{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T16:41:03Z","timestamp":1781628063924,"version":"3.54.5"},"reference-count":74,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"publisher","award":["62206170,62376199"],"award-info":[{"award-number":["62206170,62376199"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01898","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20413-20424","source":"Crossref","is-referenced-by-count":1,"title":["Leveraging Debiased Cross-Modal Attention Maps and Code-Based Reasoning for Zero-Shot Referring Expression Comprehension"],"prefix":"10.1109","author":[{"given":"Juntao","family":"Chen","sequence":"first","affiliation":[{"name":"Tongji University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Shen","sequence":"additional","affiliation":[{"name":"Tongji University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihua","family":"Wei","sequence":"additional","affiliation":[{"name":"Tongji University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijun","family":"Sun","sequence":"additional","affiliation":[{"name":"Tongji University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tongji University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.586"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref4","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16188"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01509"},{"key":"ref8","article-title":"Teaching large language models to self-debug","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chen"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3867"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3296823"},{"key":"ref13","first-page":"41714186","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","author":"Devlin","year":"2019"},{"key":"ref14","first-page":"70293","article-title":"Faith and fate: limits of transformers on compositionality","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Dziri"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2009.03.008"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01362"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.507"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0900"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00257"},{"key":"ref23","article-title":"Qwen2. 5-coder technical report","author":"Hui","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref24","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref27","article-title":"The curse of multi-modalities: Evaluating hallucinations of large multimodal models across language, visual, and audio","author":"Leng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref28","first-page":"9694","article-title":"Align before fuse: vision and language representation learning with momentum distillation","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","author":"Li"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612260"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00566"},{"key":"ref33","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445945"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref41","first-page":"72983","article-title":"Scaling open-vocabulary object detection","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Minderer"},{"key":"ref42","article-title":"DINOv2: Learning robust visual features without supervision","volume-title":"Transactions on Machine Learning Research","author":"Oquab","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10174-9"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.14"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_18"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2997"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28278"},{"key":"ref50","first-page":"44991","article-title":"Why larger language models do in-context learning differently?","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Shi"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref53","volume-title":"Rccf: Accelerating the redeployment of congestion control algorithms to provide near-optimal service for different flows","author":"Su"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01045"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01277"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.357"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1514"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_10"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681071"},{"key":"ref63","volume-title":"Can large language model agents simulate human trust behavior?","author":"Xie","year":"2024"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref66","article-title":"If lm is the wizard, then code is the wand: A survey on how code empowers large language models to serve as intelligent agents","volume-title":"ICLR 2024 Workshop on Large Language Model (LLM) Agents","author":"Yang","year":"2024"},{"key":"ref67","first-page":"24993","article-title":"Fine-grained visual prompting","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Yang"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2024.01.004"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00142"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01949"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2614"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_14"}],"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\/11444613.pdf?arnumber=11444613","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:18:29Z","timestamp":1777529909000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444613\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01898","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}