{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:32:51Z","timestamp":1763191971119,"version":"3.45.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228883","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Seeing is Believing? Enhancing Vision-Language Navigation using Visual Perturbations"],"prefix":"10.1109","author":[{"given":"Xuesong","family":"Zhang","sequence":"first","affiliation":[{"name":"Hefei University of Technology,The School of Computer Science and Information Engineering,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Li","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,The School of Computer Science and Information Engineering,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunbo","family":"Xu","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,The School of Computer Science and Information Engineering,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenzhen","family":"Hu","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,The School of Computer Science and Information Engineering,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richang","family":"Hong","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,The School of Computer Science and Information Engineering,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01868"},{"key":"ref3","first-page":"1001","article-title":"Selective Object Rearrangement in Clutter","volume-title":"Proceedings of Machine Learning Research","author":"Tang"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"article-title":"Agent Journey Beyond RGB: Unveiling Hybrid Semantic-Spatial Environmental Representations for Vision-and-Language Navigation[J]","year":"2024","author":"Zhang","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref9","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume":"30","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3407759"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01498"},{"key":"ref12","first-page":"20660","article-title":"Evolving graphical planner: Contextual global planning for vision-and-language navigation","volume":"33","author":"Deng","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01112"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref16","first-page":"2737","article-title":"Bevbert: Multi-modal map pre-training for language-guided navigation","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"An"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00284"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01544"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.727"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1655"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.inlg-main.19"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.438"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-024-01560-0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234243"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01502"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25223"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"author":"Wu","key":"ref30","article-title":"NoiseBoost: Alleviating Hallucination with Noise Perturbation for Multimodal Large Language Models"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01248"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/124"},{"article-title":"Does VLN Pretraining Work with Nonsensical or Irrelevant Instructions?","year":"2023","author":"Zhu","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/164"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25243"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Radford"},{"key":"ref40","article-title":"Frequency-Enhanced Data Augmentation for Vision-and-Language Navigation","volume":"36","author":"He","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00254"},{"key":"ref42","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings","author":"Ross"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228883.pdf?arnumber=11228883","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:28:40Z","timestamp":1763191720000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228883\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228883","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}