{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T22:04:49Z","timestamp":1766268289384,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"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":[[2022,10,16]]},"DOI":"10.1109\/icip46576.2022.9897323","type":"proceedings-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T17:27:24Z","timestamp":1667496444000},"page":"2846-2850","source":"Crossref","is-referenced-by-count":19,"title":["CMA-CLIP: Cross-Modality Attention Clip for Text-Image Classification"],"prefix":"10.1109","author":[{"given":"Jinmiao","family":"Fu","sequence":"first","affiliation":[{"name":"Amazon Inc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaoyuan","family":"Xu","sequence":"additional","affiliation":[{"name":"Amazon Inc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huidong","family":"Liu","sequence":"additional","affiliation":[{"name":"Amazon Inc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Amazon Inc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Xie","sequence":"additional","affiliation":[{"name":"Amazon Inc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chien-Chih","family":"Wang","sequence":"additional","affiliation":[{"name":"Amazon Inc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Liu","sequence":"additional","affiliation":[{"name":"Amazon Inc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Sun","sequence":"additional","affiliation":[{"name":"Amazon Inc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bryan","family":"Wang","sequence":"additional","affiliation":[{"name":"Amazon Inc"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Visualbert: A simple and performant baseline for vision and language","volume":"abs\/1908.03557","author":"Li","year":"2019","journal-title":"arXiv"},{"key":"ref2","article-title":"Vl-bert: Pre-training of generic visual-linguistic representations","author":"Su","year":"2020","journal-title":"ICLR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref5","article-title":"Pixel-bert: Aligning image pixels with text by deep multi-modal transformers","volume":"abs\/2004.00849","author":"Huang","year":"2020","journal-title":"ArXiv"},{"key":"ref6","article-title":"Vilbert: Pre-training task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019","journal-title":"NeurIPS"},{"key":"ref7","article-title":"Bootstrap your own latent - a new approach to self-supervised learning","author":"Grill","year":"2020","journal-title":"NeurIPS"},{"key":"ref8","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"Caron","year":"2020","journal-title":"arXiv preprint arXiv:2006.09882"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"ref10","article-title":"Big self-supervised models are strong semi-supervised learners","author":"Chen","year":"2020","journal-title":"NeurIPS"},{"key":"ref11","article-title":"Contrastive learning of medical visual representations from paired images and text","volume":"abs\/2010.00747","author":"Zhang","year":"2020","journal-title":"arXiv"},{"key":"ref12","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref13","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021","journal-title":"arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3451390"},{"key":"ref15","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref16","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref18","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume":"abs\/1810.04805","author":"Devlin","year":"2019","journal-title":"arXiv"},{"key":"ref19","article-title":"Fashion-gen: The generative fashion dataset and challenge","volume":"abs\/1806.08317","author":"Rostamzadeh","year":"2018","journal-title":"arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-4666-3646-0.ch004"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01246"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401430"},{"key":"ref24","article-title":"Imagebert: Cross-modal pre-training with large-scale weak-supervised image-text data","author":"Qi","year":"2020","journal-title":"arXiv preprint arXiv:2001.07966"},{"key":"ref25","article-title":"Supervised multimodal bitransformers for classifying images and text","volume":"abs\/1909.02950","author":"Kiela","year":"2019","journal-title":"arXiv"}],"event":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2022,10,16]]},"location":"Bordeaux, France","end":{"date-parts":[[2022,10,19]]}},"container-title":["2022 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9897158\/9897159\/09897323.pdf?arnumber=9897323","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T15:49:36Z","timestamp":1705938576000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9897323\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,16]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icip46576.2022.9897323","relation":{},"subject":[],"published":{"date-parts":[[2022,10,16]]}}}