{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:04:12Z","timestamp":1780052652044,"version":"3.53.1"},"reference-count":100,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["62025603"],"award-info":[{"award-number":["62025603"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2037"],"award-info":[{"award-number":["U21B2037"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176222"],"award-info":[{"award-number":["62176222"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176223"],"award-info":[{"award-number":["62176223"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176226"],"award-info":[{"award-number":["62176226"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072386"],"award-info":[{"award-number":["62072386"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072387"],"award-info":[{"award-number":["62072387"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072389"],"award-info":[{"award-number":["62072389"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62002305"],"award-info":[{"award-number":["62002305"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2021T40397"],"award-info":[{"award-number":["2021T40397"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2019B1515120049"],"award-info":[{"award-number":["2019B1515120049"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province of China","doi-asserted-by":"publisher","award":["2021J01002"],"award-info":[{"award-number":["2021J01002"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tip.2021.3139234","type":"journal-article","created":{"date-parts":[[2022,4,26]],"date-time":"2022-04-26T19:35:24Z","timestamp":1651001724000},"page":"3386-3398","source":"Crossref","is-referenced-by-count":61,"title":["Towards Lightweight Transformer Via Group-Wise Transformation for Vision-and-Language Tasks"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5334-1843","authenticated-orcid":false,"given":"Gen","family":"Luo","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, Media Analytics and Computing Laboratory, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5110-4526","authenticated-orcid":false,"given":"Yiyi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Media Analytics and Computing Laboratory, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3912-9306","authenticated-orcid":false,"given":"Xiaoshuai","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Media Analytics and Computing Laboratory, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7645-9606","authenticated-orcid":false,"given":"Liujuan","family":"Cao","sequence":"additional","affiliation":[{"name":"Tencent Technology (Shanghai) Company Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongjian","family":"Wu","sequence":"additional","affiliation":[{"name":"Tencent Technology (Shanghai) Company Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feiyue","family":"Huang","sequence":"additional","affiliation":[{"name":"Tencent Technology (Shanghai) Company Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9163-2932","authenticated-orcid":false,"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Media Analytics and Computing Laboratory, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. NIPS","author":"Vaswani"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref4","article-title":"Multimodal unified attention networks for vision-and-language interactions","volume-title":"arXiv:1908.04107","author":"Yu","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00592"},{"key":"ref8","article-title":"SMArT: Training shallow memory-aware transformers for robotic explainability","volume-title":"arXiv:1910.02974","author":"Cornia","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref10","first-page":"11135","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Herdade"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413977"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1219"},{"key":"ref14","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"arXiv:1810.04805","author":"Devlin","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref16","article-title":"VisualBERT: A simple and performant baseline for vision and language","volume-title":"arXiv:1908.03557","author":"Harold Li","year":"2019"},{"key":"ref17","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"},{"key":"ref18","article-title":"12-in-1: Multi-task vision and language representation learning","volume-title":"arXiv:1912.02315","author":"Lu","year":"2019"},{"key":"ref19","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"arXiv:1908.08530","author":"Su","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref21","first-page":"5754","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref25","first-page":"1","article-title":"Reducing transformer depth on demand with structured dropout","volume-title":"Proc. ICLR","author":"Fan"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref27","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","volume-title":"arXiv:1910.01108","author":"Sanh","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6409"},{"key":"ref29","article-title":"WaLDORf: Wasteless language-model distillation on reading-comprehension","volume-title":"arXiv:1912.06638","author":"Tian","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/EMC2-NIPS53020.2019.00016"},{"key":"ref31","first-page":"2229","article-title":"A tensorized transformer for language modeling","volume-title":"Proc. NIPS","author":"Ma"},{"key":"ref32","article-title":"Rethinking attention with performers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Choromanski"},{"key":"ref33","article-title":"Linformer: Self-attention with linear complexity","volume-title":"arXiv:2006.04768","author":"Wang","year":"2020"},{"key":"ref34","article-title":"Reformer: The efficient transformer","volume-title":"Proc. Int. Conf. Learn. Represent","author":"Kitaev"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref36","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","volume-title":"arXiv:1704.04861","author":"Howard","year":"2017"},{"key":"ref37","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref47","article-title":"Microsoft COCO captions: Data collection and evaluation server","volume-title":"arXiv:1504.00325","author":"Chen","year":"2015"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1133"},{"key":"ref51","article-title":"The evolved transformer","volume-title":"arXiv:1901.11117","author":"So","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1032"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_21"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00856"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17034"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref64","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"arXiv:2104.13840","author":"Chu","year":"2021"},{"key":"ref65","article-title":"XCiT: Cross-covariance image transformers","volume-title":"arXiv:2106.09681","author":"El-Nouby","year":"2021"},{"key":"ref66","article-title":"Contextual transformer networks for visual recognition","volume-title":"arXiv:2107.12292","author":"Li","year":"2021"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.520"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/155"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref75","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref76","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. ACL Workshop Text Summarization Braches Out","author":"Lin"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref79","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref81","article-title":"Hadamard product for low-rank bilinear pooling","volume-title":"arXiv:1610.04325","author":"Kim","year":"2016"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref86","article-title":"Compositional attention networks for machine reasoning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hudson"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref88","first-page":"4967","article-title":"A simple neural network module for relational reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Santoro"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01039"},{"key":"ref90","article-title":"Adam: A method for stochastic optimization","volume-title":"arXiv:1412.6980","author":"Kingma","year":"2014"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref97","first-page":"1564","article-title":"Bilinear attention networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.375"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2014-564"},{"key":"ref100","article-title":"Image transformer","volume-title":"arXiv:1802.05751","author":"Parmar","year":"2018"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9626658\/09763437.pdf?arnumber=9763437","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T17:42:45Z","timestamp":1747849365000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9763437\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":100,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3139234","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}