{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T12:42:17Z","timestamp":1780317737420,"version":"3.54.1"},"reference-count":41,"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":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["AISG-RP-2018-003"],"award-info":[{"award-number":["AISG-RP-2018-003"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MOE AcRF Tier-1","award":["RG95\/20"],"award-info":[{"award-number":["RG95\/20"]}]},{"name":"OPPO Research Grant"},{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2023.3237166","type":"journal-article","created":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T19:13:34Z","timestamp":1673896414000},"page":"8408-8417","source":"Crossref","is-referenced-by-count":12,"title":["Effective End-to-End Vision Language Pretraining With Semantic Visual Loss"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1882-9733","authenticated-orcid":false,"given":"Xiaofeng","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6649-7660","authenticated-orcid":false,"given":"Fayao","family":"Liu","sequence":"additional","affiliation":[{"name":"Agency for Science, Technology and Research (A*STAR), Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0329-7458","authenticated-orcid":false,"given":"Guosheng","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00728"},{"key":"ref4","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":"ref5","first-page":"104","article-title":"UNITER: Learning universal image-text representations","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Chen","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref7","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NIPS Deep Learn. Representation Learn. Workshop","author":"Hinton","year":"2015"},{"key":"ref8","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","volume-title":"CORR","author":"Huang","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Representations, Virtual Event, Austria, 2021","author":"Dosovitskiy","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2888822"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3009491"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3002667"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref19","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. 2019 Conf. North Amer. Chapter Assoc. Comput. Linguistics: Human Lang. Technologies","author":"Devlin","year":"2019"},{"key":"ref20","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref21","article-title":"Reformer: The efficient transformer","volume-title":"Proc.8th Int. Conf. Learn. Representations","author":"Kitaev","year":"2020"},{"key":"ref22","first-page":"3833","article-title":"Rethinking pre-training and self-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zoph","year":"2020"},{"key":"ref23","article-title":"Linformer: Self-attention with linear complexity","volume-title":"CORR","author":"Wang","year":"2020"},{"key":"ref24","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","volume-title":"CORR","author":"Sanh","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1441"},{"key":"ref27","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","volume-title":"CORR","author":"Liu","year":"2019"},{"key":"ref28","article-title":"Supervised contrastive learning for pre-trained language model fine-tuning","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Gunel","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88688-4_58"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICSEngT.2016.7849633"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref32","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":"ref33","article-title":"ImageBERT: Cross-modal pre-training with large-scale weak-supervised image-text data","volume-title":"CORR","author":"Qi","year":"2020"},{"key":"ref34","article-title":"Microsoft coco captions: Data collection and evaluation server","volume-title":"CORR","author":"Chen","year":"2015"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0965-7"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2034"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/10017364.pdf?arnumber=10017364","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:02:30Z","timestamp":1703030550000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10017364\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3237166","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}