{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:40:27Z","timestamp":1732668027442,"version":"3.28.2"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shenzhen General Program","award":["JCYJ20220530143600001"]},{"name":"Basic Research Project","award":["HZQB-KCZYZ-2021067"]},{"name":"Shenzhen-Hong Kong Joint Funding","award":["SGDX20211123112401002"]},{"name":"Shenzhen Outstanding Talents Training Fund, by Guangdong Research Project","award":["2017ZT07X152","2019CX01X104"]},{"name":"Guangdong Provincial Key Laboratory of Future Networks of Intelligence","award":["2022B1212010001"]},{"DOI":"10.13039\/100022813","name":"Chinese University of Hong Kong, Shenzhen","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100022813","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61931024","81922046"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSFC-Youth","award":["62203296"]},{"name":"Tencent Open Fund"},{"name":"ITSO at CUHKSZ"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tvcg.2023.3340679","type":"journal-article","created":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T19:16:34Z","timestamp":1702062994000},"page":"7473-7485","source":"Crossref","is-referenced-by-count":2,"title":["Comprehensive Visual Question Answering on Point Clouds through Compositional Scene Manipulation"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"http:\/\/orcid.org\/0000-0001-5218-6693","authenticated-orcid":false,"given":"Xu","family":"Yan","sequence":"first","affiliation":[{"name":"Future Network of Intelligence Institute, School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-3100-1252","authenticated-orcid":false,"given":"Zhihao","family":"Yuan","sequence":"additional","affiliation":[{"name":"Future Network of Intelligence Institute, School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China"}]},{"ORCID":"http:\/\/orcid.org\/0009-0001-5422-6115","authenticated-orcid":false,"given":"Yuhao","family":"Du","sequence":"additional","affiliation":[{"name":"Future Network of Intelligence Institute, School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-9128-1167","authenticated-orcid":false,"given":"Yinghong","family":"Liao","sequence":"additional","affiliation":[{"name":"Future Network of Intelligence Institute, School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-8041-1245","authenticated-orcid":false,"given":"Yao","family":"Guo","sequence":"additional","affiliation":[{"name":"Institute of Medical Robotics, Shanghai Jiao Tong Univerisity, Shanghai, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-9205-1881","authenticated-orcid":false,"given":"Shuguang","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, The Future Network of Intelligence Institute, The Chinese University of Hong Kong, Shenzhen, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-7669-2686","authenticated-orcid":false,"given":"Zhen","family":"Li","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, The Future Network of Intelligence Institute, The Chinese University of Hong Kong, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref5","first-page":"5099","article-title":"PointNet: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Qi"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00837"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00958"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00743"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref15","first-page":"839","article-title":"RUBi: Reducing unimodal biases for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cadene"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","year":"2019","author":"Raffel","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00500"},{"article-title":"Threedworld: A platform for interactive multi-modal physical simulation","year":"2020","author":"Gan","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref24","first-page":"361","article-title":"Multimodal residual learning for visual QA","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"author":"Kim","key":"ref28","article-title":"Hadamard product for low-rank bilinear pooling"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00936"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"article-title":"Learning by abstraction: The neural state machine","year":"2019","author":"Hudson","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref35","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00838"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01138"},{"key":"ref43","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1150"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00775"},{"key":"ref46","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Qi"},{"key":"ref47","first-page":"100","article-title":"Text2Shape: Generating shapes from natural language by learning joint embeddings","volume-title":"Proc. Asian Conf. Comput. Vis.","author":"Chen"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00903"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16253"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00181"},{"key":"ref51","first-page":"1046","article-title":"Languagerefer: Spatial-language model for 3D visual grounding","volume-title":"Proc. 5th Annu. Conf. Robot Learn.","author":"Roh"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"article-title":"D3Net: A speaker-listener architecture for semi-supervised dense captioning and visual grounding in RGB-D scans","year":"2021","author":"Chen","key":"ref54"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413977"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.09.001"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"ref59","first-page":"20522","article-title":"Language conditioned spatial relation reasoning for 3D object grounding","volume":"35","author":"Chen","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/2945\/10737249\/10349943.pdf?arnumber=10349943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:27:43Z","timestamp":1732667263000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10349943\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":59,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2023.3340679","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"type":"print","value":"1077-2626"},{"type":"electronic","value":"1941-0506"},{"type":"electronic","value":"2160-9306"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}