{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T22:06:59Z","timestamp":1780351619740,"version":"3.54.1"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3335875","type":"journal-article","created":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T19:14:49Z","timestamp":1701371689000},"page":"5548-5560","source":"Crossref","is-referenced-by-count":37,"title":["VideoXum: Cross-Modal Visual and Textural Summarization of Videos"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3223-3827","authenticated-orcid":false,"given":"Jingyang","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Rochester, Rochester, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5441-5776","authenticated-orcid":false,"given":"Hang","family":"Hua","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Rochester, Rochester, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2603-5239","authenticated-orcid":false,"given":"Ming","family":"Chen","sequence":"additional","affiliation":[{"name":"OPPO US Research Center, Palo Alto, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4666-9642","authenticated-orcid":false,"given":"Yikang","family":"Li","sequence":"additional","affiliation":[{"name":"OPPO US Research Center, Palo Alto, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4542-7809","authenticated-orcid":false,"given":"Jenhao","family":"Hsiao","sequence":"additional","affiliation":[{"name":"OPPO US Research Center, Palo Alto, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1607-6080","authenticated-orcid":false,"given":"Chiuman","family":"Ho","sequence":"additional","affiliation":[{"name":"OPPO US Research Center, Palo Alto, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4516-9729","authenticated-orcid":false,"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Rochester, Rochester, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874092"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3437378.3442693"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2010.08.004"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.118"},{"key":"ref10","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref11","first-page":"3833","article-title":"Rethinking pre-training and self-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zoph","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref13","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref16","first-page":"13988","article-title":"Clip-it! Language-guided video summarization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Narasimhan","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref18","article-title":"GODIVA: Generating open-domain videos from natural descriptions","author":"Wu","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12255"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_39"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00174"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123328"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00773"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.04.132"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00056"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2916989"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00173"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3321408.3322622"},{"key":"ref31","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. 49th Annu. Meetings Assoc. Comput. Linguistics","author":"Chen","year":"2011"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref36","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref39","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref40","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref41","first-page":"5776","article-title":"MINILM: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2020"},{"key":"ref42","first-page":"4514","article-title":"Probing inter-modality: Visual parsing with self-attention for vision-language pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xue","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref48","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref49","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac","year":"2022"},{"key":"ref50","article-title":"GIT: A generative image-to-text transformer for vision and language","volume":"2022","author":"Wang","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref51","article-title":"Coca: Contrastive captioners are image-text foundation models","volume":"2022","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref52","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021"},{"key":"ref53","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref54","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref55","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref57","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref58","first-page":"32897","article-title":"VLMo: Unified vision-language pre-training with mixture-of-modality-experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bao","year":"2022"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/762"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref62","article-title":"UniVL: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020"},{"key":"ref63","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lei","year":"2021"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_51"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00778"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.102"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref69","article-title":"Support-set bottlenecks for video-text representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Patrick","year":"2021"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_23"},{"key":"ref71","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref72","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2017"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/33.3.239"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1201\/9780367802417"},{"key":"ref75","article-title":"mPLUG-2: A modularized multi-modal foundation model across text, image and video","author":"Xu","year":"2023"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref77","first-page":"65","article-title":"Meteor: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. Assoc. Comput. Linguistics Workshop","author":"Banerjee","year":"2005"},{"key":"ref78","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref80","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Singer","year":"2023"},{"key":"ref81","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2020"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"ref84","first-page":"254","article-title":"Stronger generalization bounds for deep nets via a compression approach","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arora","year":"2018"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.258"},{"key":"ref86","article-title":"Fine-tuning pre-trained language models with noise stability regularization","author":"Hua","year":"2022"},{"key":"ref87","first-page":"11034","article-title":"Controllable unsupervised text attribute transfer via editing entangled latent representation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2019"},{"key":"ref88","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref89","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10334011.pdf?arnumber=10334011","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T20:33:25Z","timestamp":1711485205000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10334011\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":89,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3335875","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}