","DOI":"10.1109\/CVPR52688.2022.00250"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Jiang, X., Chen, Z., Xu, X., Shen, F., Cao, Z., Cai, X.: Progressive event alignment network for partial relevant video retrieval. In: ICME, pp. 1973\u20131978. IEEE (2023)","DOI":"10.1109\/ICME55011.2023.00338"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Jin, W., Zhao, Z., Zhang, P., Zhu, J., He, X., Zhuang, Y.: Hierarchical crossmodal graph consistency learning for video-text retrieval. In: SIGIR, pp. 1114\u20131124 (2021)","DOI":"10.1145\/3404835.3462974"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Carlos\u00a0Niebles, J.: Dense-captioning events in videos. In: ICCV, pp. 706\u2013715 (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Berg, T.L., Bansal, M.: Tvr: a large-scale dataset for video-subtitle moment retrieval. In: ECCV, pp. 447\u2013463. Springer (2020)","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Li, X., Xu, C., Yang, G., Chen, Z., Dong, J.: W2vv++ fully deep learning for ad-hoc video search. In: ACM MM, pp. 1786\u20131794 (2019)","DOI":"10.1145\/3343031.3350906"},{"key":"3_CR20","doi-asserted-by":"publisher","first-page":"4351","DOI":"10.1109\/TMM.2020.3042067","volume":"23","author":"X Li","year":"2020","unstructured":"Li, X., Zhou, F., Xu, C., Ji, J., Yang, G.: Sea: Sentence encoder assembly for video retrieval by textual queries. IEEE Trans. Multimedia 23, 4351\u20134362 (2020)","journal-title":"IEEE Trans. Multimedia"},{"key":"3_CR21","unstructured":"Liu, Y., Albanie, S., Nagrani, A., Zisserman, A.: Use what you have: video retrieval using representations from collaborative experts. arXiv preprint arXiv:1907.13487 (2019)"},{"key":"3_CR22","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., Ji, L., Zhong, M., Chen, Y., Lei, W., Duan, N., Li, T.: Clip4clip: an empirical study of clip for end to end video clip retrieval and captioning. Neurocomputing 508, 293\u2013304 (2022)","journal-title":"Neurocomputing"},{"key":"3_CR23","doi-asserted-by":"crossref","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: ICCV, pp. 2630\u20132640 (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Miech, A., Alayrac, J.B., Smaira, L., Laptev, I., Sivic, J., Zisserman, A.: End-to-end learning of visual representations from uncurated instructional videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9879\u20139889 (2020)","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Nishimura, T., Nakada, S., Kondo, M.: Large-scale vision-language models learn super images for efficient and high-performance partially relevant video retrieval. arXiv preprint arXiv:2312.00414 (2023)","DOI":"10.1145\/3708349"},{"key":"3_CR26","doi-asserted-by":"publisher","first-page":"2914","DOI":"10.1109\/TMM.2021.3090595","volume":"24","author":"X Song","year":"2021","unstructured":"Song, X., Chen, J., Wu, Z., Jiang, Y.G.: Spatial-temporal graphs for cross-modal text2video retrieval. IEEE Trans. Multimedia 24, 2914\u20132923 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"3_CR27","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, H.T.: Cross-modal dynamic networks for video moment retrieval with text query. IEEE Trans. Multimedia 24, 1221\u20131232 (2022)","journal-title":"IEEE Trans. Multimedia"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Wang, J., et\u00a0al.: Milvus: a purpose-built vector data management system. In: Proceedings of the 2021 International Conference on Management of Data, pp. 2614\u20132627 (2021)","DOI":"10.1145\/3448016.3457550"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Wang, N., Wang, Z., Xu, X., Shen, F., Yang, Y., Shen, H.T.: Attention based relation reasoning network for video-text retrieval. In: ICME, pp.\u00a01\u20136 (2021)","DOI":"10.1109\/ICME51207.2021.9428215"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Wang, Y., Dong, J., Liang, T., Zhang, M., Cai, R., Wang, X.: Cross-lingual cross-modal retrieval with noise-robust learning. In: ACM MM, pp. 422\u2013433 (2022)","DOI":"10.1145\/3503161.3548003"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, J., Chen, B., Zeng, Z., Xia, S.T.: Gmmformer: Gaussian-mixture-model based transformer for efficient partially relevant video retrieval. In: AAAI, vol.\u00a038, pp. 5767\u20135775 (2024)","DOI":"10.1609\/aaai.v38i6.28389"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Wu, W., Luo, H., Fang, B., Wang, J., Ouyang, W.: Cap4video: What can auxiliary captions do for text-video retrieval? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10704\u201310713 (2023)","DOI":"10.1109\/CVPR52729.2023.01031"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Yang, X., Feng, F., Ji, W., Wang, M., Chua, T.S.: Deconfounded video moment retrieval with causal intervention. In: SIGIR, pp. 1\u201310 (2021)","DOI":"10.1145\/3404835.3462823"},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Yu, Y., Kim, J., Kim, G.: A joint sequence fusion model for video question answering and retrieval. In: ECCV, pp. 471\u2013487 (2018)","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Video corpus moment retrieval with contrastive learning. In: SIGIR, pp. 685\u2013695 (2021)","DOI":"10.1145\/3404835.3462874"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-7005-5_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T14:25:22Z","timestamp":1750688722000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-7005-5_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819670048","9789819670055"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-7005-5_3","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}