{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:21:25Z","timestamp":1777890085672,"version":"3.51.4"},"reference-count":82,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00660","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7025-7036","source":"Crossref","is-referenced-by-count":0,"title":["Embodied Navigation with Auxiliary Task of Action Description Prediction"],"prefix":"10.1109","author":[{"given":"Haru","family":"Kondoh","sequence":"first","affiliation":[{"name":"Institute of Science Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Asako","family":"Kanezaki","sequence":"additional","affiliation":[{"name":"Institute of Science Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2737","article-title":"Bevbert: Multimodal map pre-training for language-guided navigation","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"An","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3386695"},{"key":"ref3","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"ref6","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968488"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"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":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Chen","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01526"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01009"},{"key":"ref13","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS)","author":"Chen","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref15","article-title":"Videollama 2: Advancing spatial-temporal modeling and audio understanding in videollms","author":"Cheng","year":"2024","journal-title":"arXiv"},{"key":"ref16","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"NeurIPS Workshop on Deep Learning","author":"Chung","year":"2014"},{"key":"ref17","article-title":"Distilling deep reinforcement learning policies in soft decision trees","volume-title":"Proceedings of International Joint Conference on Artificial Intelligence","author":"Coppens","year":"2019"},{"key":"ref18","first-page":"14961","article-title":"See, hear, explore: Curiosity via audio-visual association","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS)","author":"Dean","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref20","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"North American Chapter of the Association for Computational Linguistics","author":"Devlin","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/MIPRO.2018.8400040"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278736"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3301275.3302316"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1082"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00063"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2594473.2594475"},{"key":"ref27","article-title":"Speaker-follower models for vision-and-language navigation","author":"Fried","year":"2018","journal-title":"NeurIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197008"},{"key":"ref29","first-page":"533","article-title":"Using large language models for interpreting autonomous robots behaviors","volume-title":"Hybrid Artificial Intelligent Systems","author":"Miguel","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2021.107052"},{"key":"ref31","article-title":"Mlanet: Multi-level attention network with sub-instruction for continuous vision-and-language navigation","author":"He","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25951"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref34","article-title":"The curious case of neural text degeneration","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Holtzman","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref36","first-page":"105","article-title":"Audio visual language maps for robot navigation","volume-title":"International Symposium on Experimental Robotics","author":"Huang","year":"2023"},{"key":"ref37","article-title":"Explainable reinforcement learning via reward decomposition","volume-title":"IJCAI\/ECAI Workshop on explainable artificial intelligence","author":"Juozapaitis","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01041"},{"key":"ref39","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Kipf","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref41","article-title":"Social attention for autonomous decision-making in dense traffic","author":"Leurent","year":"2019","journal-title":"ArXiv, abs\/1911.12250"},{"key":"ref42","article-title":"Navcot: Boosting 11m-based vision-andlanguage navigation via learning disentangled reasoning","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-10928-8_25"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28167"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00511"},{"key":"ref46","article-title":"Selfmonitoring navigation agent via auxiliary progress estimation","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Ma","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2343"},{"key":"ref48","author":"Majumder","journal-title":"Semantic audio-visual navigation through distractor silencing"},{"key":"ref49","article-title":"Towards interpretable reinforcement learning using attention augmented agents","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS)","author":"Mott","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.60"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0451"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref54","article-title":"Habitat-matterport 3d dataset (HM3d): 1000 largescale 3d environments for embodied AI","volume-title":"Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","author":"Ramakrishnan","year":"2021"},{"key":"ref55","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to noregret online learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics","author":"Ross","year":"2011"},{"key":"ref56","article-title":"Conservative q -improvement: Reinforcement learning for an interpretable decision-tree policy","author":"Aaron","year":"2019","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0048-x"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref59","first-page":"492","article-title":"Lmnav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Proceedings of Conference on Robot Learning (CoRL)","author":"Shah","year":"2023"},{"key":"ref60","article-title":"Hierarchical and interpretable skill acquisition in multi-task reinforcement learning","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Shu","year":"2018"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05963-2"},{"key":"ref62","first-page":"17493","article-title":"Generating high-quality explanations for navigation in partially-revealed environments","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS)","author":"Stein","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref64","article-title":"Knowledge-driven scene priors for semantic audio-visual embodied navigation","author":"Tatiya","year":"2022","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Attention is all you need","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS)","author":"Vaswani","year":"2017"},{"key":"ref66","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3272518"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01499"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref70","article-title":"Dd-ppo: Learning near-perfect pointgoal navigators from 2.5 billion frames","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Wijmans","year":"2019"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01538"},{"key":"ref74","article-title":"ReAct: Synergizing reasoning and acting in language models","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Yao","year":"2023"},{"key":"ref75","article-title":"Pay self-attention to audio-visual navigation","volume-title":"Proceedings of British Machine Vision Conference (BMVC)","author":"Yu","year":"2022"},{"key":"ref76","article-title":"Sound adversarial audiovisual navigation","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Yu","year":"2022"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01293"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_15"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.229"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444177.pdf?arnumber=11444177","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:11Z","timestamp":1777613351000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444177\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00660","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}