{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T20:20:58Z","timestamp":1725740458838},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[],"published-print":{"date-parts":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956616","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T14:34:13Z","timestamp":1669732453000},"page":"4779-4785","source":"Crossref","is-referenced-by-count":1,"title":["Augmenting Vision Language Pretraining by Learning Codebook with Visual Semantics"],"prefix":"10.1109","author":[{"given":"Xiaoyuan","family":"Guo","sequence":"first","affiliation":[{"name":"Emory University,Department of Computer Science,GA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiali","family":"Duan","sequence":"additional","affiliation":[{"name":"University of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.-C. Jay","family":"Kuo","sequence":"additional","affiliation":[{"name":"University of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Judy","family":"Wawira Gichoya","sequence":"additional","affiliation":[{"name":"Emory University,Department of Radiology and Imaging Sciences,GA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Imon","family":"Banerjee","sequence":"additional","affiliation":[{"name":"Arizona State University,School of Computing, Informatics, and Decision Systems Engineering,AZ,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Imagebert: Cross-modal pre-training with large-scale weak-supervised image-text data","year":"2020","author":"qi","key":"ref39"},{"article-title":"Unifying vision-and-language tasks via text generation","year":"2021","author":"cho","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"article-title":"Large-scale adversarial training for vision-and-language representation learning","year":"2020","author":"gan","key":"ref32"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"radford","key":"ref31"},{"article-title":"Decoupled weight decay regularization","year":"2017","author":"loshchilov","key":"ref30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"article-title":"Visualbert: A simple and performant baseline for vision and language","year":"2019","author":"li","key":"ref36"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"article-title":"Neural discrete representation learning","year":"2017","author":"oord","key":"ref10"},{"article-title":"Unimo: Towards unified-modal understanding and generation via cross-modal contrastive learning","year":"2020","author":"li","key":"ref40"},{"article-title":"Categorical reparameterization with gumbel-softmax","year":"2016","author":"jang","key":"ref11"},{"article-title":"BEiT: BERT Pre-Training of Image Transformers","year":"2021","author":"bao","key":"ref12"},{"article-title":"Zero-shot text-to-image generation","year":"2021","author":"ramesh","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01278"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"dosovitskiy","key":"ref15"},{"article-title":"Vl-bert: Pre-training of generic visual-linguistic representations","year":"2019","author":"su","key":"ref16"},{"article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","year":"2019","author":"lu","key":"ref17"},{"key":"ref18","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","author":"li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"article-title":"A corpus for reasoning about natural language grounded in photographs","year":"2018","author":"suhr","key":"ref28"},{"article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","year":"2021","author":"kim","key":"ref4"},{"article-title":"Visual entailment: A novel task for fine-grained image understanding","year":"2019","author":"xie","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"article-title":"Learning transferable visual models from natural language supervision","year":"2021","author":"radford","key":"ref6"},{"article-title":"Masked Autoen-coders Are Scalable Vision Learners","year":"2021","author":"he","key":"ref29"},{"key":"ref5","first-page":"121","article-title":"Oscar: Object-semantics aligned pre-training for vision-language tasks","author":"li","year":"2020","journal-title":"European Conference on Computer Vision"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"oord","key":"ref8"},{"article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","year":"2021","author":"jia","key":"ref7"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"devlin","key":"ref2"},{"key":"ref9","first-page":"104","article-title":"Uniter: Universal image-text representation learning","author":"chen","year":"2020","journal-title":"European Conference on Computer Vision"},{"article-title":"Language models are few-shot learners","year":"2020","author":"brown","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"article-title":"VIOLET: End-to-End Video-Language Transformers with Masked Visual-token Modeling","year":"2021","author":"fu","key":"ref42"},{"key":"ref24","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"ordonez","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00952"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01520"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"article-title":"PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers","year":"2021","author":"dong","key":"ref43"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2022,8,21]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956616.pdf?arnumber=9956616","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T15:03:40Z","timestamp":1671462220000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956616\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956616","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}