{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:20:32Z","timestamp":1759332032561,"version":"3.37.3"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LR22F020001"],"award-info":[{"award-number":["LR22F020001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62125201","62072147","62020106007","61836002"],"award-info":[{"award-number":["62125201","62072147","62020106007","61836002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LDT23F02025F02"],"award-info":[{"award-number":["LDT23F02025F02"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2023.3254205","type":"journal-article","created":{"date-parts":[[2023,3,17]],"date-time":"2023-03-17T17:23:24Z","timestamp":1679073804000},"page":"9543-9556","source":"Crossref","is-referenced-by-count":5,"title":["Bilaterally Slimmable Transformer for Elastic and Efficient Visual Question Answering"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8407-1137","authenticated-orcid":false,"given":"Zhou","family":"Yu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7419-049X","authenticated-orcid":false,"given":"Zitian","family":"Jin","sequence":"additional","affiliation":[{"name":"HDU-ITMO Joint Institute, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1922-7283","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6885-3451","authenticated-orcid":false,"given":"Mingliang","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5003-3124","authenticated-orcid":false,"given":"Hongbo","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2290-1785","authenticated-orcid":false,"given":"Jianping","family":"Fan","sequence":"additional","affiliation":[{"name":"AI Lab at Lenovo Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref4","first-page":"1","article-title":"How much can clip benefit vision-and-language tasks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shen","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413977"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2796248"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3147385"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097502"},{"article-title":"Multimodal unified attention networks for vision-and-language interactions","year":"2019","author":"Yu","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref13","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref15","first-page":"1571","article-title":"Bilinear attention networks","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Kim","year":"2018"},{"key":"ref16","first-page":"1","article-title":"Vl-Bert: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su","year":"2020"},{"key":"ref17","first-page":"13","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref18","first-page":"2229","article-title":"A tensorized transformer for language modeling","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Ma","year":"2019"},{"key":"ref19","first-page":"1","article-title":"Albert: A lite bert for self-supervised learning of language representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lan","year":"2019"},{"key":"ref20","first-page":"1","article-title":"Universal transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dehghani","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1361"},{"key":"ref22","first-page":"1","article-title":"Reducing transformer depth on demand with structured dropout","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fan","year":"2019"},{"article-title":"Distilling task-specific knowledge from bert into simple neural networks","year":"2019","author":"Tang","key":"ref23"},{"article-title":"Distilbert, a distilled version of BERT: Smaller, faster, cheaper and lighter","year":"2019","author":"Sanh","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.537"},{"key":"ref27","first-page":"5776","article-title":"Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Wang","year":"2020"},{"key":"ref28","first-page":"1","article-title":"Slimmable neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu","year":"2018"},{"key":"ref29","first-page":"9782","article-title":"Dynabert: Dynamic bert with adaptive width and depth","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Hou","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3173131"},{"key":"ref31","first-page":"1","article-title":"Simple baseline for visual question answering","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou","year":"2015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref34","first-page":"1","article-title":"Hadamard product for low-rank bilinear pooling","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Kim","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref38","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Lu","year":"2016"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3026892"},{"key":"ref41","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguist.: Hum. Lang. Technol.","author":"Devlin","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref43","first-page":"1","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475251"},{"key":"ref52","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":"ref53","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2022"},{"key":"ref54","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":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref56","first-page":"1","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Han","year":"2016"},{"key":"ref57","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Han","year":"2015"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"article-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and $<$ 0.5 mb model size","year":"2016","author":"Iandola","key":"ref59"},{"article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","year":"2017","author":"Howard","key":"ref60"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00919"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00189"},{"key":"ref66","first-page":"1","article-title":"Once-for-all: Train one network and specialize it for efficient deployment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cai","year":"2019"},{"article-title":"Layer normalization","year":"2016","author":"Ba","key":"ref67"},{"article-title":"Roberta: A robustly optimized bert pretraining approach","year":"2019","author":"Liu","key":"ref68"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref69"},{"issue":"8","key":"ref70","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"issue":"140","key":"ref71","first-page":"1","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":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.529"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.686"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.250"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref76"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/10075477.pdf?arnumber=10075477","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:30:33Z","timestamp":1705019433000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10075477\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3254205","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2023]]}}}