{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:19:44Z","timestamp":1778048384366,"version":"3.51.4"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00167","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1664-1673","source":"Crossref","is-referenced-by-count":0,"title":["FAST-EQA: Efficient Embodied Question Answering with Global and Local Region Relevancy"],"prefix":"10.1109","author":[{"given":"Haochen","family":"Zhang","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nirav","family":"Savaliya","sequence":"additional","affiliation":[{"name":"Honda Research Institute,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Faizan","family":"Siddiqui","sequence":"additional","affiliation":[{"name":"Honda Research Institute,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enna","family":"Sachdeva","sequence":"additional","affiliation":[{"name":"Honda Research Institute,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127706"},{"key":"ref2","article-title":"Videonavqa: Bridging the gap between visual and embodied question answering","volume-title":"Proceedings of the 30th British Machine Vision Conference (BMVC), 2019. Spotlight presentation at Visually Grounded Interaction Learning (ViGIL) Workshop, NeurIPS","author":"Cangea"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16180"},{"key":"ref4","article-title":"Object goal navigation using goal-oriented semantic exploration","author":"Chaplot","journal-title":"Advances in Neural Information Processing Systems (NeurIPS), 2020. Winner of the CVPR 2020 Habitat ObjectNav Challenge"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11247438"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610178"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref9","first-page":"53","article-title":"Neural modular control for embodied question answering","volume-title":"Proceedings of The 2nd Conference on Robot Learning (CoRL)","author":"Das"},{"key":"ref10","first-page":"8469","article-title":"Palm-e: An embodied multimodal language model","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML)","author":"Driess"},{"key":"ref11","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","author":"Ester","year":"1996","journal-title":"kdd"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00430"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref14","article-title":"Inner monologue: Embodied reasoning through planning with language models","volume-title":"Conference on Robot Learning (CoRL)","author":"Huang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.050"},{"key":"ref16","article-title":"Gpt-4o system card","author":"Hurst","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00850"},{"key":"ref18","article-title":"Prismatic vlms: Investigating the design space of visually-conditioned language models","volume-title":"Forty-first International Conference on Machine Learning","author":"Karamcheti"},{"key":"ref19","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"International conference on machine learning"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/02783649251369549"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"ref23","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01187"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.089"},{"key":"ref26","article-title":"Grapheqa: Using 3d semantic scene graphs for real-time embodied question answering","author":"Saxena","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02091"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.077"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00682"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CIRA.1997.613851"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01612"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610712"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00647"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.29"},{"key":"ref37","article-title":"Memory-centric embodied question answer","author":"Zhai","year":"2025"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.734"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492580.pdf?arnumber=11492580","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:58:27Z","timestamp":1778047107000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492580\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00167","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}