{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:41:35Z","timestamp":1759333295844,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T00:00:00Z","timestamp":1571097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["61751209","1611461"],"award-info":[{"award-number":["61751209","1611461"]}]},{"name":"National Key Research and Development Program of China","award":["SQ2018AAA010010"],"award-info":[{"award-number":["SQ2018AAA010010"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3351017","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"1211-1219","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Walking with MIND"],"prefix":"10.1145","author":[{"given":"Juncheng","family":"Li","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"volume-title":"Blindfold baselines for embodied qa. arXiv preprint arXiv:1811.05013","year":"2018","author":"Anand Ankesh","key":"e_1_3_2_1_1_1"},{"volume-title":"Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (Jun 2018","year":"2018","author":"Anderson Peter","key":"e_1_3_2_1_2_1"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305399"},{"key":"e_1_3_2_1_5_1","unstructured":"Christopher P. Burgess Irina Higgins Arka Pal Loic Matthey Nick Watters Guillaume Desjardins and Alexander Lerchner. 2018. Understanding disentangling in -VAE. arxiv: cs.LG\/1804.03599  Christopher P. Burgess Irina Higgins Arka Pal Loic Matthey Nick Watters Guillaume Desjardins and Alexander Lerchner. 2018. Understanding disentangling in -VAE. arxiv: cs.LG\/1804.03599"},{"volume-title":"Rama Kumar Pasumarthi, Dheeraj Rajagopal, and Ruslan Salakhutdinov.","year":"2017","author":"Chaplot Devendra Singh","key":"e_1_3_2_1_6_1"},{"volume-title":"Proceedings of the 25th AAAI Conference on Artificial Intelligence (AAAI-2011)","author":"David","key":"e_1_3_2_1_7_1"},{"volume-title":"Embodied Question Answering. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) .","year":"2018","author":"Das Abhishek","key":"e_1_3_2_1_8_1"},{"volume-title":"Neural modular control for embodied question answering. arXiv preprint arXiv:1810.11181","year":"2018","author":"Das Abhishek","key":"e_1_3_2_1_9_1"},{"volume-title":"Principles of mental imagery","author":"Finke Ronald A","key":"e_1_3_2_1_10_1"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00430"},{"key":"e_1_3_2_1_12_1","unstructured":"David Ha and J\u00fcrgen Schmidhuber. 2018. World Models. arxiv: cs.LG\/1803.10122  David Ha and J\u00fcrgen Schmidhuber. 2018. World Models. arxiv: cs.LG\/1803.10122"},{"key":"e_1_3_2_1_13_1","volume-title":"International Conference on Learning Representations","volume":"3","author":"Higgins Irina","year":"2017"},{"volume-title":"Long short-term memory. Neural computation","year":"1997","author":"Hochreiter Sepp","key":"e_1_3_2_1_14_1"},{"volume-title":"Mental models, deductive reasoning, and the brain. The cognitive neurosciences","year":"1995","author":"Johnson-Laird Philip N","key":"e_1_3_2_1_15_1"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Natalie Jones Helen Ross Timothy Lynam Pascal Perez and Anne Leitch. 2011. Mental models: an interdisciplinary synthesis of theory and methods. (2011).  Natalie Jones Helen Ross Timothy Lynam Pascal Perez and Anne Leitch. 2011. Mental models: an interdisciplinary synthesis of theory and methods. (2011).","DOI":"10.5751\/ES-03802-160146"},{"key":"e_1_3_2_1_17_1","unstructured":"Diederik P Kingma and Max Welling. 2013. Auto-Encoding Variational Bayes. arxiv: cs.LG\/1312.6114  Diederik P Kingma and Max Welling. 2013. Auto-Encoding Variational Bayes. arxiv: cs.LG\/1312.6114"},{"volume-title":"Ai2-thor: An interactive 3d environment for visual ai. arXiv preprint arXiv:1712.05474","year":"2017","author":"Kolve Eric","key":"e_1_3_2_1_18_1"},{"key":"e_1_3_2_1_19_1","first-page":"289","article-title":"Image and brain: The resolution of the imagery debate","volume":"372","author":"Kosslyn SM","year":"1994","journal-title":"Nature"},{"key":"e_1_3_2_1_20_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105.  Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105."},{"volume-title":"Action in Route Instructions. In In Proc. of the Nat. Conf. on Artificial Intelligence (AAAI. 1475--1482","year":"2006","author":"Macmahon Matt","key":"e_1_3_2_1_21_1"},{"volume-title":"Walter","year":"2015","author":"Mei Hongyuan","key":"e_1_3_2_1_22_1"},{"volume-title":"International conference on machine learning. 1928--1937","year":"2016","author":"Mnih Volodymyr","key":"e_1_3_2_1_23_1"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305890.3305956"},{"volume-title":"High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438","year":"2015","author":"Schulman John","key":"e_1_3_2_1_25_1"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298239.3298465"},{"volume-title":"William Yang Wang, and Lei Zhang","year":"2018","author":"Wang Xin","key":"e_1_3_2_1_27_1"},{"volume-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning","year":"1992","author":"Williams Ronald J","key":"e_1_3_2_1_28_1"},{"volume-title":"Six views of embodied cognition. Psychonomic bulletin & review","year":"2002","author":"Wilson Margaret","key":"e_1_3_2_1_29_1"},{"key":"e_1_3_2_1_31_1","unstructured":"Yu Wu Lu Jiang and Yi Yang. 2019. Revisiting EmbodiedQA: A Simple Baseline and Beyond. arxiv: cs.CV\/1904.04166  Yu Wu Lu Jiang and Yi Yang. 2019. Revisiting EmbodiedQA: A Simple Baseline and Beyond. arxiv: cs.CV\/1904.04166"},{"key":"e_1_3_2_1_32_1","unstructured":"Yi Wu Yuxin Wu Georgia Gkioxari and Yuandong Tian. 2018. Building Generalizable Agents with a Realistic and Rich 3D Environment. arxiv: cs.LG\/1801.02209  Yi Wu Yuxin Wu Georgia Gkioxari and Yuandong Tian. 2018. Building Generalizable Agents with a Realistic and Rich 3D Environment. arxiv: cs.LG\/1801.02209"},{"key":"e_1_3_2_1_33_1","unstructured":"Edward N Zalta Uri Nodelman Colin Allen and John Perry. 2003. Stanford encyclopedia of philosophy.  Edward N Zalta Uri Nodelman Colin Allen and John Perry. 2003. Stanford encyclopedia of philosophy."}],"event":{"name":"MM '19: The 27th ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Nice France","acronym":"MM '19"},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351017","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3351017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:11Z","timestamp":1750201991000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351017"}},"subtitle":["Mental Imagery eNhanceD Embodied QA"],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":31,"alternative-id":["10.1145\/3343031.3351017","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3351017","relation":{},"subject":[],"published":{"date-parts":[[2019,10,15]]},"assertion":[{"value":"2019-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}