{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:26:59Z","timestamp":1783528019002,"version":"3.55.0"},"reference-count":41,"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\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020950","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\/wacv61042.2026.00310","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"3172-3181","source":"Crossref","is-referenced-by-count":1,"title":["Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment"],"prefix":"10.1109","author":[{"given":"Kai-Po","family":"Chang","sequence":"first","affiliation":[{"name":"National Taiwan University,Graduate Institute of Communication Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Yuan","family":"Cheng","sequence":"additional","affiliation":[{"name":"National Taiwan University,Graduate Institute of Communication Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi-Pin","family":"Huang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Graduate Institute of Communication Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fu-En","family":"Yang","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Chiang Frank","family":"Wang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Graduate Institute of Communication Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025"},{"key":"ref3","article-title":"RAPPER: Reinforced rationale-prompted paradigm for natural language explanation in visual question answering","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chang"},{"key":"ref4","article-title":"PerturboLLaVA: Reducing multimodal hallucinations with perturbative visual training","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Chen"},{"key":"ref5","article-title":"Vidhal: Benchmarking temporal hallucinations in vision llms","author":"Choong","year":"2024"},{"key":"ref6","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref7","author":"Fellbaum","year":"2010","journal-title":"Princeton university: About wordnet"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02245"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"ref10","article-title":"Gpt-4o system card","author":"Hurst","year":"2024"},{"key":"ref11","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"International conference on machine learning","author":"Jaegle"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02553"},{"key":"ref13","first-page":"48955","article-title":"Miradata: A large-scale video dataset with long durations and structured captions","volume":"37","author":"Ju","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref16","article-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models","author":"Li","year":"2024"},{"key":"ref17","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Li"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.723"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01249"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref22","author":"Park","year":"2025","journal-title":"Mitigating dialogue hallucination for large vision language models via adversarial instruction tuning"},{"key":"ref23","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref24","author":"Ravi","year":"2024","journal-title":"Sam 2: Segment anything in images and videos"},{"key":"ref25","author":"Ren","year":"2024","journal-title":"Grounding dino 1.5: Advance the \u201cedge\u201d of open-set object detection"},{"key":"ref26","article-title":"Data-augmented phrase-level alignment for mitigating object hallucination","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Sarkar"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1108\/eb026526"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02521"},{"key":"ref29","article-title":"MLLM can see? dynamic correction decoding for hallucination mitigation","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Wang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-55065-7_302265"},{"key":"ref31","article-title":"Videohallucer: Evaluating intrinsic and extrinsic hallucinations in large video-language models","author":"Wang","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0910"},{"key":"ref33","article-title":"Unified triplet-level hallucination evaluation for large vision-language models","author":"Wu","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"key":"ref34","first-page":"53553","article-title":"Evaluating and analyzing relationship hallucinations in large vision-language models","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Wu"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref36","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024"},{"key":"ref37","article-title":"Vript: A video is worth thousands of words","author":"Yang","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref39","article-title":"Video instruction tuning with synthetic data","author":"Zhang","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref41","article-title":"Aligning modalities in vision large language models via preference fine-tuning","author":"Zhou","year":"2024"}],"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\/11491962.pdf?arnumber=11491962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:53:21Z","timestamp":1778046801000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11491962\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00310","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}