{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:19:24Z","timestamp":1774419564240,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888565","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Graph-aware Reasoning and Bidirectional Selection for Vision-Language Navigation"],"prefix":"10.1109","author":[{"given":"Dongming","family":"Zhou","sequence":"first","affiliation":[{"name":"National University of Defense Technology,School of Computer Science,Changsha,China,410003"}]},{"given":"Jinsheng","family":"Deng","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Advanced Interdisciplinary Studies,Changsha,China,410073"}]},{"given":"Zhengbin","family":"Pang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,School of Computer Science,Changsha,China,410003"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"Guangxi University,School of Computer and Electronic Information,Nanning,China,530004"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01040"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110511"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00997"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01004"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.529"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3380244"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3362058"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3234766"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tec.2023.3306804"},{"key":"ref12","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888514"},{"key":"ref14","article-title":"Structured state space models for in-context reinforcement learning","volume":"36","author":"Lu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","article-title":"Transformers are ssms: Generalized models and efficient algorithms through structured state space duality","author":"Dao","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672044"},{"key":"ref17","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00254"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01544"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01498"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107487"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_13"},{"key":"ref24","article-title":"Theoretical foundations of deep selective state-space models","author":"Cirone","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01411"},{"key":"ref26","first-page":"492","article-title":"Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Conference on robot learning","author":"Shah"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3386695"},{"key":"ref28","article-title":"Learning transformer programs","volume":"36","author":"Friedman","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00548"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3395633"},{"key":"ref31","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33131"},{"key":"ref33","article-title":"Text-controlled motion mamba: Text-instructed temporal grounding of human motion","author":"Wang","year":"2024"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref35","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01305"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888565.pdf?arnumber=10888565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:32Z","timestamp":1774416212000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888565\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888565","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}