{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T21:15:46Z","timestamp":1765228546080,"version":"3.46.0"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2024A1515012791"],"award-info":[{"award-number":["2024A1515012791"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004000","name":"Guangzhou Municipal Science and Technology Program Key Projects","doi-asserted-by":"publisher","award":["2023B01J1001"],"award-info":[{"award-number":["2023B01J1001"]}],"id":[{"id":"10.13039\/501100004000","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62332019","62461160309","62302297"],"award-info":[{"award-number":["62332019","62461160309","62302297"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302297"],"award-info":[{"award-number":["62302297"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019005","name":"Young Elite Scientists Sponsorship Program by China Association for Science and Technology","doi-asserted-by":"publisher","award":["2022QNRC001"],"award-info":[{"award-number":["2022QNRC001"]}],"id":[{"id":"10.13039\/501100019005","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tcsvt.2025.3590456","type":"journal-article","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T17:47:31Z","timestamp":1752860851000},"page":"12492-12507","source":"Crossref","is-referenced-by-count":0,"title":["Robust 3D Visual Question Answering via Bias Learning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6861-9414","authenticated-orcid":false,"given":"Aihua","family":"Mao","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuyi","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1858-3358","authenticated-orcid":false,"given":"Ran","family":"Yi","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5774-1916","authenticated-orcid":false,"given":"Yong-Jin","family":"Liu","sequence":"additional","affiliation":[{"name":"BNRist, Department of Computer Science and Technology, MOE-Key Laboratory of Pervasive Computing, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296889"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3291379"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref9","first-page":"3","article-title":"Deep compositional question answering with neural module networks","volume-title":"Proc. CVPR","author":"Andreas"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref11","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":"ref12","first-page":"5105","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Qi"},{"key":"ref13","first-page":"1","article-title":"Move to understand a 3D scene: Bridging visual grounding and exploration for efficient and versatile embodied navigation","author":"Zhu","year":"2025","journal-title":"arXiv:2507.04047"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00593"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01057"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01547"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3382684"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3410041"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref22","first-page":"1","article-title":"SQA3D: Situated question answering in 3D scenes","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Ma"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01124"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.11"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3264524"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3216770"},{"key":"ref33","first-page":"1541","article-title":"Overcoming language priors in visual question answering with adversarial regularization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Ramakrishnan"},{"key":"ref34","first-page":"841","article-title":"RUBi: Reducing unimodal biases for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Cadene"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1418"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6776"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00268"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00161"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"ref40","article-title":"Patch-based image inpainting with generative adversarial networks","author":"Demir","year":"2018","journal-title":"arXiv:1803.07422"},{"key":"ref41","first-page":"7354","article-title":"Self-attention generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref42","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"Brock","year":"2018","journal-title":"arXiv:1809.11096"},{"key":"ref43","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014","journal-title":"arXiv:1411.1784"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126695"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3229081"},{"key":"ref46","article-title":"3D question answering","author":"Ye","year":"2021","journal-title":"arXiv:2112.08359"},{"key":"ref47","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28222"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.542"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/1118162.1118168"},{"key":"ref57","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref59","article-title":"Multi-CLIP: Contrastive vision-language pre-training for question answering tasks in 3D scenes","author":"Delitzas","year":"2023","journal-title":"arXiv:2306.02329"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3225327"},{"key":"ref61","first-page":"20482","article-title":"3D-LLM: Injecting the 3D world into large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hong"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_11"},{"key":"ref63","article-title":"Evaluating zero-shot GPT-4V performance on 3D visual question answering benchmarks","author":"Singh","year":"2024","journal-title":"arXiv:2405.18831"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11278843\/11084926.pdf?arnumber=11084926","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:42:52Z","timestamp":1765219372000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11084926\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":63,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3590456","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}