{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T07:40:06Z","timestamp":1735026006784,"version":"3.32.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800691","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"344-348","source":"Crossref","is-referenced-by-count":0,"title":["Mitigating Hallucination in Visual Language Model Segmentation with Negative Sampling"],"prefix":"10.1109","author":[{"given":"Tong Lee","family":"Chung","sequence":"first","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences"}]},{"given":"Jun","family":"Cheng","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences"}]},{"given":"Jianxin","family":"Pang","sequence":"additional","affiliation":[{"name":"Research Institute of UBTech Robotics"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"journal-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","year":"2023","author":"Bai","key":"ref2"},{"key":"ref3","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Liu","year":"2023"},{"article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhu","key":"ref4"},{"key":"ref5","article-title":"Language models are few-shot learners","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Brown","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.309"},{"key":"ref7","article-title":"Training language models to follow instructions with human feedback","volume-title":"Advances in Neural Information Processing Systems","author":"Ouyang","year":"2022"},{"key":"ref8","article-title":"Flamingo: a visual language model for few-shot learning","volume-title":"Advances in Neural Information Processing Systems","author":"Alayrac","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.876"},{"key":"ref10","article-title":"Lisa: Reasoning segmentation via large language model","author":"Lai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.550"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"2061","DOI":"10.18653\/v1\/2021.findings-acl.181","article-title":"Are rotten apples edible? challenging commonsense inference ability with exceptions","volume-title":"Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021","author":"Do","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11279"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1128"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.423"},{"key":"ref20","article-title":"What makes for good views for contrastive learning?","volume-title":"Proceedings of the 34th International Conference on Neural Infor-mation Processing Systems","author":"Tian","year":"2020"},{"article-title":"Contrastive learning with hard negative samples","volume-title":"International Conference on Learning Representations","author":"Robinson","key":"ref21"},{"article-title":"Extreme classification via adversarial softmax approximation","volume-title":"International Conference on Learning Representations","author":"Bamler","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02302"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2024,11,7]]},"location":"Beijing, China","end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800691.pdf?arnumber=10800691","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:34:06Z","timestamp":1735022046000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800691\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800691","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}