{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:12:17Z","timestamp":1778051537758,"version":"3.51.4"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00829","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"8596-8605","source":"Crossref","is-referenced-by-count":0,"title":["Relevance-aware Multi-context Contrastive Decoding for Retrieval-augmented Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Jongha","family":"Kim","sequence":"first","affiliation":[{"name":"Korea University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byungoh","family":"Ko","sequence":"additional","affiliation":[{"name":"Korea University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeehye","family":"Na","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinsung","family":"Yoon","sequence":"additional","affiliation":[{"name":"Google Cloud AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyunwoo J.","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Web interface"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref3","article-title":"Self-rag: Learning to retrieve, generate, and critique through self-reflection","volume-title":"ICLR","author":"Asai"},{"key":"ref4","article-title":"Language models are few-shot learners","volume-title":"NeurIPS","author":"Brown"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00188"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01311"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.925"},{"key":"ref8","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024"},{"key":"ref9","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref10","article-title":"Dola: Decoding by contrasting layers improves factuality in large language models","volume-title":"ICLR","author":"Chuang"},{"key":"ref11","article-title":"Scaling instruction-finetuned language models","volume-title":"JMLR","author":"Chung"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.70"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01108"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02238"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463259"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i27.39417"},{"key":"ref20","article-title":"Instructive decoding: Instruction-tuned large language models are self-refiner from noisy instructions","volume-title":"ICLR","author":"Kim"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.261"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02067"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32474"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref25","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume-title":"NeurIPS","author":"Lewis"},{"key":"ref26","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML","author":"Li"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.687"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.772"},{"key":"ref30","article-title":"Fine-grained late-interaction multi-modal retrieval for retrieval augmented visual question answering","volume-title":"NeurIPS","author":"Lin"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.289"},{"key":"ref32","article-title":"Revive: Regional visual representation matters in knowledge-based visual question answering","volume-title":"NeurIPS","author":"Lin"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.517"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00289"},{"key":"ref38","article-title":"Contrastive decoding improves reasoning in large language models","author":"O\u2019Brien","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1179"},{"key":"ref40","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01438"},{"key":"ref43","article-title":"Large language models can be easily distracted by irrelevant context","volume-title":"ICML","author":"Shi"},{"key":"ref44","article-title":"Self-consistency improves chain of thought reasoning in language models","volume-title":"ICLR","author":"Wang"},{"key":"ref45","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024"},{"key":"ref46","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref47","article-title":"Making retrieval-augmented language models robust to irrelevant context","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yoran"},{"key":"ref48","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01255"},{"key":"ref50","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","volume-title":"ICLR","author":"Zhu"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492383.pdf?arnumber=11492383","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:16:42Z","timestamp":1778048202000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492383\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00829","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}