{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:55:40Z","timestamp":1775325340853,"version":"3.50.1"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62336008"],"award-info":[{"award-number":["62336008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCF-Baidu Open Fund"},{"name":"NExT Research Center"},{"name":"Skywork AI, Singapore"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3393452","type":"journal-article","created":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T17:48:57Z","timestamp":1714067337000},"page":"7701-7719","source":"Crossref","is-referenced-by-count":34,"title":["Enhancing Video-Language Representations With Structural Spatio-Temporal Alignment"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3026-6347","authenticated-orcid":false,"given":"Hao","family":"Fei","sequence":"first","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6192-1194","authenticated-orcid":false,"given":"Shengqiong","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6335-1340","authenticated-orcid":false,"given":"Meishan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3895-5510","authenticated-orcid":false,"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8906-3777","authenticated-orcid":false,"given":"Shuicheng","family":"Yan","sequence":"additional","affiliation":[{"name":"Skywork AI, Kunlun 2050 Research, Singapore"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Sparks of artificial general intelligence: Early experiments with GPT-4","author":"Bubeck","year":"2023"},{"key":"ref2","article-title":"PaLM-E: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref3","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref4","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref5","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref6","article-title":"UniViLM: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01427"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref10","article-title":"Video-LLaVA: Learning united visual representation by alignment before projection","author":"Lin","year":"2023"},{"key":"ref11","first-page":"5696","article-title":"OmniVL: One foundation model for image-language and video-language tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01413"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref16","first-page":"38032","article-title":"Long-form video-language pre-training with multimodal temporal contrastive learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.545"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-2812"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"ref22","article-title":"A generalization of transformer networks to graphs","author":"Dwivedi","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.66"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.778"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3481540"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01413"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1159"},{"key":"ref39","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Velickovic"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref42","article-title":"VIOLET : End-to-end video-language transformers with masked visual-token modeling","author":"Fu","year":"2021"},{"key":"ref43","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983349"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01350"},{"key":"ref47","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref50","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref51","first-page":"1602","article-title":"Born-again neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Furlanello"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.731"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref55","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref60","article-title":"UniformerV2: Spatiotemporal learning by arming image vits with video uniformer","author":"Li","year":"2022"},{"key":"ref61","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tong","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3322329"},{"key":"ref64","article-title":"VLAB: Enhancing video language pre-training by feature adapting and blending","author":"He","year":"2023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00331"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"ref68","article-title":"Improving video-text retrieval by multi-stream corpus alignment and dual Softmax loss","author":"Cheng","year":"2021"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414640"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01091"},{"key":"ref74","article-title":"VALUE: A multi-task benchmark for video-and-language understanding evaluation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00203"},{"key":"ref76","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. Conf. Assoc. Comput. Linguistics","author":"Chen"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref78","article-title":"LanguageBind: Extending video-language pretraining to n-modality by language-based semantic alignment","author":"Zhu","year":"2023"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3060449"},{"key":"ref81","first-page":"12818","article-title":"Recurrent space-time graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Nicolicioiu"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10746266\/10508488.pdf?arnumber=10508488","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:08:49Z","timestamp":1732666129000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10508488\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":81,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3393452","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}