{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T07:23:53Z","timestamp":1743146633160,"version":"3.40.3"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030208691"},{"type":"electronic","value":"9783030208707"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-20870-7_14","type":"book-chapter","created":{"date-parts":[[2019,5,24]],"date-time":"2019-05-24T16:14:21Z","timestamp":1558714461000},"page":"223-239","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning from PhotoShop Operation Videos: The PSOV Dataset"],"prefix":"10.1007","author":[{"given":"Jingchun","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han-Kai","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hailin","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengjin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,25]]},"reference":[{"issue":"13","key":"14_CR1","first-page":"1608","volume":"29","author":"P Abbeel","year":"2010","unstructured":"Abbeel, P., Coates, A., Ng, A.Y.: Autonomous helicopter aerobatics through apprenticeship learning. IJRR 29(13), 1608\u20131639 (2010)","journal-title":"IJRR"},{"key":"14_CR2","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Caelles, S., Maninis, K.K., Pont-Tuset, J., Leal-Taix\u00e9, L., Cremers, D., Van Gool, L.: One-shot video object segmentation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.565"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Chen, C., Seff, A., Kornhauser, A., Xiao, J.: DeepDriving: learning affordance for direct perception in autonomous driving. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.312"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3D object detection network for autonomous driving. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.691"},{"key":"14_CR6","unstructured":"Cheng, J., et al.: Learning to segment instances in videos with spatial propagation network. arXiv preprint arXiv:1709.04609 (2017)"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, J., Tsai, Y.H., Wang, S., Yang, M.H.: SegFlow: joint learning for video object segmentation and optical flow. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.81"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"14_CR11","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: CARLA: an open urban driving simulator. In: CoRL (2017)"},{"issue":"2","key":"14_CR12","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The Pascal visual object classes (VOC) challenge. IJCV 88(2), 303\u2013338 (2010)","journal-title":"IJCV"},{"issue":"11","key":"14_CR13","first-page":"1231","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. IJRR 32(11), 1231\u20131237 (2013)","journal-title":"IJRR"},{"key":"14_CR14","unstructured":"Gelly, S., Silver, D.: Achieving master level play in 9 $$\\times $$ 9 computer go. In: AAAI (2008)"},{"issue":"11","key":"14_CR15","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1016\/j.artint.2011.03.007","volume":"175","author":"S Gelly","year":"2011","unstructured":"Gelly, S., Silver, D.: Monte-Carlo tree search and rapid action value estimation in computer go. Artif. Intill. 175(11), 1856\u20131875 (2011)","journal-title":"Artif. Intill."},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Ramanan, D., Gupta, A., Sivic, J., Russell, B.: ActionVLAD: learning spatio-temporal aggregation for action classification. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.337"},{"key":"14_CR17","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.179"},{"issue":"1","key":"14_CR18","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. PAMI 35(1), 495\u2013502 (2013)","journal-title":"PAMI"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"14_CR20","unstructured":"Khoreva, A., Benenson, R., Ilg, E., Brox, T., Schiele, B.: Lucid data dreaming for multiple object tracking. arXiv preprint arXiv:1703.09554 (2017)"},{"issue":"1","key":"14_CR21","first-page":"34","volume":"16","author":"M Kim","year":"2009","unstructured":"Kim, M., Kim, S., Park, S., Choi, M.T., Kim, M., Gomaa, H.: Service robot for the elderly. RAM 16(1), 34\u201345 (2009)","journal-title":"RAM"},{"issue":"12","key":"14_CR22","first-page":"1705","volume":"53","author":"S Lef\u00e8vre","year":"2015","unstructured":"Lef\u00e8vre, S., Carvalho, A., Gao, Y., Tseng, H.E., Borrelli, F.: Driver models for personalised driving assistance. VSD 53(12), 1705\u20131720 (2015)","journal-title":"VSD"},{"key":"14_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"14_CR24","unstructured":"Oh, J., Guo, X., Lee, H., Lewis, R.L., Singh, S.: Action-conditional video prediction using deep networks in atari games. In: NIPS (2015)"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Revaud, J., Weinzaepfel, P., Harchaoui, Z., Schmid, C.: EpicFlow: edge-preserving interpolation of correspondences for optical flow. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298720"},{"key":"14_CR26","unstructured":"Rhee, C., Chung, W., Kim, M., Shim, Y., Lee, H.: Door opening control using the multi-fingered robotic hand for the indoor service robot. In: ICRA (2004)"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Rodriguez, M.D., Ahmed, J., Shah, M.: Action mach a spatio-temporal maximum average correlation height filter for action recognition. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"14_CR28","unstructured":"Shashua, A., Gdalyahu, Y., Hayun, G.: Pedestrian detection for driving assistance systems: single-frame classification and system level performance. In: IEEE Intelligent Vehicles Symposium, 2004, pp. 1\u20136. IEEE, June 2004"},{"key":"14_CR29","unstructured":"Shi, T., Karpathy, A., Fan, L., Hernandez, J., Liang, P.: World of bits: an open-domain platform for web-based agents. In: ICML (2017)"},{"key":"14_CR30","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550, 354\u2013359 (2017)","journal-title":"Nature"},{"key":"14_CR31","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS (2014)"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Song, S., Lan, C., Xing, J., Zeng, W., Liu, J.: An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In: AAAI (2017)","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"14_CR33","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. CoRR (2012)"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Sturm, J., Engelhard, N., Endres, F., Burgard, W., Cremers, D.: A benchmark for the evaluation of RGB-D SLAM systems. In: IROS (2012)","DOI":"10.1109\/IROS.2012.6385773"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Sun, D., Yang, X., Liu, M.Y., Kautz, J.: PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00931"},{"key":"14_CR36","unstructured":"Taggart, W., Turkle, S., Kidd, C.D.: An interactive robot in a nursing home: preliminary remarks. In: COGSCI Workshop (2005)"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.510"},{"issue":"6","key":"14_CR38","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/TPAMI.2017.2712608","volume":"40","author":"G Varol","year":"2017","unstructured":"Varol, G., Laptev, I., Schmid, C.: Long-term temporal convolutions for action recognition. PAMI 40(6), 1510\u20131517 (2017)","journal-title":"PAMI"},{"key":"14_CR39","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Leibe, B.: Online adaptation of convolutional neural networks for video object segmentation. arXiv preprint arXiv:1706.09364 (2017)","DOI":"10.5244\/C.31.116"},{"issue":"1","key":"14_CR40","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1109\/TCIAIG.2015.2504108","volume":"9","author":"J Wang","year":"2017","unstructured":"Wang, J., Xiao, C., Zhu, T., Hsueh, C.H., Tseng, W.J., Wu, I.C.: Only-one-victor pattern learning in computer go. IEEE Trans. Comput. Intell. AI Games 9(1), 88\u2013102 (2017)","journal-title":"IEEE Trans. Comput. Intell. AI Games"},{"key":"14_CR41","doi-asserted-by":"crossref","unstructured":"Yannakakis, G.N.: Game AI revisited. In: CF (2012)","DOI":"10.1145\/2212908.2212954"},{"key":"14_CR42","doi-asserted-by":"crossref","unstructured":"Yue-Hei Ng, J., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299101"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20870-7_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,18]],"date-time":"2022-09-18T16:19:25Z","timestamp":1663517965000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-20870-7_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208691","9783030208707"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20870-7_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"25 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"979","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":"274","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":"0","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":"28% - 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","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":"2.7","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)"}}]}}