{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:54Z","timestamp":1777865454761,"version":"3.51.4"},"reference-count":71,"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 Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2037,U22B2051,U23A20383,U21A20472,62176222,62176223,62176226,62072386,62072387,62072389,62002305,62272401,62402015"],"award-info":[{"award-number":["U21B2037,U22B2051,U23A20383,U21A20472,62176222,62176223,62176226,62072386,62072387,62072389,62002305,62272401,62402015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M750100"],"award-info":[{"award-number":["2024M750100"]}],"id":[{"id":"10.13039\/501100002858","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\/iccv51701.2025.02260","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24380-24391","source":"Crossref","is-referenced-by-count":0,"title":["From Objects to Events: Unlocking Complex Visual Understanding in Object Detectors Via LLM-guided Symbolic Reasoning"],"prefix":"10.1109","author":[{"given":"Yuhui","family":"Zeng","sequence":"first","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoxiang","family":"Wu","sequence":"additional","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjie","family":"Nie","sequence":"additional","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangyao","family":"Chen","sequence":"additional","affiliation":[{"name":"Peking University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiawu","family":"Zheng","sequence":"additional","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunhang","family":"Shen","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Peng","sequence":"additional","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[{"name":"Peking University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2910017.2910624"},{"key":"ref2","first-page":"279","article-title":"Neuro-symbolic visual reasoning: Disentangling","volume-title":"International Conference on Machine Learning","author":"Amizadeh","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02570"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref9","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","volume-title":"arXiv preprint arXiv:2010.11929","author":"Dosovitskiy","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00129"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01315"},{"key":"ref12","article-title":"Neuralsymbolic computing: An effective methodology for principled integration of machine learning and reasoning","volume-title":"arXiv preprint arXiv:1905.06088","author":"d\u2019Avila Garcez","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01334"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3074805"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref17","article-title":"Connecting large language models with evolutionary algorithms yields powerful prompt optimizers","volume-title":"arXiv preprint arXiv:2309.08532","author":"Guo","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00902"},{"key":"ref19","article-title":"Llms as visual explainers: Advancing image classification with evolving visual descriptions","volume-title":"arXiv preprint arXiv:2311.11904","author":"Han","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3374383"},{"key":"ref21","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"arXiv preprint arXiv:2106.09685","author":"Hu","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01032"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2021.emnlp-main.243","article-title":"The power of scale for parameter-efficient prompt tuning","volume-title":"arXiv preprint arXiv:2104.08691","author":"Lester","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298925"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3162962"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0924"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02652"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP53242.2021.9675337"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01885"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3269780"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref37","article-title":"Dab-detr: Dynamic anchor boxes are better queries for detr","volume-title":"arXiv preprint arXiv:2201.12329","author":"Liu","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01169"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"ref42","article-title":"The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision","volume-title":"arXiv preprint arXiv:1904.12584","author":"Mao","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN57019.2023.10309311"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2020.3005751"},{"key":"ref46","article-title":"Dinov2: Learning robust visual features without supervision","volume-title":"arXiv preprint arXiv:2304.07193","author":"Oquab","year":"2023"},{"key":"ref47","article-title":"Plum: Prompt learning using metaheuristic","volume-title":"arXiv preprint arXiv:2311.08364","author":"Pan","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00197"},{"key":"ref49","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2023.emnlp-main.876","article-title":"Detgpt: Detect what you need via reasoning","volume-title":"arXiv preprint arXiv:2305.14167","author":"Pi","year":"2023"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref52","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume-title":"Advances in neural information processing systems","volume":"28","author":"Ren","year":"2015"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01513"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_16"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CAI54212.2023.00029"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01253"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00857"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-023-02750-5"},{"key":"ref59","article-title":"Eva-clip: Improved training techniques for clip at scale","volume-title":"arXiv preprint arXiv:2303.15389","author":"Sun","year":"2023"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25346"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2010.5655356"},{"key":"ref62","first-page":"98478","article-title":"Scene graph disentanglement and composition for generalizable complex image generation","volume-title":"Advances in Neural Information Processing Systems","volume":"37","author":"Wang","year":"2025"},{"key":"ref63","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2022.emnlp-main.559","article-title":"Gps: Genetic prompt search for efficient few-shot learning","volume-title":"arXiv preprint arXiv:2210.17041","author":"Xu","year":"2022"},{"key":"ref64","article-title":"Neural-symbolic vqa: Disentangling reasoning from vision and language understanding","volume-title":"Advances in neural information processing systems","volume":"31","author":"Yi","year":"2018"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_36"},{"key":"ref66","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","volume-title":"arXiv preprint arXiv:2203.03605","author":"Zhang","year":"2022"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00860"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01349"},{"key":"ref69","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","volume-title":"arXiv preprint arXiv:2010.04159","author":"Zhu","year":"2020"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01101"},{"key":"ref71","article-title":"Segment everything everywhere all at once","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Zou","year":"2024"}],"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\/11446181.pdf?arnumber=11446181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:34:45Z","timestamp":1777530885000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02260","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}