{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:49Z","timestamp":1777865329918,"version":"3.51.4"},"reference-count":63,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02232","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24078-24089","source":"Crossref","is-referenced-by-count":2,"title":["Naver: a Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic Reasoning"],"prefix":"10.1109","author":[{"given":"Zhixi","family":"Cai","sequence":"first","affiliation":[{"name":"Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fucai","family":"Ke","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simindokht","family":"Jahangard","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maria","family":"Garcia de la Banda","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reza","family":"Haffari","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter J.","family":"Stuckey","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hamid","family":"Rezatofighi","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.586"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","first-page":"279","article-title":"Neuro-Symbolic Visual Reasoning: Disentangling","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Amizadeh","year":"2020"},{"key":"ref4","article-title":"Qwen2.5-VL Technical Report","author":"Bai","year":"2025"},{"key":"ref5","article-title":"Constitutional AI: Harmlessness from AI Feedback","author":"Bai","year":"2022"},{"key":"ref6","first-page":"1877","article-title":"Language Models are Few-Shot Learners","volume-title":"Advances in Neural Information Processing Systems","author":"Brown","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.218"},{"key":"ref9","article-title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"issue":"240","key":"ref12","first-page":"1","article-title":"PaLM: Scaling Language Modeling with Pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3867"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.52202\/075280-2142","article-title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","author":"Dai","year":"2023"},{"key":"ref15","first-page":"2468","article-title":"ProbLog: a probabilistic prolog and its application in link discovery","volume-title":"Proceedings of the 20th international joint conference on Artifical intelligence","author":"De Raedt","year":"2007"},{"key":"ref16","article-title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","year":"2025"},{"key":"ref17","first-page":"16321","article-title":"Referring Segmentation","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Ding","year":"2021"},{"key":"ref18","article-title":"The Llama 3 Herd of Models","author":"Dubey","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01269"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_8"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.00371","article-title":"Segment Anything","author":"Kirillov","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref25","article-title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","author":"Li","year":"2023"},{"key":"ref26","article-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","volume-title":"International Conference on Machine Learning","author":"Li","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3591280"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref30","article-title":"Improved Baselines with Visual Instruction Tuning","author":"Liu","year":"2023"},{"key":"ref31","article-title":"Visual Instruction Tuning","author":"Liu","year":"2023"},{"key":"ref32","article-title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","author":"Liu","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1882"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3191"},{"key":"ref36","article-title":"GPT-4o System Card","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref38","article-title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","volume-title":"Advances in Neural Information Processing Systems","author":"Paszke","year":"2019"},{"key":"ref39","article-title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","author":"Peng","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02561"},{"issue":"8","key":"ref41","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref43","article-title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","author":"Shen","year":"2023"},{"key":"ref44","article-title":"Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers","author":"Stani\u0107","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.01092","article-title":"ViperGPT: Visual Inference via Python Execution for Reasoning","author":"Sur\u00eds","year":"2023"},{"key":"ref46","article-title":"Gemma 2: Improving Open Language Models at a Practical Size","year":"2024"},{"key":"ref47","article-title":"Will we run out of data? Limits of LLM scaling based on human generated data","author":"Villalobos","year":"2024"},{"key":"ref48","article-title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","author":"Wang","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref50","article-title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","author":"Wu","year":"2023"},{"key":"ref51","article-title":"NExT-GPT: Any-to-Any Multimodal LLM","author":"Wu","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref54","article-title":"xGen-MM(BLIP-3): A Family of Open Large Multimodal Models","author":"Xue","year":"2024"},{"key":"ref55","article-title":"Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V","author":"Yang","year":"2023"},{"key":"ref56","article-title":"Depth Anything V2","author":"Yang","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00427"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.755"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref61","first-page":"25994","article-title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","volume-title":"Proceedings of the 39th International Conference on Machine Learning","author":"Zeng","year":"2022"},{"key":"ref62","article-title":"PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model","author":"Zhang","year":"2024"},{"key":"ref63","article-title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","author":"Zhu","year":"2023"}],"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\/11445900.pdf?arnumber=11445900","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:16:02Z","timestamp":1777529762000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445900\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02232","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}