{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:29Z","timestamp":1777865369463,"version":"3.51.4"},"reference-count":71,"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"}],"funder":[{"DOI":"10.13039\/501100006465","name":"Korea Creative Content Agency","doi-asserted-by":"publisher","award":["RS-2024-00398413"],"award-info":[{"award-number":["RS-2024-00398413"]}],"id":[{"id":"10.13039\/501100006465","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02036","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21927-21937","source":"Crossref","is-referenced-by-count":0,"title":["Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURA"],"prefix":"10.1109","author":[{"given":"Zhixuan","family":"Li","sequence":"first","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyunse","family":"Yoon","sequence":"additional","affiliation":[{"name":"Yonsei University,Department of Electrical and Electronic Engineering,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanghoon","family":"Lee","sequence":"additional","affiliation":[{"name":"Yonsei University,Department of Electrical and Electronic Engineering,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weisi","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXi"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811646"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25056-9_40"},{"key":"ref4","first-page":"213","article-title":"End-toend object detection with transformer","volume-title":"Proceedings of the IEEE\/CVF European Conference on Computer Vision","author":"Carion","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811367"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25104"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00547"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00643"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00146"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00122"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref13","article-title":"LoRA: Low-rank adaptation of large language model","volume-title":"International Conference on Learning Representations","author":"Hu","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00322"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3301213"},{"key":"ref16","first-page":"1","article-title":"S2-csnet: Scale-aware scalable sampling network for image compressive sensin","author":"Hui","year":"2024","journal-title":"ACM Multimedia"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535114"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01741"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01000"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0362"},{"key":"ref21","article-title":"Multimodal 3d reasoning segmentation with complex scene","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Exploring 3d activity reasoning and planning: From implicit human intentions to route-aware plannin","author":"Jiang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Llms meet vlms: Boost open vocabulary ob-ject detection with fine-grained descriptor","volume-title":"International Conference on Learning Representations","author":"Jin","year":"2024"},{"key":"ref24","article-title":"Segment anything in high qualit","author":"Ke","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","first-page":"4015","article-title":"Segment anythin","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Kirillov","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref27","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language model","volume-title":"International Conference on Machine Learning","author":"Li","year":"2023"},{"key":"ref28","first-page":"677","article-title":"Amodal instance segmentatio","volume-title":"Proceedings of the IEEE\/CVF European Conference on Computer Vision","author":"Li","year":"2016"},{"key":"ref29","first-page":"165","article-title":"2D amodal instance segmentation guided by 3D shape prio","volume-title":"Proceedings of the IEEE\/CVF European Conference on Computer Vision","author":"Li","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096534"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3318075"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02148"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref34","first-page":"16246","article-title":"Variational amodal object completio","volume":"33","author":"Ling","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref36","article-title":"Visual instruction tunin","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28176"},{"key":"ref38","article-title":"PLUG: Revisiting amodal segmentation with foundation model and hierarchical focu","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Decoupled weight decay regularizatio","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680930"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01719"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02035"},{"key":"ref43","first-page":"7396","article-title":"A weakly supervised amodal segmenter with boundary uncertainty estimatio","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Nguyen","year":"2021"},{"key":"ref44","article-title":"Pytorch: An imperative style, high-performance deep learning librar","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref45","first-page":"3014","article-title":"Amodal instance segmentation with KINS datase","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Qi","year":"2019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00914"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3460414"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317714"},{"key":"ref51","first-page":"240","article-title":"Generalised dice overlap as a deep learning loss function for highly unbalanced segmentation","volume-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: Third International Workshop, DLMIA 2017, and 7th International Workshop, ML-CDS 2017, Held in Conjunction with MICCAI 2017, Qu\u00e9bec City, QC, Canada, September 14, Proceedings 3","author":"Carole","year":"2017"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00128"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.5040\/9781501365072.09396"},{"key":"ref54","article-title":"LLaMA 2: Open foundation and fine-tuned chat model","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00183"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16407"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01525"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00869"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_6"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ISIMP.2004.1434171"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02645"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00384"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01081"},{"key":"ref65","article-title":"LLaMA- Adapter: Efficient fine-tuning of language models with zero-init attentio","volume-title":"International Conference on Learning Representations","author":"Zhang","year":"2024"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445882"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2291"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350911"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_5"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01517-0"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.320"}],"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\/11444387.pdf?arnumber=11444387","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:21:26Z","timestamp":1777530086000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444387\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02036","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}