{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:37:30Z","timestamp":1757608650456,"version":"3.44.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":["62406267"],"award-info":[{"award-number":["62406267"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128851","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"9550-9557","source":"Crossref","is-referenced-by-count":1,"title":["SCA3D: Enhancing Cross-Modal 3D Retrieval via 3D Shape and Caption Paired Data Augmentation"],"prefix":"10.1109","author":[{"given":"Junlong","family":"Ren","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou),AI Thrust,Guangzhou,China"}]},{"given":"Hao","family":"Wu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou),AI Thrust,Guangzhou,China"}]},{"given":"Hui","family":"Xiong","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou),AI Thrust,Guangzhou,China"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou),AI Thrust,Guangzhou,China"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/ICRA48891.2023.10160969"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/CVPR52733.2024.01710"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/IROS58592.2024.10801352"},{"volume-title":"First Workshop on Vision-Language Models for Navigation and Manipulation at ICRA 2024","author":"Hu","article-title":"Look before you leap: Unveiling the power of gpt-4v in robotic vision-language planning","key":"ref4"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/cvpr52734.2025.00040"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/CVPR52733.2024.01868"},{"volume-title":"The Twelfth International Conference on Learning Representations","author":"BAKR","article-title":"Cot3dref: Chain-of-thoughts data-efficient 3d visual grounding","key":"ref7"},{"volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Man","article-title":"Lexicon3d: Probing visual foundation models for complex 3d scene understanding","key":"ref8"},{"key":"ref9","first-page":"104792","article-title":"Gvkf: Gaussian voxel kernel functions for highly efficient surface reconstruction in open scenes","volume-title":"Advances in Neural Information Processing Systems","volume":"37","author":"Song","year":"2025"},{"volume-title":"The Thirteenth International Conference on Learning Representations","author":"Cheng","article-title":"Graph-guided scene reconstruction from images with 3d gaussian splatting","key":"ref10"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ICRA55743.2025.11128286"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1007\/978-3-030-20893-6_7"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1609\/aaai.v33i01.3301126"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/WACV57701.2024.00571"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/CVPR52729.2023.00665"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICME57554.2024.10688095"},{"key":"ref17","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.29007\/1mjd"},{"key":"ref19","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref20","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":"ref21","first-page":"36978","article-title":"Open-vclip: Transforming clip to an open-vocabulary video model via interpo-lated weight optimization","volume-title":"International Conference on Machine Learning","author":"Weng"},{"key":"ref22","first-page":"2022","article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","volume-title":"NeurIPS Workshop Datacentric AI","author":"Schuhmann"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/iccv.2019.00272"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/CVPR.2009.5206848"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/CVPR52733.2024.01261"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/CVPR52729.2023.00261"},{"volume-title":"The Twelfth International Conference on Learning Representations","author":"Podell","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","key":"ref27"},{"key":"ref28","article-title":"Bloom: A 176b-parameter open-access multilingual language model","author":"Le Scao","year":"2022","journal-title":"arXiv e-prints"},{"key":"ref29","article-title":"Shapenet: An information-rich 3d model repository","author":"Chang","year":"2015","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"NIPS 2014 Workshop on Deep Learning, December 2014"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/cvpr52688.2022.00613"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1109\/CVPR52688.2022.00836"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/ICCV51070.2023.02025"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/CVPR.2019.00100"},{"key":"ref35","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Qi"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1145\/582415.582418"},{"volume-title":"Llava-next: Improved reasoning, ocr, and world knowledge","year":"2024","author":"Liu","key":"ref37"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.48550\/arXiv.1406.3269"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128851.pdf?arnumber=11128851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:09:05Z","timestamp":1756879745000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128851\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128851","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}