{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:05:08Z","timestamp":1784268308446,"version":"3.55.0"},"reference-count":68,"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\/iccv51701.2025.00839","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8973-8983","source":"Crossref","is-referenced-by-count":1,"title":["Kestrel: 3D Multimodal LLM for Part-Aware Grounded Description"],"prefix":"10.1109","author":[{"given":"Mahmoud","family":"Ahmed","sequence":"first","affiliation":[{"name":"King Abdullah University of Science and Technology (Kaust)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjie","family":"Fei","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology (Kaust)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Ding","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology (Kaust)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eslam Mohamed","family":"Bakr","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology (Kaust)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed","family":"Elhoseiny","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology (Kaust)"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref4","author":"Bai","year":"2023","journal-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond"},{"key":"ref5","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref7","article-title":"Shapenet: An information-rich 3d model repository","author":"Chang","year":"2015","journal-title":"arXiv preprint"},{"key":"ref8","first-page":"202","article-title":"Scanrefer: 3d object localization in rgb-d scans using natural language","volume-title":"European conference on Computer Vision","author":"Zhenyu Chen"},{"key":"ref9","article-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Shikra: Unleashing multi-modal llm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Pix2seq: A language modeling framework for object detection","author":"Chen","year":"2021","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2272"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref14","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90 chatgpt quality"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_35"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref22","article-title":"Point-bind & point-llm: Aligning point cloud with multi-modality for 3d understanding, generation, and instruction following","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_20"},{"key":"ref24","article-title":"3d-llm: Injecting the 3 d world into large language models","author":"Hong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_27"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref28","article-title":"Lisa: Reasoning segmentation via large language model","author":"Lai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref30","article-title":"Covlm: Composing visual entities and relationships in large language models via communicative decoding","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","first-page":"19730","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"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_7"},{"key":"ref33","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref34","article-title":"Improved baselines with visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Improved baselines with visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02082"},{"key":"ref38","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3291"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00100"},{"key":"ref41","volume-title":"OpenAI Research","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref44","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.02413"},{"key":"ref46","author":"Qi","year":"2023","journal-title":"Gpt4point: A unified framework for point-language understanding and generation"},{"key":"ref47","article-title":"Shapellm: Universal 3d object understanding for embodied interaction","author":"Qi","year":"2024","journal-title":"arXiv preprint"},{"issue":"8","key":"ref48","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref49","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01236"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref54","article-title":"3dcompat ++: An improved large-scale 3d vision dataset for compositional recognition","author":"Slim","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Unig3d: A unified 3d object generation dataset","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681257"},{"key":"ref57","article-title":"Stanford alpaca: An instruction-following llama model","author":"Taori","year":"2023"},{"key":"ref58","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"key":"ref61","article-title":"Visionllm: Large language model is also an openended decoder for vision-centric tasks","volume":"36","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"ref65","article-title":"Ulip: Learning unified representation of language, image and point cloud for 3d understanding","author":"Xue","year":"2022","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02558"},{"key":"ref67","article-title":"Uni3d: Exploring unified 3d representation at scale","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhou"},{"key":"ref68","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2024","journal-title":"ICLR"}],"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\/11443529.pdf?arnumber=11443529","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:14:11Z","timestamp":1777612451000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443529\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00839","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}