{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T20:17:03Z","timestamp":1774124223241,"version":"3.50.1"},"reference-count":71,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004147","name":"Tsinghua University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]},{"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\/501100004147","name":"Tsinghua University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801689","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"7750-7757","source":"Crossref","is-referenced-by-count":2,"title":["MG-VLN: Benchmarking Multi-Goal and Long-Horizon Vision-Language Navigation with Language Enhanced Memory Map"],"prefix":"10.1109","author":[{"given":"Junbo","family":"Zhang","sequence":"first","affiliation":[{"name":"Tsinghua University,Institute for Interdisciplinary Information Sciences"}]},{"given":"Kaisheng","family":"Ma","sequence":"additional","affiliation":[{"name":"Tsinghua University,Institute for Interdisciplinary Information Sciences"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.073"},{"key":"ref5","article-title":"OK- Robot: What Really Matters in Integrating Open-Knowledge Models for Robotics","author":"Liu","year":"2024","journal-title":"ArXiv"},{"key":"ref6","article-title":"SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Task Planning","volume-title":"Conference on Robot Learning","author":"Rana"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00063"},{"key":"ref8","first-page":"9700","article-title":"Multion: Benchmarking semantic map memory using multi-object navigation","volume":"33","author":"Wani","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982216"},{"key":"ref10","article-title":"Reduce, Reuse, Recycle: Modular Multi-Object Navigation","author":"Raychaudhuri","year":"2023","journal-title":"ArXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3263110"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01433"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref18","article-title":"Vision-and-Dialog Navigation","volume-title":"Conference on Robot Learning","author":"Thomason"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"ref20","first-page":"31","article-title":"Speaker-follower models for vision-and-language navigation","author":"Fried","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00689"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00168"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01498"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234243"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02223"},{"key":"ref30","article-title":"Learning Exploration Policies for Navigation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Chen"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01437-z"},{"key":"ref32","article-title":"Learning To Explore Using Active Neural SLAM","volume-title":"International Conference on Learning Representations (ICLR)","author":"Chaplot"},{"key":"ref33","first-page":"38149","article-title":"Weakly-supervised multi-granularity map learning for vision-and-language navigation","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","article-title":"Chasing Ghosts: Instruction Following as Bayesian State Tracking","author":"Anderson","year":"2019","journal-title":"Neural Information Processing Systems."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956561"},{"key":"ref36","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":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01112"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01432"},{"key":"ref40","article-title":"BEVBert: Multimodal Map Pre-training for Language-guided Navigation","author":"An","year":"2022","journal-title":"ArXiv"},{"key":"ref41","article-title":"GridMM:Grid Memory Map for Vision-and-Language Navigation","volume-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Wang"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01007"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00167"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01447"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01503"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01499"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01826"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01041"},{"key":"ref50","article-title":"PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation","author":"Li","year":"2023","journal-title":"ArXiv"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01040"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref53","article-title":"Language and Visual Entity Relationship Graph for Agent Navigation","author":"Hong","year":"2020","journal-title":"Advances in Neural Information Processing Systems."},{"key":"ref54","first-page":"15558","article-title":"K-lite: Learning transferable visual models with external knowledge","volume":"35","author":"Shen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00254"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref58","article-title":"Sgolam: Simultaneous goal localization and mapping for multi-object goal navigation","author":"Kim","year":"2021","journal-title":"ArXiv"},{"key":"ref59","first-page":"28670","article-title":"Learning active camera for multi-object navigation","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref60","article-title":"Multi-Object Navigation with dynamically learned neural implicit representations","author":"Marza","year":"2022","journal-title":"ArXiv"},{"key":"ref61","article-title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Ramakrishnan"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160259"},{"key":"ref63","article-title":"Semi-Supervised Classification with Graph Convolutional Networks","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kipf"},{"key":"ref64","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref65","article-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","author":"Li","year":"2023","journal-title":"ArXiv"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01744"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25453"},{"key":"ref68","first-page":"4171","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume-title":"Proceedings of NAACL-HLT","author":"Kenton"},{"key":"ref69","article-title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","author":"Lu","year":"2019","journal-title":"Neural Information Processing Systems."},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00696"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10801689.pdf?arnumber=10801689","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T06:58:00Z","timestamp":1735196280000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801689\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801689","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}