{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T06:21:09Z","timestamp":1763533269835,"version":"3.45.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:00Z","timestamp":1759881600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:00Z","timestamp":1759881600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,8]]},"DOI":"10.1109\/ismar-adjunct68609.2025.00027","type":"proceedings-article","created":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T18:42:51Z","timestamp":1763491371000},"page":"107-112","source":"Crossref","is-referenced-by-count":0,"title":["Few-Shot Action Scene Graph Generation from Video via Multimodal Language Models for Structuring Spatial Experience"],"prefix":"10.1109","author":[{"given":"Jinseok","family":"Hong","sequence":"first","affiliation":[{"name":"KAIST UVR Lab"}]},{"given":"Hyerim","family":"Park","sequence":"additional","affiliation":[{"name":"KAIST PMRC"}]},{"given":"Heejeong","family":"Ko","sequence":"additional","affiliation":[{"name":"KAIST UVR Lab"}]},{"given":"Woontack","family":"Woo","sequence":"additional","affiliation":[{"name":"UVR Lab,KAIST KI-ITC ARRC"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00025"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.11113\/humentech.v1n2.27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3137605"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3548845"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3327284"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00332"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2024.06.007"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging11030091"},{"article-title":"Fine-grained vision-language modeling for multimodal training assistants in augmented reality","year":"2025","author":"Huang","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02674"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/vr58804.2024.00099"},{"article-title":"Vr-gpt: Visual language model for intelligent virtual reality applications","year":"2024","author":"Konenkov","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687607"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275035"},{"article-title":"Self-refine: Iterative refinement with self-feedback","year":"2023","author":"Madaan","key":"ref15"},{"year":"2024","key":"ref16","article-title":"Gpt-4o system card"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00662"},{"key":"ref18","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.34133\/cbsystems.0100"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01762"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR62088.2024.00091"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00965"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530135"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183112"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00633"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322941"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.147"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3602216"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR-Adjunct64951.2024.00078"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3549147"},{"article-title":"Long video understanding with learnable retrieval in video-language models","year":"2025","author":"Xu","key":"ref32"},{"key":"ref33","article-title":"Llm meets scene graph: Can large language models understand and generate scene graphs?","author":"Yang","year":"2025","journal-title":"a benchmark and empirical study"},{"article-title":"Commonscenes: generating commonsense 3d indoor scenes with scene graph diffusion","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems, NIPS \u201923","author":"Zhai","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_10"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01784"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111992"},{"article-title":"Video instruction tuning with synthetic data","year":"2024","author":"Zhang","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00356"}],"event":{"name":"2025 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)","start":{"date-parts":[[2025,10,8]]},"location":"Daejeon, Korea, Republic of","end":{"date-parts":[[2025,10,12]]}},"container-title":["2025 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11236072\/11236073\/11236195.pdf?arnumber=11236195","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T06:19:26Z","timestamp":1763533166000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11236195\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,8]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ismar-adjunct68609.2025.00027","relation":{},"subject":[],"published":{"date-parts":[[2025,10,8]]}}}