{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T04:41:36Z","timestamp":1783226496688,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key Research and Development Project of New Generation Artificial Intelligence of China","award":["2018AAA0102500"],"award-info":[{"award-number":["2018AAA0102500"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475575","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T05:40:18Z","timestamp":1634535618000},"page":"4343-4352","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":26,"title":["ION"],"prefix":"10.1145","author":[{"given":"Weijie","family":"Li","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinhang","family":"Song","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yubing","family":"Bai","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sixian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuqiang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031"},{"key":"e_1_3_2_1_2_1","volume-title":"Alexey Dosovitskiy, Saurabh Gupta, Vladlen Koltun, Jana Kosecka, Jitendra Malik, Roozbeh Mottaghi, Manolis Savva, and Amir Roshan Zamir.","author":"Anderson Peter","year":"2018","unstructured":"Peter Anderson , Angel X. Chang , Devendra Singh Chaplot , Alexey Dosovitskiy, Saurabh Gupta, Vladlen Koltun, Jana Kosecka, Jitendra Malik, Roozbeh Mottaghi, Manolis Savva, and Amir Roshan Zamir. 2018 a. On Evaluation of Embodied Navigation Agents. CoRR , Vol. abs\/ 1807 .06757 (2018). arxiv: 1807.06757 http:\/\/arxiv.org\/abs\/1807.06757 Peter Anderson, Angel X. Chang, Devendra Singh Chaplot, Alexey Dosovitskiy, Saurabh Gupta, Vladlen Koltun, Jana Kosecka, Jitendra Malik, Roozbeh Mottaghi, Manolis Savva, and Amir Roshan Zamir. 2018a. On Evaluation of Embodied Navigation Agents. CoRR, Vol. abs\/1807.06757 (2018). arxiv: 1807.06757 http:\/\/arxiv.org\/abs\/1807.06757"},{"key":"e_1_3_2_1_3_1","volume-title":"Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018","author":"Anderson Peter","year":"2018","unstructured":"Peter Anderson , Qi Wu , Damien Teney , Jake Bruce , Mark Johnson , Niko S\u00fc nderhauf, Ian D. Reid , Stephen Gould , and Anton van den Hengel. 2018b . Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018 , Salt Lake City, UT, USA , June 18-22, 2018 . IEEE Computer Society, 3674--3683. https:\/\/doi.org\/10.1109\/CVPR.2018.00387 10.1109\/CVPR.2018.00387 Peter Anderson, Qi Wu, Damien Teney, Jake Bruce, Mark Johnson, Niko S\u00fc nderhauf, Ian D. Reid, Stephen Gould, and Anton van den Hengel. 2018b. Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018. IEEE Computer Society, 3674--3683. https:\/\/doi.org\/10.1109\/CVPR.2018.00387"},{"key":"e_1_3_2_1_4_1","volume-title":"Exploiting Scene-Specific Features for Object Goal Navigation. In Computer Vision - ECCV 2020 Workshops - Glasgow, UK, August 23--28","author":"Campari Tommaso","year":"2020","unstructured":"Tommaso Campari , Paolo Eccher , Luciano Serafini , and Lamberto Ballan . 2020 . Exploiting Scene-Specific Features for Object Goal Navigation. In Computer Vision - ECCV 2020 Workshops - Glasgow, UK, August 23--28 , 20ndrea Fusiello (Eds.). Springer, 406--421. https:\/\/doi.org\/10.1007\/978-3-030-66823-5_24 10.1007\/978-3-030-66823-5_24 Tommaso Campari, Paolo Eccher, Luciano Serafini, and Lamberto Ballan. 2020. Exploiting Scene-Specific Features for Object Goal Navigation. In Computer Vision - ECCV 2020 Workshops - Glasgow, UK, August 23--28, 20ndrea Fusiello (Eds.). Springer, 406--421. https:\/\/doi.org\/10.1007\/978-3-030-66823-5_24"},{"key":"e_1_3_2_1_5_1","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Chaplot Devendra Singh","year":"2020","unstructured":"Devendra Singh Chaplot , Dhiraj Gandhi , Abhinav Gupta , and Russ R. Salakhutdinov . 2020 a. Object Goal Navigation using Goal-Oriented Semantic Exploration . In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020 , NeurIPS 2020 , December 6-12, 2020, virtual,, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/2c75cf2681788adaca63aa95ae028b22-Abstract.html Devendra Singh Chaplot, Dhiraj Gandhi, Abhinav Gupta, and Russ R. Salakhutdinov. 2020 a. Object Goal Navigation using Goal-Oriented Semantic Exploration. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual,, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/2c75cf2681788adaca63aa95ae028b22-Abstract.html"},{"key":"e_1_3_2_1_6_1","volume-title":"Learning To Explore Using Active Neural SLAM. In 8th International Conference on Learning Representations, ICLR 2020","author":"Chaplot Devendra Singh","year":"2020","unstructured":"Devendra Singh Chaplot , Dhiraj Gandhi , Saurabh Gupta , Abhinav Gupta , and Ruslan Salakhutdinov . 2020 b . Learning To Explore Using Active Neural SLAM. In 8th International Conference on Learning Representations, ICLR 2020 , Addis Ababa, Ethiopia , April 26-30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=HklXn1BKDH Devendra Singh Chaplot, Dhiraj Gandhi, Saurabh Gupta, Abhinav Gupta, and Ruslan Salakhutdinov. 2020 b. Learning To Explore Using Active Neural SLAM. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=HklXn1BKDH"},{"key":"e_1_3_2_1_7_1","volume-title":"Neural Topological SLAM for Visual Navigation. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020","author":"Chaplot Devendra Singh","year":"2020","unstructured":"Devendra Singh Chaplot , Ruslan Salakhutdinov , Abhinav Gupta , and Saurabh Gupta . 2020 c . Neural Topological SLAM for Visual Navigation. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 , Seattle, WA, USA , June 13-19, 2020. IEEE, 12872--12881. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01289 10.1109\/CVPR42600.2020.01289 Devendra Singh Chaplot, Ruslan Salakhutdinov, Abhinav Gupta, and Saurabh Gupta. 2020 c. Neural Topological SLAM for Visual Navigation. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020. IEEE, 12872--12881. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01289"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11832"},{"key":"e_1_3_2_1_9_1","volume-title":"ImageNet: A Large-Scale Hierarchical Image Database. In 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009","author":"Deng Jia","year":"2009","unstructured":"Jia Deng , Wei Dong , Richard Socher , Li-Jia Li , Kai Li , and Fei-Fei Li . 2009 . ImageNet: A Large-Scale Hierarchical Image Database. In 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009 ), 20--25 June 2009, Miami, Florida, USA. IEEE Computer Society, 248--255. https:\/\/doi.org\/10.1109\/CVPR. 2009.5206848 10.1109\/CVPR.2009.5206848 Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Fei-Fei Li. 2009. ImageNet: A Large-Scale Hierarchical Image Database. In 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 20--25 June 2009, Miami, Florida, USA. IEEE Computer Society, 248--255. https:\/\/doi.org\/10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings, Part VII (Lecture Notes in Computer Science","volume":"34","author":"Du Heming","year":"2020","unstructured":"Heming Du , Xin Yu , and Liang Zheng . 2020 . Learning Object Relation Graph and Tentative Policy for Visual Navigation. In Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23--28, 2020 , Proceedings, Part VII (Lecture Notes in Computer Science , Vol. 12352),, Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (Eds.). Springer, 19-- 34 . https:\/\/doi.org\/10.1007\/978-3-030-58571-6_2 10.1007\/978-3-030-58571-6_2 Heming Du, Xin Yu, and Liang Zheng. 2020. Learning Object Relation Graph and Tentative Policy for Visual Navigation. In Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part VII (Lecture Notes in Computer Science, Vol. 12352),, Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (Eds.). Springer, 19--34. https:\/\/doi.org\/10.1007\/978-3-030-58571-6_2"},{"key":"e_1_3_2_1_11_1","volume-title":"Speaker-Follower Models for Vision-and-Language Navigation. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018","author":"Fried Daniel","year":"2018","unstructured":"Daniel Fried , Ronghang Hu , Volkan Cirik , Anna Rohrbach , Jacob Andreas , Louis-Philippe Morency , Taylor Berg-Kirkpatrick , Kate Saenko , Dan Klein , and Trevor Darrell . 2018 . Speaker-Follower Models for Vision-and-Language Navigation. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018 , NeurIPS 2018, December 3-8, 2018, Montr\u00e9 al, Canada,, Samy Bengio, Hanna M. Wallach, Hugo Larochelle, Kristen Grauman, Nicol\u00f2 Cesa-Bianchi, and Roman Garnett (Eds.). 3318--3329. https:\/\/proceedings.neurips.cc\/paper\/2018\/hash\/6a81681a7af700c6385d36577ebec359-Abstract.html Daniel Fried, Ronghang Hu, Volkan Cirik, Anna Rohrbach, Jacob Andreas, Louis-Philippe Morency, Taylor Berg-Kirkpatrick, Kate Saenko, Dan Klein, and Trevor Darrell. 2018. Speaker-Follower Models for Vision-and-Language Navigation. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montr\u00e9 al, Canada,, Samy Bengio, Hanna M. Wallach, Hugo Larochelle, Kristen Grauman, Nicol\u00f2 Cesa-Bianchi, and Roman Garnett (Eds.). 3318--3329. https:\/\/proceedings.neurips.cc\/paper\/2018\/hash\/6a81681a7af700c6385d36577ebec359-Abstract.html"},{"key":"e_1_3_2_1_12_1","volume-title":"Cognitive Mapping and Planning for Visual Navigation. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","author":"Gupta Saurabh","year":"2017","unstructured":"Saurabh Gupta , James Davidson , Sergey Levine , Rahul Sukthankar , and Jitendra Malik . 2017 . Cognitive Mapping and Planning for Visual Navigation. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 , Honolulu, HI, USA , July 21-26, 2017. IEEE Computer Society, 7272--7281. https:\/\/doi.org\/10.1109\/CVPR.2017.769 10.1109\/CVPR.2017.769 Saurabh Gupta, James Davidson, Sergey Levine, Rahul Sukthankar, and Jitendra Malik. 2017. Cognitive Mapping and Planning for Visual Navigation. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017. IEEE Computer Society, 7272--7281. https:\/\/doi.org\/10.1109\/CVPR.2017.769"},{"key":"e_1_3_2_1_13_1","volume-title":"Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016","author":"He Kaiming","year":"2016","unstructured":"Kaiming He , Xiangyu Zhang , Shaoqing Ren , and Jian Sun . 2016 . Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 , Las Vegas, NV, USA , June 27-30, 2016. IEEE Computer Society, 770--778. https:\/\/doi.org\/10.1109\/CVPR.2016.90 10.1109\/CVPR.2016.90 Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016. IEEE Computer Society, 770--778. https:\/\/doi.org\/10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_14_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019","author":"Ke Liyiming","year":"2019","unstructured":"Liyiming Ke , Xiujun Li , Yonatan Bisk , Ari Holtzman , Zhe Gan , Jingjing Liu , Jianfeng Gao , Yejin Choi , and Siddhartha S. Srinivasa . 2019. Tactical Rewind: Self-Correction via Backtracking in Vision-And-Language Navigation . In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019 , Long Beach, CA, USA , June 16-20, 2019 . Computer Vision Foundation \/ IEEE, 6741--6749. https:\/\/doi.org\/10.1109\/CVPR.2019.00690 10.1109\/CVPR.2019.00690 Liyiming Ke, Xiujun Li, Yonatan Bisk, Ari Holtzman, Zhe Gan, Jingjing Liu, Jianfeng Gao, Yejin Choi, and Siddhartha S. Srinivasa. 2019. Tactical Rewind: Self-Correction via Backtracking in Vision-And-Language Navigation. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019. Computer Vision Foundation \/ IEEE, 6741--6749. https:\/\/doi.org\/10.1109\/CVPR.2019.00690"},{"key":"e_1_3_2_1_15_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba . 2015 . Adam : A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds .). http:\/\/arxiv.org\/abs\/1412.6980 Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_2_1_16_1","volume-title":"AI2-THOR: An Interactive 3D Environment for Visual AI. CoRR","author":"Kolve Eric","year":"2017","unstructured":"Eric Kolve , Roozbeh Mottaghi , Daniel Gordon , Yuke Zhu , Abhinav Gupta , and Ali Farhadi . 2017. AI2-THOR: An Interactive 3D Environment for Visual AI. CoRR , Vol. abs\/ 1712 .05474 ( 2017 ). arxiv: 1712.05474 http:\/\/arxiv.org\/abs\/1712.05474 Eric Kolve, Roozbeh Mottaghi, Daniel Gordon, Yuke Zhu, Abhinav Gupta, and Ali Farhadi. 2017. AI2-THOR: An Interactive 3D Environment for Visual AI. CoRR, Vol. abs\/1712.05474 (2017). arxiv: 1712.05474 http:\/\/arxiv.org\/abs\/1712.05474"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_18_1","volume-title":"Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020","author":"Li Juncheng","year":"2020","unstructured":"Juncheng Li , Xin Wang , Siliang Tang , Haizhou Shi , Fei Wu , Yueting Zhuang , and William Yang Wang . 2020 . Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 , Seattle, WA, USA , June 13-19, 2020. IEEE, 12120--12129. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01214 10.1109\/CVPR42600.2020.01214 Juncheng Li, Xin Wang, Siliang Tang, Haizhou Shi, Fei Wu, Yueting Zhuang, and William Yang Wang. 2020. Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020. IEEE, 12120--12129. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01214"},{"key":"e_1_3_2_1_19_1","volume-title":"Zurich, Switzerland","volume":"755","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin , Michael Maire , Serge J. Belongie , James Hays , Pietro Perona , Deva Ramanan , Piotr Doll\u00e1r , and C. Lawrence Zitnick . 2014. Microsoft COCO: Common Objects in Context. In Computer Vision - ECCV 2014 - 13th European Conference , Zurich, Switzerland , September 6-12, 2014 , Proceedings, Part V (Lecture Notes in Computer Science , Vol. 8693), David J. Fleet, Tom\u00e1 s Pajdla, Bernt Schiele, and Tinne Tuytelaars (Eds.). Springer, 740-- 755 . https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48 10.1007\/978-3-319-10602-1_48 Tsung-Yi Lin, Michael Maire, Serge J. Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common Objects in Context. In Computer Vision - ECCV 2014 - 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V (Lecture Notes in Computer Science, Vol. 8693), David J. Fleet, Tom\u00e1 s Pajdla, Bernt Schiele, and Tinne Tuytelaars (Eds.). Springer, 740--755. https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_20_1","volume-title":"7th International Conference on Learning Representations, ICLR 2019","author":"Ma Chih-Yao","year":"2019","unstructured":"Chih-Yao Ma , Jiasen Lu , Zuxuan Wu , Ghassan AlRegib , Zsolt Kira , Richard Socher , and Caiming Xiong . 2019 a. Self-Monitoring Navigation Agent via Auxiliary Progress Estimation . In 7th International Conference on Learning Representations, ICLR 2019 , New Orleans, LA, USA , May 6-9, 2019. OpenReview.net. https:\/\/openreview.net\/forum?id=r1GAsjC5Fm Chih-Yao Ma, Jiasen Lu, Zuxuan Wu, Ghassan AlRegib, Zsolt Kira, Richard Socher, and Caiming Xiong. 2019 a. Self-Monitoring Navigation Agent via Auxiliary Progress Estimation. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net. https:\/\/openreview.net\/forum?id=r1GAsjC5Fm"},{"key":"e_1_3_2_1_21_1","volume-title":"The Regretful Agent: Heuristic-Aided Navigation Through Progress Estimation. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019","author":"Ma Chih-Yao","year":"2019","unstructured":"Chih-Yao Ma , Zuxuan Wu , Ghassan AlRegib , Caiming Xiong , and Zsolt Kira . 2019 b . The Regretful Agent: Heuristic-Aided Navigation Through Progress Estimation. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019 , Long Beach, CA, USA, June 16--20 , 2019. Computer Vision Foundation \/ IEEE, 6732--6740. https:\/\/doi.org\/10.1109\/CVPR.2019.00689 10.1109\/CVPR.2019.00689 Chih-Yao Ma, Zuxuan Wu, Ghassan AlRegib, Caiming Xiong, and Zsolt Kira. 2019 b. The Regretful Agent: Heuristic-Aided Navigation Through Progress Estimation. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16--20, 2019. Computer Vision Foundation \/ IEEE, 6732--6740. https:\/\/doi.org\/10.1109\/CVPR.2019.00689"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016 (JMLR Workshop and Conference Proceedings","volume":"1937","author":"Mnih Volodymyr","year":"2016","unstructured":"Volodymyr Mnih , Adri\u00e0 Puigdom\u00e8 nech Badia , Mehdi Mirza , Alex Graves , Timothy P. Lillicrap , Tim Harley , David Silver , and Koray Kavukcuoglu . 2016 . Asynchronous Methods for Deep Reinforcement Learning . In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016 (JMLR Workshop and Conference Proceedings , Vol. 48),, Maria-Florina Balcan and Kilian Q. Weinberger (Eds.). JMLR.org, 1928-- 1937 . http:\/\/proceedings.mlr.press\/v48\/mniha16.html Volodymyr Mnih, Adri\u00e0 Puigdom\u00e8 nech Badia, Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous Methods for Deep Reinforcement Learning. In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016 (JMLR Workshop and Conference Proceedings, Vol. 48),, Maria-Florina Balcan and Kilian Q. Weinberger (Eds.). JMLR.org, 1928--1937. http:\/\/proceedings.mlr.press\/v48\/mniha16.html"},{"key":"e_1_3_2_1_23_1","volume-title":"Visual Representations for Semantic Target Driven Navigation. In International Conference on Robotics and Automation, ICRA 2019","author":"Mousavian Arsalan","year":"2019","unstructured":"Arsalan Mousavian , Alexander Toshev , Marek Fiser , Jana Koseck\u00e1 , Ayzaan Wahid , and James Davidson . 2019 . Visual Representations for Semantic Target Driven Navigation. In International Conference on Robotics and Automation, ICRA 2019 , Montreal, QC, Canada, May 20--24 , 2019. IEEE, 8846--8852. https:\/\/doi.org\/10.1109\/ICRA.2019.8793493 10.1109\/ICRA.2019.8793493 Arsalan Mousavian, Alexander Toshev, Marek Fiser, Jana Koseck\u00e1, Ayzaan Wahid, and James Davidson. 2019. Visual Representations for Semantic Target Driven Navigation. In International Conference on Robotics and Automation, ICRA 2019, Montreal, QC, Canada, May 20--24, 2019. IEEE, 8846--8852. https:\/\/doi.org\/10.1109\/ICRA.2019.8793493"},{"key":"e_1_3_2_1_24_1","volume-title":"Grounded Human-Object Interaction Hotspots From Video. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019","author":"Nagarajan Tushar","year":"2019","unstructured":"Tushar Nagarajan , Christoph Feichtenhofer , and Kristen Grauman . 2019 . Grounded Human-Object Interaction Hotspots From Video. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019 , Seoul, Korea (South), October 27 - November 2, 2019. IEEE, 8687--8696. https:\/\/doi.org\/10.1109\/ICCV.2019.00878 10.1109\/ICCV.2019.00878 Tushar Nagarajan, Christoph Feichtenhofer, and Kristen Grauman. 2019. Grounded Human-Object Interaction Hotspots From Video. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019. IEEE, 8687--8696. https:\/\/doi.org\/10.1109\/ICCV.2019.00878"},{"key":"e_1_3_2_1_25_1","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Nagarajan Tushar","year":"2020","unstructured":"Tushar Nagarajan and Kristen Grauman . 2020 . Learning Affordance Landscapes for Interaction Exploration in 3D Environments . In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020 , NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/15825aee15eb335cc13f9b559f166ee8-Abstract.html Tushar Nagarajan and Kristen Grauman. 2020. Learning Affordance Landscapes for Interaction Exploration in 3D Environments. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/15825aee15eb335cc13f9b559f166ee8-Abstract.html"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01281"},{"key":"e_1_3_2_1_27_1","volume-title":"Manning","author":"Pennington Jeffrey","year":"2014","unstructured":"Jeffrey Pennington , Richard Socher , and Christopher D . Manning . 2014 . Glove : Global Vectors for Word Representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, October 25--29, 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL,, Alessandro Moschitti, Bo Pang, and Walter Daelemans (Eds.). ACL, 1532--1543. https:\/\/doi.org\/10.3115\/v1\/d14-1162 10.3115\/v1 Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. Glove: Global Vectors for Word Representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, October 25--29, 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL,, Alessandro Moschitti, Bo Pang, and Walter Daelemans (Eds.). ACL, 1532--1543. https:\/\/doi.org\/10.3115\/v1\/d14-1162"},{"key":"e_1_3_2_1_28_1","volume-title":"REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020","author":"Qi Yuankai","year":"2020","unstructured":"Yuankai Qi , Qi Wu , Peter Anderson , Xin Wang , William Yang Wang , Chunhua Shen , and Anton van den Hengel. 2020 . REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 , Seattle, WA, USA, June 13--19 , 2020 . IEEE, 9979--9988. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01000 10.1109\/CVPR42600.2020.01000 Yuankai Qi, Qi Wu, Peter Anderson, Xin Wang, William Yang Wang, Chunhua Shen, and Anton van den Hengel. 2020. REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13--19, 2020. IEEE, 9979--9988. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01000"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_1_30_1","volume-title":"6th International Conference on Learning Representations, ICLR","author":"Savinov Nikolay","year":"2018","unstructured":"Nikolay Savinov , Alexey Dosovitskiy , and Vladlen Koltun . 2018. SEMI-PARAMETRIC TOPOLOGICAL MEMORY FOR NAVIGATION . In 6th International Conference on Learning Representations, ICLR 2018 , Vancouver, BC , Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview .net. https:\/\/openreview.net\/forum?id=SygwwGbRW Nikolay Savinov, Alexey Dosovitskiy, and Vladlen Koltun. 2018. SEMI-PARAMETRIC TOPOLOGICAL MEMORY FOR NAVIGATION. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=SygwwGbRW"},{"key":"e_1_3_2_1_31_1","volume-title":"MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments. CoRR","author":"Savva Manolis","year":"2017","unstructured":"Manolis Savva , Angel X. Chang , Alexey Dosovitskiy , Thomas A. Funkhouser , and Vladlen Koltun . 2017 . MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments. CoRR , Vol. abs\/ 1712 .03931 (2017). arxiv: 1712.03931 http:\/\/arxiv.org\/abs\/1712.03931 Manolis Savva, Angel X. Chang, Alexey Dosovitskiy, Thomas A. Funkhouser, and Vladlen Koltun. 2017. MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments. CoRR, Vol. abs\/1712.03931 (2017). arxiv: 1712.03931 http:\/\/arxiv.org\/abs\/1712.03931"},{"key":"e_1_3_2_1_32_1","volume-title":"Habitat: A Platform for Embodied AI Research. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019","author":"Savva Manolis","year":"2019","unstructured":"Manolis Savva , Jitendra Malik , Devi Parikh , Dhruv Batra , Abhishek Kadian , Oleksandr Maksymets , Yili Zhao , Erik Wijmans , Bhavana Jain , Julian Straub , Jia Liu , and Vladlen Koltun . 2019 . Habitat: A Platform for Embodied AI Research. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019 , Seoul, Korea (South), October 27 - November 2, 2019. IEEE, 9338--9346. https:\/\/doi.org\/10.1109\/ICCV.2019.00943 10.1109\/ICCV.2019.00943 Manolis Savva, Jitendra Malik, Devi Parikh, Dhruv Batra, Abhishek Kadian, Oleksandr Maksymets, Yili Zhao, Erik Wijmans, Bhavana Jain, Julian Straub, Jia Liu, and Vladlen Koltun. 2019. Habitat: A Platform for Embodied AI Research. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019. IEEE, 9338--9346. https:\/\/doi.org\/10.1109\/ICCV.2019.00943"},{"key":"e_1_3_2_1_33_1","volume-title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020","author":"Shridhar Mohit","year":"2020","unstructured":"Mohit Shridhar , Jesse Thomason , Daniel Gordon , Yonatan Bisk , Winson Han , Roozbeh Mottaghi , Luke Zettlemoyer , and Dieter Fox . 2020 . ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 , Seattle, WA, USA , June 13-19, 2020. IEEE, 10737--10746. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01075 10.1109\/CVPR42600.2020.01075 Mohit Shridhar, Jesse Thomason, Daniel Gordon, Yonatan Bisk, Winson Han, Roozbeh Mottaghi, Luke Zettlemoyer, and Dieter Fox. 2020. ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020. IEEE, 10737--10746. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01075"},{"key":"e_1_3_2_1_34_1","volume-title":"Vision-and-Dialog Navigation. In 3rd Annual Conference on Robot Learning, CoRL 2019, Osaka, Japan, October 30 - November 1, 2019, Proceedings (Proceedings of Machine Learning Research","volume":"406","author":"Thomason Jesse","year":"2019","unstructured":"Jesse Thomason , Michael Murray , Maya Cakmak , and Luke Zettlemoyer . 2019 . Vision-and-Dialog Navigation. In 3rd Annual Conference on Robot Learning, CoRL 2019, Osaka, Japan, October 30 - November 1, 2019, Proceedings (Proceedings of Machine Learning Research , Vol. 100), Leslie Pack Kaelbling, Danica Kragic, and Komei Sugiura (Eds.). PMLR, 394-- 406 . http:\/\/proceedings.mlr.press\/v100\/thomason20a.html Jesse Thomason, Michael Murray, Maya Cakmak, and Luke Zettlemoyer. 2019. Vision-and-Dialog Navigation. In 3rd Annual Conference on Robot Learning, CoRL 2019, Osaka, Japan, October 30 - November 1, 2019, Proceedings (Proceedings of Machine Learning Research, Vol. 100), Leslie Pack Kaelbling, Danica Kragic, and Komei Sugiura (Eds.). PMLR, 394--406. http:\/\/proceedings.mlr.press\/v100\/thomason20a.html"},{"key":"e_1_3_2_1_35_1","volume-title":"Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019","author":"Wang Xin","year":"2019","unstructured":"Xin Wang , Qiuyuan Huang , Asli Celikyilmaz , Jianfeng Gao , Dinghan Shen , Yuan-Fang Wang , William Yang Wang , and Lei Zhang . 2019 a . Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019 , Long Beach, CA, USA, June 16--20 , 2019. Computer Vision Foundation \/ IEEE, 6629--6638. https:\/\/doi.org\/10.1109\/CVPR.2019.00679 10.1109\/CVPR.2019.00679 Xin Wang, Qiuyuan Huang, Asli Celikyilmaz, Jianfeng Gao, Dinghan Shen, Yuan-Fang Wang, William Yang Wang, and Lei Zhang. 2019 a. Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16--20, 2019. Computer Vision Foundation \/ IEEE, 6629--6638. https:\/\/doi.org\/10.1109\/CVPR.2019.00679"},{"key":"e_1_3_2_1_36_1","first-page":"13","volume-title":"NeurIPS 2019 Workshop","author":"Wang Xin","year":"2019","unstructured":"Xin Wang , Vihan Jain , Eugene Ie , William Yang Wang , Zornitsa Kozareva , and Sujith Ravi . 2019 b. Natural Language Grounded Multitask Navigation. In Visually Grounded Interaction and Language (ViGIL) , NeurIPS 2019 Workshop , Vancouver, Canada , December 13, 2019. https:\/\/vigilworkshop.github.io\/static\/papers\/ 13 .pdf Xin Wang, Vihan Jain, Eugene Ie, William Yang Wang, Zornitsa Kozareva, and Sujith Ravi. 2019 b. Natural Language Grounded Multitask Navigation. In Visually Grounded Interaction and Language (ViGIL), NeurIPS 2019 Workshop, Vancouver, Canada, December 13, 2019. https:\/\/vigilworkshop.github.io\/static\/papers\/13.pdf"},{"key":"e_1_3_2_1_37_1","volume-title":"Munich","volume":"55","author":"Wang Xin","year":"2018","unstructured":"Xin Wang , Wenhan Xiong , Hongmin Wang , and William Yang Wang . 2018 . Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation. In Computer Vision - ECCV 2018 - 15th European Conference , Munich , Germany, September 8-14, 2018, Proceedings, Part XVI (Lecture Notes in Computer Science , Vol. 11220), Vittorio Ferrari, Martial Hebert, Cristian Sminchisescu, and Yair Weiss (Eds.). Springer, 38-- 55 . https:\/\/doi.org\/10.1007\/978-3-030-01270-0_3 10.1007\/978-3-030-01270-0_3 Xin Wang, Wenhan Xiong, Hongmin Wang, and William Yang Wang. 2018. Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation. In Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XVI (Lecture Notes in Computer Science, Vol. 11220), Vittorio Ferrari, Martial Hebert, Cristian Sminchisescu, and Yair Weiss (Eds.). Springer, 38--55. https:\/\/doi.org\/10.1007\/978-3-030-01270-0_3"},{"key":"e_1_3_2_1_38_1","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Wani Saim","year":"2020","unstructured":"Saim Wani , Shivansh Patel , Unnat Jain , Angel X. Chang , and Manolis Savva . 2020 . MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation . In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020 , NeurIPS 2020, December 6-12, 2020, virtual,, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/6e01383fd96a17ae51cc3e15447e7533-Abstract.html Saim Wani, Shivansh Patel, Unnat Jain, Angel X. Chang, and Manolis Savva. 2020. MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual,, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/6e01383fd96a17ae51cc3e15447e7533-Abstract.html"},{"key":"e_1_3_2_1_39_1","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Wijmans Erik","year":"2020","unstructured":"Erik Wijmans , Abhishek Kadian , Ari Morcos , Stefan Lee , Irfan Essa , Devi Parikh , Manolis Savva , and Dhruv Batra . 2020 . DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames . In 8th International Conference on Learning Representations, ICLR 2020 , Addis Ababa, Ethiopia , April 26-30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=H1gX8C4YPr Erik Wijmans, Abhishek Kadian, Ari Morcos, Stefan Lee, Irfan Essa, Devi Parikh, Manolis Savva, and Dhruv Batra. 2020. DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=H1gX8C4YPr"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00691"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126686"},{"key":"e_1_3_2_1_42_1","volume-title":"Bayesian Relational Memory for Semantic Visual Navigation. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019","author":"Wu Yi","year":"2019","unstructured":"Yi Wu , Yuxin Wu , Aviv Tamar , Stuart J. Russell , Georgia Gkioxari , and Yuandong Tian . 2019 . Bayesian Relational Memory for Semantic Visual Navigation. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019 , Seoul, Korea (South), October 27 - November 2, 2019. IEEE, 2769--2779. https:\/\/doi.org\/10.1109\/ICCV.2019.00286 10.1109\/ICCV.2019.00286 Yi Wu, Yuxin Wu, Aviv Tamar, Stuart J. Russell, Georgia Gkioxari, and Yuandong Tian. 2019. Bayesian Relational Memory for Semantic Visual Navigation. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019. IEEE, 2769--2779. https:\/\/doi.org\/10.1109\/ICCV.2019.00286"},{"key":"e_1_3_2_1_43_1","volume-title":"7th International Conference on Learning Representations, ICLR 2019","author":"Yang Wei","year":"2019","unstructured":"Wei Yang , Xiaolong Wang , Ali Farhadi , Abhinav Gupta , and Roozbeh Mottaghi . 2019 . Visual Semantic Navigation using Scene Priors . In 7th International Conference on Learning Representations, ICLR 2019 , New Orleans, LA, USA , May 6-9, 2019. OpenReview.net. https:\/\/openreview.net\/forum?id=HJeRkh05Km Wei Yang, Xiaolong Wang, Ali Farhadi, Abhinav Gupta, and Roozbeh Mottaghi. 2019. Visual Semantic Navigation using Scene Priors. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net. https:\/\/openreview.net\/forum?id=HJeRkh05Km"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475575","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475575","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:49:11Z","timestamp":1750193351000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475575"}},"subtitle":["Instance-level Object Navigation"],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":44,"alternative-id":["10.1145\/3474085.3475575","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475575","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}