{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T12:09:33Z","timestamp":1742990973626,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030976712"},{"type":"electronic","value":"9783030976729"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-030-97672-9_29","type":"book-chapter","created":{"date-parts":[[2022,3,31]],"date-time":"2022-03-31T04:03:10Z","timestamp":1648699390000},"page":"323-335","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Various-Level Spatio-Temporal Alignment for Cross-Domain Action Recognition"],"prefix":"10.1007","author":[{"given":"Hyungmin","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dohyung","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaehong","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,4,1]]},"reference":[{"issue":"4","key":"29_CR1","doi-asserted-by":"publisher","first-page":"494","DOI":"10.4218\/etrij.2018-0520","volume":"41","author":"K Yun","year":"2019","unstructured":"Yun, K., Kwon, Y., Oh, S., Moon, J., Park, J.: Vision-based garbage dumping action detection for real-world surveillance platform. ETRI J. 41(4), 494\u2013505 (2019)","journal-title":"ETRI J."},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Nie, Q., Wang, X., et al.: A child caring robot for the dangerous behavior detection based on the object recognition and human action recognition. In: IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 1921\u20131926 (2018)","DOI":"10.1109\/ROBIO.2018.8665218"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., et al.: SlowFast networks for video recognition. In: ICCV, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"29_CR4","doi-asserted-by":"publisher","unstructured":"Das, S., Sharma, S., Dai, R., Br\u00e9mond, F., Thonnat, M.: VPN: learning video-pose embedding for activities of daily living. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 72\u201390. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_5","DOI":"10.1007\/978-3-030-58545-7_5"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., et al.: NTU RGB+D: a large scale dataset for 3d human activity analysis. In: CVPR, pp. 1010\u20131019 (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"29_CR6","unstructured":"Kay, W., Carreira, J., et al.: The kinetics human action video dataset. arXiv (2017)"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Jang, J., Kim, D., et al.: ETRI-activity3D: a large-scale RGB-D dataset for robots to recognize daily activities of the elderly. In: IROS, pp. 10990\u201310997 (2020)","DOI":"10.1109\/IROS45743.2020.9341160"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Kim, H., Kim, D., et al.: ETRI-activity3D: learning multi-modal attentional consensus in action recognition for elderly-care robots. In: International Conference on Ubiquitous Robots, pp. 308\u2013313 (2021)","DOI":"10.1109\/UR52253.2021.9494666"},{"key":"29_CR9","unstructured":"Goodfellow, I., Pouget-Abadie., et al.: Generative adversarial nets. In: NIPS, p. 27 (2014)"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Bousmalis, K., Silberman, N., et al.: Unsupervised pixel-level domain adaptation with generative adversarial networks. In: CVPR, pp. 3722\u20133731 (2017)","DOI":"10.1109\/CVPR.2017.18"},{"issue":"1","key":"29_CR11","first-page":"2096","volume":"17","author":"Y Ganin","year":"2016","unstructured":"Ganin, Y., Ustinova, E., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2096\u20132030 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Y., Li, W., et al.: Domain adaptive faster R-CNN for object detection in the wild. In: CVPR, pp. 3339\u20133348 (2018)","DOI":"10.1109\/CVPR.2018.00352"},{"key":"29_CR13","unstructured":"Hoffman, J., Tzeng, E., et al.: CyCADA: cycle-consistent adversarial domain adaptation. In: ICML, pp. 1989\u20131998 (2018)"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Chen, M.-H. and Kira, Z., et al.: Temporal attentive alignment for large-scale video domain adaptation. In: ICCV, pp. 6321\u20136330 (2019)","DOI":"10.1109\/ICCV.2019.00642"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Pan, B. and Cao, Z., et al.: Adversarial cross-domain action recognition with co-attention. In: AAAI, pp. 11815\u201311822 (2020)","DOI":"10.1609\/aaai.v34i07.6854"},{"key":"29_CR16","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1109\/TIP.2020.3038372","volume":"30","author":"Z Gao","year":"2020","unstructured":"Gao, Z., Guo, L., et al.: A pairwise attentive adversarial spatiotemporal network for cross-domain few-shot action recognition-R2. IEEE Trans. Image Process. 30, 767\u2013782 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"29_CR17","unstructured":"Hermann, K., Chen, T., et al.: The origins and prevalence of texture bias in convolutional neural networks. In: NeurIPS (2020)"},{"key":"29_CR18","doi-asserted-by":"publisher","unstructured":"Choi, J., Sharma, G., Schulter, S., Huang, J.B.: Shuffle and attend: video domain adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 678\u2013695. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_40","DOI":"10.1007\/978-3-030-58610-2_40"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Chen, C.-F.R., Panda, R., et al.: Deep analysis of CNN-based spatio-temporal representations for action recognition. In: CVPR, pp. 6165\u20136175 (2021)","DOI":"10.1109\/CVPR46437.2021.00610"},{"key":"29_CR20","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS, pp. 568\u2013576 (2014)"},{"key":"29_CR21","doi-asserted-by":"publisher","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C. Fan, H., et al.: SlowFast networks for video recognition. In: ICCV, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., et al.: TSM: temporal shift module for efficient video understanding. In: ICCV, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., et al.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A., et al.: Quo vadis, action recognition? A new model and the kinetics dataset. In: CVPR, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., et al.: A closer look at spatiotemporal convolutions for action recognition. In: CVPR, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"29_CR27","doi-asserted-by":"publisher","unstructured":"Zolfaghari, M., Singh, K., Brox, T.: ECO: efficient convolutional network for online video understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 713\u2013730. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_43","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"29_CR28","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/j.eswa.2016.09.026","volume":"66","author":"K Charalampous","year":"2016","unstructured":"Charalampous, K., Kostavelis, I., et al.: Robot navigation in large-scale social maps: an action recognition approach. Expert Syst. Appl. 66, 261\u2013273 (2016)","journal-title":"Expert Syst. Appl."},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"Mundher, Z., A., Zhong, J., et al.: A real-time fall detection system in elderly care using mobile robot and kinect sensor. Intl. J. Mater. Mech. Manuf. 2(2), 133\u2013138 (2014)","DOI":"10.7763\/IJMMM.2014.V2.115"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Efthymiou, N., Koutras, P., et al.: Multi-view fusion for action recognition in child-robot interaction In: IEEE International Conference on Image Processing (ICIP), pp. 455\u2013459 (2018)","DOI":"10.1109\/ICIP.2018.8451146"},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Zhao, X., Naguib, A., et al.: Kinect based calling gesture recognition for taking order service of elderly care robot. In: International Symposium on Robot and Human Interactive Communication, pp. 525\u2013530 (2014)","DOI":"10.1109\/ROMAN.2014.6926306"},{"key":"29_CR32","unstructured":"Jamal, A., Namboodiri, V.P., et al.: Deep domain adaptation in action space. In: BMVC, vol. 2, no. 3, p. 5 (2018)"},{"key":"29_CR33","doi-asserted-by":"publisher","unstructured":"Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 831\u2013846. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_49","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"29_CR34","doi-asserted-by":"crossref","unstructured":"Pan, B., Cao, Z., et al.: Adversarial cross-domain action recognition with co-attention. In: AAAI, vol. 34, no. 7, pp. 11815\u201311822 (2020)","DOI":"10.1609\/aaai.v34i07.6854"},{"key":"29_CR35","doi-asserted-by":"crossref","unstructured":"Fernando, B., Herath, S.: Anticipating human actions by correlating past with the future with Jaccard similarity measures. In: CVPR, pp. 13224\u201313233 (2021)","DOI":"10.1109\/CVPR46437.2021.01302"},{"key":"29_CR36","doi-asserted-by":"crossref","unstructured":"Sultani, W., Saleemi, I.: Human action recognition across datasets by foreground-weighted histogram decomposition. In: CVPR, pp. 764\u2013771 (2014)","DOI":"10.1109\/CVPR.2014.103"},{"key":"29_CR37","doi-asserted-by":"crossref","unstructured":"Song, X., Zhao, S., et al.: Human action recognition across datasets by foreground-weighted histogram decomposition. In: CVPR, pp. 764\u2013771 (2014)","DOI":"10.1109\/CVPR.2014.103"}],"container-title":["Lecture Notes in Networks and Systems","Robot Intelligence Technology and Applications 6"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-97672-9_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,21]],"date-time":"2024-09-21T09:28:50Z","timestamp":1726910930000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-97672-9_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030976712","9783030976729"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-97672-9_29","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"1 April 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"RiTA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Robot Intelligence Technology and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"rita2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}