{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:21:42Z","timestamp":1778048502264,"version":"3.51.4"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00745","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"7719-7729","source":"Crossref","is-referenced-by-count":0,"title":["HOLO: Holistic Lightweight Optimization for Scene Understanding with Auto-Annotation and Multimodal Learning"],"prefix":"10.1109","author":[{"given":"Xiaoyun","family":"Hu","sequence":"first","affiliation":[{"name":"Tongji University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohan","family":"Yan","sequence":"additional","affiliation":[{"name":"Tongji University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tongji University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Wei","sequence":"additional","affiliation":[{"name":"Tongji University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhicheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Tongji University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"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":"65","article-title":"Meteor: an automatic metric for mt evaluation with high levels of correlation with human judgments","volume-title":"Proceedings of ACL-WMT","author":"Banerjee"},{"key":"ref6","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/2969830.2969856"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref10","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","author":"Chen","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00357"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00067-6"},{"key":"ref19","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"ref21","article-title":"Point-bind & point-llm: Aligning point cloud with multi-modality for 3d understanding, generation, and instruction following","author":"Guo","year":"2023"},{"issue":"2","key":"ref22","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref23","article-title":"Chat-scene: Bridging 3d scene and large language models with object identifiers","author":"Huang","year":"2023"},{"key":"ref24","article-title":"An embodied generalist agent in 3d world","author":"Huang","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"issue":"3","key":"ref26","first-page":"3","article-title":"Phi-2: The surprising power of small language models","volume":"1","author":"Javaheripi","year":"2023","journal-title":"Microsoft Research Blog"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01374"},{"key":"ref28","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":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72120-5_8"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32524"},{"key":"ref31","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref32","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024"},{"key":"ref33","article-title":"Uni3d-llm: Unifying point cloud perception, generation and editing with large language models","author":"Liu","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00645"},{"key":"ref37","article-title":"Sqa3d: Situated question answering in 3d scenes","author":"Ma","year":"2022"},{"key":"ref38","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics","author":"Papineni"},{"key":"ref39","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_13"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02495"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127274"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681257"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.28"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref48","article-title":"Enhancing the reasoning ability of multimodal large language models via mixed preference optimization","author":"Wang","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-8508-7_11"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127468"},{"key":"ref53","article-title":"Deco: Decoupling token compression from semantic abstraction in multimodal large language models","author":"Yao","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01397"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00356"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492326.pdf?arnumber=11492326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:07:11Z","timestamp":1778047631000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492326\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00745","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}