{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:45:09Z","timestamp":1770846309585,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11342447","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"2103-2108","source":"Crossref","is-referenced-by-count":0,"title":["Iterative Residual Cross-Attention Mechanism: An Integrated Approach for Audio-Visual Navigation Tasks"],"prefix":"10.1109","author":[{"given":"Hailong","family":"Zhang","sequence":"first","affiliation":[{"name":"Xinjiang University,Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center, School of Computer Science and Technology,Urumqi,China,830017"}]},{"given":"Yinfeng","family":"Yu","sequence":"additional","affiliation":[{"name":"Xinjiang University,Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center, School of Computer Science and Technology,Urumqi,China,830017"}]},{"given":"Liejun","family":"Wang","sequence":"additional","affiliation":[{"name":"Xinjiang University,Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center, School of Computer Science and Technology,Urumqi,China,830017"}]},{"given":"Fuchun","family":"Sun","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100091"}]},{"given":"Wendong","family":"Zheng","sequence":"additional","affiliation":[{"name":"Tianjin University of Technology,School of Electrical Engineering and Automation,Tianjin,China,300382"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref2","article-title":"The replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01289"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981090"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i22.34526"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.638"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561936"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_2"},{"key":"ref10","article-title":"Learning to set waypoints for audio-visual navigation","volume-title":"ICLR","author":"Chen"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01009"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/38"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01579"},{"key":"ref14","article-title":"Sound adversarial audio-visual navigation","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022","author":"Yu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","first-page":"46","article-title":"Pay self-attention to audio-visual navigation","volume-title":"33rd British Machine Vision Conference 2022, BMVC 2022, London, UK, November 21-24, 2022","author":"Yu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197008"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref20","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 814, 2019, Vancouver, BC, Canada","author":"Paszke"},{"key":"ref21","first-page":"8896","article-title":"Soundspaces 2.0: A simulation platform for visual-acoustic learning","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11342447.pdf?arnumber=11342447","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:53:08Z","timestamp":1770843188000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342447\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11342447","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}