{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:54:46Z","timestamp":1777568086113,"version":"3.51.4"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030286187","type":"print"},{"value":"9783030286194","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,11,28]],"date-time":"2019-11-28T00:00:00Z","timestamp":1574899200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-28619-4_30","type":"book-chapter","created":{"date-parts":[[2019,11,28]],"date-time":"2019-11-28T00:04:15Z","timestamp":1574899455000},"page":"371-386","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Multiview Approach to Learning Articulated Motion Models"],"prefix":"10.1007","author":[{"given":"Andrea F.","family":"Daniele","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas M.","family":"Howard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew R.","family":"Walter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,11,28]]},"reference":[{"key":"30_CR1","doi-asserted-by":"crossref","unstructured":"Alayrac, J.B., Sivic, J., Laptev, I., Lacoste-Julien, S.: Joint discovery of object states and manipulation actions (2017). arXiv:170202738","DOI":"10.1109\/ICCV.2017.234"},{"key":"30_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C.L., Parikh, D.: VQA: visual question answering (2015). arXiv:150500468","DOI":"10.1109\/ICCV.2015.279"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Argall, B.D., Chernova, S., Veloso, M., Browning, B.: A survey of robot learning from demonstration. Robot. Auton. Syst. (2009)","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Artzi, Y., Zettlemoyer, L.: Weakly supervised learning of semantic parsers for mapping instructions to actions. Trans. Assoc. Comput. Linguist. (2013)","DOI":"10.1162\/tacl_a_00209"},{"key":"30_CR5","unstructured":"Bouguet, J.Y.: Pyramidal implementation of the affine Lucas-Kanade feature tracker description of the algorithm. Intel Corp. (2001)"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Byravan, A., Fox, D.: SE3-Nets: learning rigid body motion using deep neural networks. In: Proceedings of ICRA (2017)","DOI":"10.1109\/ICRA.2017.7989023"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Chen, D.L., Mooney, R.J.: Learning to interpret natural language navigation instructions from observations. In: Proceedings of AAAI (2011)","DOI":"10.1609\/aaai.v25i1.7974"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Donahue, J., Hendricks, L.A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description (2014). arXiv:14114389","DOI":"10.21236\/ADA623249"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"Duvallet, F., Walter, M.R., Howard, T., Hemachandra, S., Oh, J., Teller, S., Roy, N., Stentz, A.: Inferring maps and behaviors from natural language instructions. In: Proceedings of ISER (2014)","DOI":"10.1007\/978-3-319-23778-7_25"},{"key":"30_CR10","unstructured":"Ester, M., Kriegel, H.P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of KDD (1996)"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM (1981)","DOI":"10.1145\/358669.358692"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Guadarrama, S., Riano, L., Golland, D., Gohring, D., Jia, Y., Klein, D., Abbeel, P., Darrell, T.: Grounding spatial relations for human-robot interaction. In: Proceedings of IROS (2013)","DOI":"10.1109\/IROS.2013.6696569"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Guadarrama, S., Rodner, E., Saenko, K., Zhang, N., Farrell, R., Donahue, J., Darrell, T.: Open-vocabulary object retrieval. In: Proceedings of RSS (2014)","DOI":"10.15607\/RSS.2014.X.041"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Hausman, K., Niekum, S., Ostenoski, S., Sukhatme, G.S.: Active articulation model estimation through interactive perception. In: Proceedings of ICRA (2015)","DOI":"10.1109\/ICRA.2015.7139655"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Hemachandra, S., Walter, M.R., Tellex, S., Teller, S.: Learning spatially-semantic representations from natural language descriptions and scene classifications. In: Proceedings of ICRA (2014)","DOI":"10.1109\/ICRA.2014.6907235"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Hemachandra, S., Duvallet, F., Howard, T.M., Roy, N., Stentz, A., Walter, M.R.: Learning models for following natural language directions in unknown environments. In: Proceedings of ICRA (2015)","DOI":"10.1109\/ICRA.2015.7139984"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Howard, T.M., Tellex, S., Roy, N.: A natural language planner interface for mobile manipulators. In: Proceedings of ICRA (2014)","DOI":"10.1109\/ICRA.2014.6907841"},{"key":"30_CR18","unstructured":"Huang, X., Walker, I., Birchfield, S.: Occlusion-aware reconstruction and manipulation of 3D articulated objects. In: Proceedings of ICRA (2012)"},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Jain, A., Kemp, C.C.: Pulling open doors and drawers: coordinating an omni-directional base and a compliant arm with equilibrium point control. In: Proceedings of ICRA (2010)","DOI":"10.1109\/ROBOT.2010.5509445"},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Kaess, M., Ranganathan, A., Dellaert, F.: iSAM: incremental smoothing and mapping. Trans. Robot. (2008)","DOI":"10.1109\/TRO.2008.2006706"},{"key":"30_CR21","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"30_CR22","unstructured":"Katz, D., Orthey, A., Brock, O.: Interactive perception of articulated objects. In: Proceedings of ISER (2010)"},{"key":"30_CR23","doi-asserted-by":"crossref","unstructured":"Katz, D., Kazemi, M., Andrew\u00a0Bagnell, J., Stentz, A.: Interactive segmentation, tracking, and kinematic modeling of unknown 3D articulated objects. In: Proceedings of ICRA (2013)","DOI":"10.1109\/ICRA.2013.6631292"},{"key":"30_CR24","doi-asserted-by":"crossref","unstructured":"Kollar, T., Tellex, S., Roy, D., Roy, N.: Toward understanding natural language directions. In: Proceedings of HRI (2010)","DOI":"10.1109\/HRI.2010.5453186"},{"key":"30_CR25","doi-asserted-by":"crossref","unstructured":"Kollar, T., Krishnamurthy. J., Strimel. G.: Toward interactive grounded language acquisition. In: Proceedings of RSS (2013)","DOI":"10.15607\/RSS.2013.IX.005"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Kong, C., Lin, D., Bansal, M., Urtasun, R., Fidler, S.: What are you talking about? text-to-image coreference. In: Proceedings of CVPR (2014)","DOI":"10.1109\/CVPR.2014.455"},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Krishnamurthy, J., Kollar, T.: Jointly learning to parse and perceive: connecting natural language to the physical world. Trans. Assoc. Comput. Linguist. (2013)","DOI":"10.1162\/tacl_a_00220"},{"key":"30_CR28","doi-asserted-by":"crossref","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. (2004)","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"30_CR29","doi-asserted-by":"crossref","unstructured":"Malmaud, J., Huang, J., Rathod, V., Johnston, N., Rabinovich, A., Murphy, K.: What\u2019s cookin\u2019? Interpreting cooking videos using text, speech and vision (2015). arXiv:150301558","DOI":"10.3115\/v1\/N15-1015"},{"key":"30_CR30","doi-asserted-by":"crossref","unstructured":"Mart\u00edn-Mart\u00edn, R., Brock, O.: Online interactive perception of articulated objects with multi-level recursive estimation based on task-specific priors. In: Proceedings of IROS (2014)","DOI":"10.1109\/IROS.2014.6942902"},{"key":"30_CR31","doi-asserted-by":"crossref","unstructured":"Mart\u00edn-Mart\u00edn, R., H\u00f6fer, S., Brock, O.: An integrated approach to visual perception of articulated objects. In: Proceedings of ICRA (2016)","DOI":"10.1109\/ICRA.2016.7487714"},{"key":"30_CR32","doi-asserted-by":"crossref","unstructured":"Matuszek, C., Fox, D., Koscher, K.: Following directions using statistical machine translation. In: Proceedings of HRI (2010)","DOI":"10.1109\/HRI.2010.5453189"},{"key":"30_CR33","doi-asserted-by":"crossref","unstructured":"Matuszek, C., Herbst, E., Zettlemoyer, L., Fox, D.: Learning to parse natural language commands to a robot control system. In: Proceedings of ISER (2012)","DOI":"10.1007\/978-3-319-00065-7_28"},{"key":"30_CR34","doi-asserted-by":"crossref","unstructured":"Mei, H., Bansal, M., Walter, M.R.: Listen, attend, and walk: neural mapping of navigational instructions to action sequences. In: Proceedings of AAAI (2016)","DOI":"10.1609\/aaai.v30i1.10364"},{"key":"30_CR35","unstructured":"Misra, D.K., Sung, J., Lee, K., Saxena, A.: Tell me Dave: Context-sensitive grounding of natural language to manipulation instructions. Int. J. Robot. Res. (2016)"},{"key":"30_CR36","doi-asserted-by":"crossref","unstructured":"Olson, E.: AprilTag: a robust and flexible visual fiducial system. In: Proceedings of ICRA (2011)","DOI":"10.1109\/ICRA.2011.5979561"},{"key":"30_CR37","unstructured":"Ordonez, V., Kulkarni, G., Berg, T.L.: Im2Text: describing images using 1 million captioned photographs. In: Proceedings of NIPS (2011)"},{"key":"30_CR38","unstructured":"Paul, R., Arkin, J., Roy, N., Howard, T.M.: Efficient grounding of abstract spatial concepts for natural language interaction with robot manipulators. In: Proceedings of RSS (2016)"},{"key":"30_CR39","doi-asserted-by":"crossref","unstructured":"Pillai, S., Walter. M.R., Teller. S.: Learning articulated motions from visual demonstration. In: Proceedings of RSS (2014)","DOI":"10.15607\/RSS.2014.X.050"},{"key":"30_CR40","doi-asserted-by":"crossref","unstructured":"Pronobis, A., Jensfelt, P.: Large-scale semantic mapping and reasoning with heterogeneous modalities. In: Proceedings of ICRA (2012)","DOI":"10.1109\/ICRA.2012.6224637"},{"key":"30_CR41","doi-asserted-by":"crossref","unstructured":"Ramanathan, V., Joulin, A., Liang, P., Fei-Fei, L.: Linking people in videos with their names using coreference resolution. In: Proceedings of ECCV (2014)","DOI":"10.1007\/978-3-319-10590-1_7"},{"key":"30_CR42","doi-asserted-by":"crossref","unstructured":"Schmidt, T., Newcombe, R., Fox, D.: DART: dense articulated real-time tracking. In: Proceedings of RSS (2014)","DOI":"10.15607\/RSS.2014.X.030"},{"key":"30_CR43","doi-asserted-by":"crossref","unstructured":"Sener, O., Zamir, A.R., Savarese, S., Saxena, A.: Unsupervised semantic parsing of video collections. In: Proceedings of ICCV (2015)","DOI":"10.1109\/ICCV.2015.509"},{"key":"30_CR44","unstructured":"Srivastava, N., Mansimov, E., Salakhutdinov, R.: Unsupervised learning of video representations using LSTMs. In: Proceedings of ICML (2015)"},{"key":"30_CR45","doi-asserted-by":"crossref","unstructured":"Sturm, J., Stachniss. C., Burgard, W.: A probabilistic framework for learning kinematic models of articulated objects. J. Artif. Intell. Res. (2011)","DOI":"10.1613\/jair.3229"},{"key":"30_CR46","unstructured":"Sung, J., Jin, S.H., Saxena, A.: Robobarista: object part-based transfer of manipulation trajectories from crowd-sourcing in 3D pointclouds. In: Proceedings of ISRR (2015)"},{"key":"30_CR47","doi-asserted-by":"crossref","unstructured":"Tellex, S., Kollar, T., Dickerson, S., Walter, M.R., Banerjee, A.G., Teller, S., Roy, N.: Understanding natural language commands for robotic navigation and mobile manipulation. In: Proceedings of AAAI (2011)","DOI":"10.1609\/aaai.v25i1.7979"},{"key":"30_CR48","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"30_CR49","doi-asserted-by":"crossref","unstructured":"Walter, M.R., Hemachandra, S., Homberg, B., Tellex, S., Teller, S.: Learning semantic maps from natural language descriptions. In: Proceedings of RSS (2013)","DOI":"10.15607\/RSS.2013.IX.004"},{"key":"30_CR50","doi-asserted-by":"crossref","unstructured":"Wang, H., Klaser, A., Schmid, C., Liu, C.L.: Action recognition by dense trajectories. In: Proceedings of CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"30_CR51","doi-asserted-by":"crossref","unstructured":"Winograd, T.: Understanding natural language. Cogn. Psychol. (1972)","DOI":"10.1016\/0010-0285(72)90002-3"},{"key":"30_CR52","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: neural image caption generation with visual attention. In: Proceedings of ICML (2015)"},{"key":"30_CR53","doi-asserted-by":"crossref","unstructured":"Yan, J., Pollefeys, M.: A general framework for motion segmentation: independent, articulated, rigid, non-rigid, degenerate and non-degenerate. In: Proceedings ECCV (2006)","DOI":"10.1007\/11744085_8"},{"key":"30_CR54","doi-asserted-by":"crossref","unstructured":"Yang, Y., Li, Y., Ferm\u00fcller, C., Aloimonos, Y.: Robot learning manipulation action plans by \u201cwatching\u201d unconstrained videos from the world wide web. In: Proceedings of AAAI (2015)","DOI":"10.1609\/aaai.v29i1.9671"},{"key":"30_CR55","doi-asserted-by":"crossref","unstructured":"Yu, S.I., Jiang, L., Hauptmann, A.: Instructional videos for unsupervised harvesting and learning of action examples. In: Proceedings of International Conference on Multimedia (2014)","DOI":"10.1145\/2647868.2654997"},{"key":"30_CR56","doi-asserted-by":"crossref","unstructured":"Zender, H., Mart\u00ednez Mozos, O., Jensfelt, P., Kruijff, G., Burgard, W.: Conceptual spatial representations for indoor mobile robots. Robot. Auton. Syst. (2008)","DOI":"10.1016\/j.robot.2008.03.007"}],"container-title":["Springer Proceedings in Advanced Robotics","Robotics Research"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-28619-4_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,7]],"date-time":"2022-10-07T02:31:01Z","timestamp":1665109861000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-28619-4_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,28]]},"ISBN":["9783030286187","9783030286194"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-28619-4_30","relation":{},"ISSN":["2511-1256","2511-1264"],"issn-type":[{"value":"2511-1256","type":"print"},{"value":"2511-1264","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11,28]]},"assertion":[{"value":"28 November 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}