{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:42:39Z","timestamp":1781584959349,"version":"3.54.5"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890236","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Video-Poetry Retrieval with Multimodal Knowledge Graph Guided Unsupervised Pre-training"],"prefix":"10.1109","author":[{"given":"Xinru","family":"Wei","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqing","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Chinese clip: Contrastive vision-language pretraining in chinese","author":"Yang","year":"2022"},{"key":"ref2","article-title":"Ccpm: A chinese classical poetry matching dataset","author":"Li","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3275071"},{"key":"ref4","article-title":"Youku-mplug: A 10 million large-scale chinese video-language dataset for pre-training and benchmarks","author":"Xu","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"ref6","article-title":"Languagebind: Extending video-language pretraining to n-modality by language-based semantic alignment","author":"Zhu","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref8","article-title":"Clip-vip: Adapting pre-trained image-text model to video-language representation alignment","author":"Xue","year":"2022"},{"key":"ref9","article-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation","author":"Wang","year":"2023"},{"key":"ref10","article-title":"Mug-STAN: Adapting Image-Language Pretrained Models for General Video Understanding","author":"Liu","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01296"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.171"},{"key":"ref13","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref14","article-title":"M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining","author":"Guo","year":"2024","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3341161.3342885"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01031"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-3005"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3241910"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/696"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00513"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref27","first-page":"24206","article-title":"Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text","volume":"34","author":"Akbari","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.370"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref31","article-title":"Univl: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01599"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.742"},{"key":"ref34","article-title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","author":"GLM","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446490"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890236.pdf?arnumber=10890236","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:11Z","timestamp":1774416311000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890236\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890236","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}