{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T11:10:27Z","timestamp":1737025827787,"version":"3.33.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003696","name":"Electronics and Telecommunications Research Institute (ETRI)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003696","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,16]]},"DOI":"10.1109\/ictc62082.2024.10827718","type":"proceedings-article","created":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T19:40:10Z","timestamp":1736883610000},"page":"215-217","source":"Crossref","is-referenced-by-count":0,"title":["Object-Centric Scene Representation Learning via SAM"],"prefix":"10.1109","author":[{"given":"Donghun","family":"Lee","sequence":"first","affiliation":[{"name":"Electronics and Telecommunications Research Institute,Autonomous IoT Research Section,Daejeon,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samyeul","family":"Noh","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute,Autonomous IoT Research Section,Daejeon,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ingook","family":"Jang","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute,Autonomous IoT Research Section,Daejeon,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seonghyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute,Autonomous IoT Research Section,Daejeon,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soonyoung","family":"Song","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute,Autonomous IoT Research Section,Daejeon,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heechul","family":"Bae","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute,Autonomous IoT Research Section,Daejeon,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"7","key":"ref1","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1145\/3448250","article-title":"Deep learning for ai","volume":"64","author":"Yoshua","year":"2021","journal-title":"Communications of the ACM"},{"key":"ref2","first-page":"163","article-title":"Ood-cv: a benchmark for robustness to out-of-distribution shifts of individual nuisances in natural images","volume-title":"European Conference on Computer Vision","author":"Bingchen"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.4218\/etrij.2023-0129"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.4218\/etrij.2022-0120"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.4218\/etrij.2022-0209"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.4218\/etrij.2023-0136"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.4218\/etrij.2021-0397"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3286184"},{"key":"ref9","article-title":"Neural-symbolic vqa: Disentangling reasoning from vision and language under-standing","volume":"31","author":"Kexin","year":"2018","journal-title":"Advances in neural information processing systems"},{"article-title":"The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision","volume-title":"International Conference on Learning Representations","author":"Jiayuan","key":"ref10"},{"key":"ref11","first-page":"1","article-title":"Neurosymbolic ai: The 3 rd wave","author":"Artur","year":"2023","journal-title":"Artificial Intelligence Review"},{"key":"ref12","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Tom","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"On the opportunities and risks of foundation models","author":"Rishi","year":"2021","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Segment anything","author":"Alexander","year":"2023","journal-title":"arXiv"},{"key":"ref15","article-title":"Segment anything in medical images","author":"Jun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Segment and track anything","author":"Yangming","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Caption anything: Interactive image description with diverse multimodal controls","author":"Teng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","first-page":"11525","article-title":"Objectcentric learning with slot attention","volume":"33","author":"Francesco","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","article-title":"Generalization and robustness implications in object-centric learning","author":"Dittadi","year":"2021","journal-title":"arXiv preprint"},{"key":"ref21","first-page":"702","article-title":"Shapestacks: Learning vision -based physical intuition for generalised object stacking","volume-title":"Proceedings of the european conference on computer vision (eccv)","author":"Dittadi"},{"volume-title":"Multi-object datasets","year":"2019","author":"Kabra","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/BF01908075"},{"article-title":"Stochastic Video Prediction with Perceptual Loss","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Donghun","key":"ref24"},{"key":"ref25","first-page":"1004","article-title":"Avoiding collaborative paradox in multi-agent reinforcement learning","volume":"43.6","author":"Hyunseok","year":"2021","journal-title":"ETRI Journal"},{"article-title":"Generative scene graph networks","volume-title":"International Conference on Learning Representations","author":"Fei","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3014922"}],"event":{"name":"2024 15th International Conference on Information and Communication Technology Convergence (ICTC)","start":{"date-parts":[[2024,10,16]]},"location":"Jeju Island, Korea, Republic of","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 15th International Conference on Information and Communication Technology Convergence (ICTC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10826571\/10826594\/10827718.pdf?arnumber=10827718","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T06:37:52Z","timestamp":1736923072000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10827718\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/ictc62082.2024.10827718","relation":{},"subject":[],"published":{"date-parts":[[2024,10,16]]}}}