{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:13:50Z","timestamp":1790273630938,"version":"4.1.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T00:00:00Z","timestamp":1670025600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T00:00:00Z","timestamp":1670025600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1007\/s11263-022-01721-6","type":"journal-article","created":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T04:27:34Z","timestamp":1670041654000},"page":"607-625","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Active Perception for Visual-Language Navigation"],"prefix":"10.1007","volume":"131","author":[{"given":"Hanqing","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenguan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steven C. H.","family":"Hoi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4109-8353","authenticated-orcid":false,"given":"Jianbing","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luc Van","family":"Gool","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,12,3]]},"reference":[{"key":"1721_CR1","unstructured":"Anderson, P., Chang, A., Chaplot, D.S., Dosovitskiy, A., Gupta, S., Koltun, V., Kosecka, J., Malik, J., Mottaghi, R., & Savva, M., et\u00a0al.: (2018) On evaluation of embodied navigation agents. arXiv preprint arXiv:1807.06757"},{"key":"1721_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., Wu, Q., Teney, D., Bruce, J., Johnson, M., S\u00fcnderhauf, N., Reid, I., Gould, S., & van\u00a0den Hengel, A.: (2018)Vision-and-language navigation: Interpreting visually-grounded navigation instructions in real environments. In Proceedings of the IEEE conference on computer vision and pattern recognition pp. 3674\u20133683.","DOI":"10.1109\/CVPR.2018.00387"},{"key":"1721_CR3","doi-asserted-by":"crossref","unstructured":"Andreas, J., Klein, D.: (2015) Alignment-based compositional semantics for instruction following. In Conference on empirical methods in natural language processing pp. 1165\u20131174.","DOI":"10.18653\/v1\/D15-1138"},{"key":"1721_CR4","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Lawrence\u00a0Zitnick, C., Parikh, D.: (2015) VQA: Visual question answering. In Proceedings of the IEEE international conference on computer vision pp. 2425\u20132433.","DOI":"10.1109\/ICCV.2015.279"},{"key":"1721_CR5","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., Weston, J.: (2009) Curriculum learning. In International conference on machine learning pp. 41\u201348.","DOI":"10.1145\/1553374.1553380"},{"key":"1721_CR6","doi-asserted-by":"crossref","unstructured":"Chang, A., Dai, A., Funkhouser, T., Halber, M., Niessner, M., Savva, M., Song, S., Zeng, A., Zhang, Y.: (2017) Matterport3D: Learning from RGB-D data in indoor environments. 3DV pp. 667\u2013676.","DOI":"10.1109\/3DV.2017.00081"},{"key":"1721_CR7","doi-asserted-by":"crossref","unstructured":"Chen, D.L., Mooney, R.J.: (2011)Learning to interpret natural language navigation instructions from observations. In The AAAI conference on artificial intelligence pp. 859\u2013865.","DOI":"10.1609\/aaai.v25i1.7974"},{"key":"1721_CR8","doi-asserted-by":"crossref","unstructured":"Das, A., Kottur, S., Gupta, K., Singh, A., Yadav, D., Moura, J.M., Parikh, D., Batra, D.: (2017) Visual dialog. In Proceedings of the IEEE conference on computer vision pattern recognition pp. 326\u2013335.","DOI":"10.1109\/CVPR.2017.121"},{"key":"1721_CR9","unstructured":"Deng, Z., Narasimhan, K., Russakovsky, O.: (2020) Evolving graphical planner: Contextual global planning for vision-and-language navigation. In Proceedings of the advances in neural information processing systems."},{"key":"1721_CR10","unstructured":"Fried, D., Hu, R., Cirik, V., Rohrbach, A., Andreas, J., Morency, L.P., Berg-Kirkpatrick, T., Saenko, K., Klein, D., Darrell, T.: (2018) Speaker-follower models for vision-and-language navigation. In Proceedings of the advances in neural information processing systems pp. 3314\u20133325."},{"key":"1721_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: (2016) Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1721_CR12","doi-asserted-by":"crossref","unstructured":"Hu, R., Fried, D., Rohrbach, A., Klein, D., Darrell, T., Saenko, K.: (2019) Are you looking? grounding to multiple modalities in vision-and-language navigation. In ACL pp. 6551\u20136557.","DOI":"10.18653\/v1\/P19-1655"},{"key":"1721_CR13","doi-asserted-by":"crossref","unstructured":"Huang, H., Jain, V., Mehta, H., Ku, A., Magalhaes, G., Baldridge, J., Ie, E.: (2019) Transferable representation learning in vision-and-language navigation. In Proceedings of the IEEE\/CVF international conference on computer vision pp. 7404\u20137413.","DOI":"10.1109\/ICCV.2019.00750"},{"key":"1721_CR14","doi-asserted-by":"crossref","unstructured":"Jain, V., Magalhaes, G., Ku, A., Vaswani, A., Ie, E., Baldridge, J.: (2019) Stay on the path: Instruction fidelity in vision-and-language navigation. In Annual meeting of the association for computational linguistics.","DOI":"10.18653\/v1\/P19-1181"},{"key":"1721_CR15","doi-asserted-by":"crossref","unstructured":"Ke, L., Li, X., Bisk, Y., Holtzman, A., Gan, Z., Liu, J., Gao, J., Choi, Y., Srinivasa, S.: (2019) Tactical rewind: Self-correction via backtracking in vision-and-language navigation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition pp. 6741\u20136749.","DOI":"10.1109\/CVPR.2019.00690"},{"key":"1721_CR16","doi-asserted-by":"crossref","unstructured":"Landi, F., Baraldi, L., Cornia, M., Corsini, M., Cucchiara, R.: (2020)Perceive, transform, and act: Multi-modal attention networks for vision-and-language navigation. arXiv preprint arXiv:1911.12377","DOI":"10.1016\/j.cviu.2021.103255"},{"key":"1721_CR17","unstructured":"Liang, C., Wang, W., Zhou, T., Miao, J., Luo, Y., Yang, Y.: (2022) Local-global context aware transformer for language-guided video segmentation. arXiv preprint arXiv:2203.09773"},{"key":"1721_CR18","unstructured":"Ma, C.Y., Lu, J., Wu, Z., AlRegib, G., Kira, Z., Socher, R., Xiong, C.: (2019) Self-monitoring navigation agent via auxiliary progress estimation. In Proceedings of the international conference on learning representations."},{"key":"1721_CR19","doi-asserted-by":"crossref","unstructured":"Ma, C.Y., Wu, Z., AlRegib, G., Xiong, C., Kira, Z.: (2019) The regretful agent: Heuristic-aided navigation through progress estimation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition pp. 6732\u20136740.","DOI":"10.1109\/CVPR.2019.00689"},{"key":"1721_CR20","unstructured":"MacMahon, M., Stankiewicz, B., Kuipers, B.: (2006) Walk the talk: connecting language, knowledge, and action in route instructions. In The AAAI conference on artificial intelligence pp. 1475\u20131482."},{"key":"1721_CR21","doi-asserted-by":"crossref","unstructured":"Mei, H., Bansal, M., Walter, M.R.: (2016) Listen, attend, and walk: Neural mapping of navigational instructions to action sequences. In The AAAI conference on artificial intelligence pp. 2772\u20132778.","DOI":"10.1609\/aaai.v30i1.10364"},{"key":"1721_CR22","unstructured":"Mirowski, P., Pascanu, R., Viola, F., Soyer, H., Ballard, A.J., Banino, A., Denil, M., Goroshin, R., Sifre, L., Kavukcuoglu, K., et\u00a0al.: (2017) Learning to navigate in complex environments. In Proceedings of the international conference learning representations."},{"key":"1721_CR23","doi-asserted-by":"crossref","unstructured":"Misra, D., Bennett, A., Blukis, V., Niklasson, E., Shatkhin, M., Artzi, Y.: (2018)Mapping instructions to actions in 3d environments with visual goal prediction. In Conference on empirical methods in natural language processing pp. 2667\u20132678.","DOI":"10.18653\/v1\/D18-1287"},{"key":"1721_CR24","unstructured":"Mnih, V., Badia, A.P., Mirza, M., Graves, A., Lillicrap, T., Harley, T., Silver, D., Kavukcuoglu, K.: (2016) Asynchronous methods for deep reinforcement learning. In International conference on machine learning pp. 1928\u20131937."},{"key":"1721_CR25","doi-asserted-by":"crossref","unstructured":"Qi, Y., Pan, Z., Zhang, S., Hengel, A.v.d., Wu, Q.: (2020) Object-and-action aware model for visual language navigation. In Proceedings of the european conference on computer vision","DOI":"10.1007\/978-3-030-58607-2_18"},{"issue":"3","key":"1721_CR26","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A. C., & Fei-Fei, L. (2015). ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"1721_CR27","doi-asserted-by":"crossref","unstructured":"Tan, H., Yu, L., Bansal, M. (2019). Learning to navigate unseen environments: Back translation with environmental dropout. In Proceedings of the conference on North American chapter of the ACL pp. 2610\u20132621.","DOI":"10.18653\/v1\/N19-1268"},{"key":"1721_CR28","doi-asserted-by":"crossref","unstructured":"Tellex, S., Kollar, T., Dickerson, S., Walter, M.R., Banerjee, A.G., Teller, S., Roy, N. (2011). Understanding natural language commands for robotic navigation and mobile manipulation. In The AAAI conference on artificial intelligence pp. 1507\u20131514.","DOI":"10.1609\/aaai.v25i1.7979"},{"key":"1721_CR29","doi-asserted-by":"crossref","unstructured":"Thomason, J., Gordon, D., Bisk, Y. (2019). Shifting the baseline: Single modality performance on visual navigation & qa. In Proceedings of the conference on north american chapter of the ACL.","DOI":"10.18653\/v1\/N19-1197"},{"key":"1721_CR30","doi-asserted-by":"crossref","unstructured":"Wang, H., Liang, W., Shen, J., Van\u00a0Gool, L., Wang, W. (2022). Counterfactual cycle-consistent learning for instruction following and generation in vision-language navigation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52688.2022.01503"},{"key":"1721_CR31","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, W., Liang, W., Xiong, C., Shen, J. (2021). Structured scene memory for vision-language navigation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition pp. 8455\u20138464.","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"1721_CR32","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, W., Shu, T., Liang, W., Shen, J. (2020). Active visual information gathering for vision-language navigation. In European conference on computer vision pp. 307\u2013322.","DOI":"10.1007\/978-3-030-58542-6_19"},{"key":"1721_CR33","unstructured":"Wang, H., Wang, W., Zhu, X., Dai, J., Wang, L. (2021). Collaborative visual navigation. arXiv preprint arXiv:2107.01151."},{"key":"1721_CR34","doi-asserted-by":"crossref","unstructured":"Wang, X., Huang, Q., Celikyilmaz, A., Gao, J., Shen, D., Wang, Y.F., Wang, W.Y., Zhang, L. (2019). Reinforced cross-modal matching and self-supervised imitation learning for vision-language navigation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition pp. 6629\u20136638.","DOI":"10.1109\/CVPR.2019.00679"},{"key":"1721_CR35","doi-asserted-by":"crossref","unstructured":"Wang, X., Xiong, W., Wang, H., Yang\u00a0Wang, W. (2018). Look before you leap: Bridging model-free and model-based reinforcement learning for planned-ahead vision-and-language navigation. In Proceedings of the european conference on computer vision (ECCV) pp. 37\u201353.","DOI":"10.1007\/978-3-030-01270-0_3"},{"key":"1721_CR36","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y. (2015). Show, attend and tell: Neural image caption generation with visual attention. In International conference on machine learning pp. 2048\u20132057."},{"key":"1721_CR37","doi-asserted-by":"crossref","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L. (2016). Modeling context in referring expressions. In European conference on computer vision pp. 69\u201385.","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"1721_CR38","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, W., Qi, S., Zhu, S.C. (2019). Reasoning visual dialogs with structural and partial observations. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition pp. 6669\u20136678.","DOI":"10.1109\/CVPR.2019.00683"},{"key":"1721_CR39","doi-asserted-by":"crossref","unstructured":"Zhu, F., Zhu, Y., Chang, X., Liang, X. (2020). Vision-language navigation with self-supervised auxiliary reasoning tasks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition pp. 10012\u201310022.","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"1721_CR40","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Mottaghi, R., Kolve, E., Lim, J.J., Gupta, A., Fei-Fei, L., Farhadi, A. (2017). Target-driven visual navigation in indoor scenes using deep reinforcement learning. In International conference on robotics and automation pp. 3357\u20133364.","DOI":"10.1109\/ICRA.2017.7989381"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01721-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-022-01721-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01721-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T06:59:32Z","timestamp":1676617172000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-022-01721-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,3]]},"references-count":40,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["1721"],"URL":"https:\/\/doi.org\/10.1007\/s11263-022-01721-6","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,3]]},"assertion":[{"value":"11 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 November 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 December 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}