{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:34:25Z","timestamp":1780763665484,"version":"3.54.1"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00271","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2825-2835","source":"Crossref","is-referenced-by-count":1,"title":["Know \u201cNo\u201d Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP"],"prefix":"10.1109","author":[{"given":"Junsung","family":"Park","sequence":"first","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jungbeom","family":"Lee","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jongyoon","family":"Song","sequence":"additional","affiliation":[{"name":"Samsung Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sangwon","family":"Yu","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dahuin","family":"Jung","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Soongsil University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sungroh","family":"Yoon","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","year":"2024","journal-title":"AI@Meta. Llama 3 model card"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01118"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref5","article-title":"Fairerclip: Debiasing clip\u2019s zero-shot predictions using functions in rkhss","author":"Dehdashtian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref7","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01551"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.531"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.102"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1355"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref14","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International Conference on machine learning","author":"Jia"},{"key":"ref15","article-title":"Negbert: a transfer learning approach for negation detection and scope resolution","author":"Khandelwal","year":"2019","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01999"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.356"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.488"},{"key":"ref20","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on machine learning","author":"Li"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref25","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref27","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01050"},{"key":"ref30","article-title":"Out-of-distribution detection with negative prompts","volume-title":"The Twelfth International Conference on Learning Representations","author":"Nie"},{"key":"ref31","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref32","year":"2023","journal-title":"OpenAI. Gpt-4 technical report"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.567"},{"key":"ref34","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref36","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on machine learning","author":"Ramesh"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref39","article-title":"LAION-5b: An open large-scale dataset for training next generation image-text models","volume-title":"Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Schuhmann"},{"key":"ref40","article-title":"Learn\u201d no\u201d to say\u201d yes\u201d better: Improving vision-language models via negations","author":"Singh","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Aligning large multi-modal models with factually augmented rlhf","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01237"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02521"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00173"},{"key":"ref45","article-title":"The all-seeing project: Towards panoptic visual recognition and understanding of the open world","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547968"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref48","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"When and why vision-language models behave like bags-of-words, and what to do about it?","author":"Yuksekgonul","year":"2022","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446193.pdf?arnumber=11446193","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:58:34Z","timestamp":1777611514000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446193\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00271","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}