{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:33:17Z","timestamp":1792787597072,"version":"4.5.0"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3457586","type":"journal-article","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T19:21:56Z","timestamp":1725996116000},"page":"187128-187140","source":"Crossref","is-referenced-by-count":18,"title":["Architectural Synergies in Bi-Modal and Bi-Contrastive Learning"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2894-9231","authenticated-orcid":false,"given":"Yujia","family":"Gu","sequence":"first","affiliation":[{"name":"California State University at Long Beach, Long Beach, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian","family":"Liu","sequence":"additional","affiliation":[{"name":"Stuyvesant High School, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianlong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Pittsburgh, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9406-5329","authenticated-orcid":false,"given":"Xinye","family":"Sha","sequence":"additional","affiliation":[{"name":"Columbia University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7328-8871","authenticated-orcid":false,"given":"Shiyong","family":"Chen","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Alayrac"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref3","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023","journal-title":"arXiv:2301.00704"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref5","article-title":"CogView2: Faster and better text-to-image generation via hierarchical transformers","author":"Ding","year":"2022","journal-title":"arXiv:2204.14217"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref7","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv:2207.12598"},{"key":"ref8","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2013.274"},{"key":"ref11","article-title":"Unified-IO: A unified model for vision, language, and multi-modal tasks","author":"Lu","year":"2022","journal-title":"arXiv:2206.08916"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref13","article-title":"Combined scaling for open-vocabulary image classification","author":"Pham","year":"2021","journal-title":"arXiv:2111.10050"},{"key":"ref14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"issue":"8","key":"ref15","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref16","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref18","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Saharia"},{"key":"ref19","article-title":"CLIPPO: Image-and-language understanding from pixels only","author":"Tschannen","year":"2022","journal-title":"arXiv:2212.08045"},{"key":"ref20","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"arXiv:2205.14100"},{"key":"ref21","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","author":"Wang","year":"2022","journal-title":"arXiv:2202.03052"},{"key":"ref22","article-title":"Image as a foreign language: BEiT pretraining for all vision and vision-language tasks","author":"Wang","year":"2022","journal-title":"arXiv:2208.10442"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611743"},{"key":"ref24","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021","journal-title":"arXiv:2108.10904"},{"key":"ref25","article-title":"FILIP: Fine-grained interactive language-image pre-training","author":"Yao","year":"2021","journal-title":"arXiv:2111.07783"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_5"},{"key":"ref27","article-title":"Vector-quantized image modeling with improved VQGAN","author":"Yu","year":"2021","journal-title":"arXiv:2110.04627"},{"key":"ref28","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv:2205.01917"},{"key":"ref29","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"arXiv:2206.10789"},{"key":"ref30","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv:2111.11432"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10670389.pdf?arnumber=10670389","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T19:47:25Z","timestamp":1734551245000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10670389\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3457586","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}