{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T11:47:35Z","timestamp":1778154455090,"version":"3.51.4"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030638320","type":"print"},{"value":"9783030638337","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-63833-7_63","type":"book-chapter","created":{"date-parts":[[2020,11,19]],"date-time":"2020-11-19T06:03:35Z","timestamp":1605765815000},"page":"750-761","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Active Object Estimation for Human-Robot Collaborative Tasks"],"prefix":"10.1007","author":[{"given":"Chaoran","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lina","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,20]]},"reference":[{"key":"63_CR1","doi-asserted-by":"crossref","unstructured":"Chen, Y., Pan, Y., Yao, T., Tian, X., Mei, T.: Mocycle-GAN: unpaired video-to-video translation. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 647\u2013655 (2019)","DOI":"10.1145\/3343031.3350937"},{"key":"63_CR2","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2758\u20132766 (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"63_CR3","doi-asserted-by":"crossref","unstructured":"Grabner, H., Gall, J., Van Gool, L.: What makes a chair a chair? In: CVPR 2011, pp. 1529\u20131536. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995327"},{"issue":"10","key":"63_CR4","doi-asserted-by":"publisher","first-page":"1775","DOI":"10.1109\/TPAMI.2009.83","volume":"31","author":"A Gupta","year":"2009","unstructured":"Gupta, A., Kembhavi, A., Davis, L.S.: Observing human-object interactions: using spatial and functional compatibility for recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31(10), 1775\u20131789 (2009)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"63_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"63_CR6","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: FlowNet 2.0: evolution of optical flow estimation with deep networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2462\u20132470 (2017)","DOI":"10.1109\/CVPR.2017.179"},{"key":"63_CR7","doi-asserted-by":"crossref","unstructured":"Kellnhofer, P., Recasens, A., Stent, S., Matusik, W., Torralba, A.: Gaze360: physically unconstrained gaze estimation in the wild. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6912\u20136921 (2019)","DOI":"10.1109\/ICCV.2019.00701"},{"key":"63_CR8","doi-asserted-by":"crossref","unstructured":"Liu, W., Luo, W., Lian, D., Gao, S.: Future frame prediction for anomaly detection-a new baseline. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6536\u20136545 (2018)","DOI":"10.1109\/CVPR.2018.00684"},{"key":"63_CR9","doi-asserted-by":"crossref","unstructured":"Liu, Z., Yao, L., Bai, L., Wang, X., Wang, C.: Spectrum-guided adversarial disparity learning. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 114\u2013124 (2020)","DOI":"10.1145\/3394486.3403054"},{"key":"63_CR10","unstructured":"Lotter, W., Kreiman, G., Cox, D.: Deep predictive coding networks for video prediction and unsupervised learning. arXiv preprint arXiv:1605.08104 (2016)"},{"key":"63_CR11","doi-asserted-by":"crossref","unstructured":"Lu, Y., Kumar, K.M., shahabeddin Nabavi, S., Wang, Y.: Future frame prediction using convolutional VRNN for anomaly detection. In: 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1\u20138. IEEE (2019)","DOI":"10.1109\/AVSS.2019.8909850"},{"key":"63_CR12","doi-asserted-by":"crossref","unstructured":"Mao, X., Li, Q., Xie, H., Lau, R.Y., Wang, Z., Paul Smolley, S.: Least squares generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2794\u20132802 (2017)","DOI":"10.1109\/ICCV.2017.304"},{"key":"63_CR13","unstructured":"Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error. In: 4th International Conference on Learning Representations, ICLR 2016 (2016)"},{"issue":"9","key":"63_CR14","doi-asserted-by":"publisher","first-page":"2678","DOI":"10.1109\/TIP.2011.2131660","volume":"20","author":"ND Narvekar","year":"2011","unstructured":"Narvekar, N.D., Karam, L.J.: A no-reference image blur metric based on the cumulative probability of blur detection (CPBD). IEEE Trans. Image Process. 20(9), 2678\u20132683 (2011)","journal-title":"IEEE Trans. Image Process."},{"key":"63_CR15","doi-asserted-by":"crossref","unstructured":"Park, S., Mello, S.D., Molchanov, P., Iqbal, U., Hilliges, O., Kautz, J.: Few-shot adaptive gaze estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9368\u20139377 (2019)","DOI":"10.1109\/ICCV.2019.00946"},{"key":"63_CR16","doi-asserted-by":"crossref","unstructured":"Pei, M., Jia, Y., Zhu, S.C.: Parsing video events with goal inference and intent prediction. In: 2011 International Conference on Computer Vision, pp. 487\u2013494. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126279"},{"key":"63_CR17","doi-asserted-by":"crossref","unstructured":"Ranjan, A., Black, M.J.: Optical flow estimation using a spatial pyramid network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4161\u20134170 (2017)","DOI":"10.1109\/CVPR.2017.291"},{"key":"63_CR18","doi-asserted-by":"crossref","unstructured":"Sadanand, S., Corso, J.J.: Action bank: a high-level representation of activity in video. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1234\u20131241. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"63_CR19","unstructured":"Sakita, K., Ogawara, K., Murakami, S., Kawamura, K., Ikeuchi, K.: Flexible cooperation between human and robot by interpreting human intention from gaze information. In: 2004 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), vol. 1, pp. 846\u2013851. IEEE (2004). (IEEE Cat. No. 04CH37566)"},{"issue":"11","key":"63_CR20","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.1016\/j.robot.2013.04.004","volume":"61","author":"C Schlenoff","year":"2013","unstructured":"Schlenoff, C., Pietromartire, A., Kootbally, Z., Balakirsky, S., Foufou, S.: Ontology-based state representations for intention recognition in human-robot collaborative environments. Robot. Auton. Syst. 61(11), 1224\u20131234 (2013)","journal-title":"Robot. Auton. Syst."},{"key":"63_CR21","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.T., Wang, G.: NTU RGB+D: a large scale dataset for 3D human activity analysis. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.115"},{"issue":"4","key":"63_CR22","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1177\/0018720816644364","volume":"58","author":"TB Sheridan","year":"2016","unstructured":"Sheridan, T.B.: Human-robot interaction: status and challenges. Hum. Factors 58(4), 525\u2013532 (2016)","journal-title":"Hum. Factors"},{"key":"63_CR23","doi-asserted-by":"crossref","unstructured":"Shotton, J., et al.: Real-time human pose recognition in parts from single depth images. In: CVPR 2011, pp. 1297\u20131304. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995316"},{"key":"63_CR24","unstructured":"Sung, J., Ponce, C., Selman, B., Saxena, A.: Unstructured human activity detection from RGBD images. In: 2012 IEEE International Conference on Robotics and Automation, pp. 842\u2013849. IEEE (2012)"},{"key":"63_CR25","doi-asserted-by":"crossref","unstructured":"Tang, K., Fei-Fei, L., Koller, D.: Learning latent temporal structure for complex event detection. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1250\u20131257. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247808"},{"key":"63_CR26","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: Advances in Neural Information Processing Systems, pp. 613\u2013621 (2016)"},{"issue":"4","key":"63_CR27","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"63_CR28","doi-asserted-by":"crossref","unstructured":"Wei, P., Liu, Y., Shu, T., Zheng, N., Zhu, S.C.: Where and why are they looking? Jointly inferring human attention and intentions in complex tasks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6801\u20136809 (2018)","DOI":"10.1109\/CVPR.2018.00711"},{"key":"63_CR29","unstructured":"Xingjian, S., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., Woo, W.C.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: Advances in Neural Information Processing Systems, pp. 802\u2013810 (2015)"},{"issue":"9","key":"63_CR30","doi-asserted-by":"publisher","first-page":"1691","DOI":"10.1109\/TPAMI.2012.67","volume":"34","author":"B Yao","year":"2012","unstructured":"Yao, B., Fei-Fei, L.: Recognizing human-object interactions in still images by modeling the mutual context of objects and human poses. IEEE Trans. Pattern Anal. Mach. Intell. 34(9), 1691\u20131703 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"63_CR31","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1007\/s00607-018-0603-z","volume":"100","author":"L Yao","year":"2018","unstructured":"Yao, L., et al.: WITS: an IoT-endowed computational framework for activity recognition in personalized smart homes. Computing 100(4), 369\u2013385 (2018)","journal-title":"Computing"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-63833-7_63","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T11:06:58Z","timestamp":1710328018000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-63833-7_63"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030638320","9783030638337"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-63833-7_63","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"20 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bangkok","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.apnns.org\/ICONIP2020","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"618","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"187","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"189","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"30% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.18","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.68","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to COVID-19 pandemic the conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}