{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T03:15:09Z","timestamp":1778210109866,"version":"3.51.4"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030110116","type":"print"},{"value":"9783030110123","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-11012-3_9","type":"book-chapter","created":{"date-parts":[[2019,1,28]],"date-time":"2019-01-28T17:50:19Z","timestamp":1548697819000},"page":"117-128","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":64,"title":["UAV-GESTURE: A Dataset for UAV Control and Gesture Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4021-3943","authenticated-orcid":false,"given":"Asanka G.","family":"Perera","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5665-0980","authenticated-orcid":false,"given":"Yee Wei","family":"Law","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6496-0543","authenticated-orcid":false,"given":"Javaan","family":"Chahl","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,1,29]]},"reference":[{"key":"9_CR1","doi-asserted-by":"publisher","unstructured":"Barekatain, M., et al.: Okutama-action: an aerial view video dataset for concurrent human action detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 2153\u20132160, July 2017. https:\/\/doi.org\/10.1109\/CVPRW.2017.267","DOI":"10.1109\/CVPRW.2017.267"},{"key":"9_CR2","doi-asserted-by":"publisher","unstructured":"Bonetto, M., Korshunov, P., Ramponi, G., Ebrahimi, T.: Privacy in mini-drone based video surveillance. In: 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), vol. 04, pp. 1\u20136, May 2015. https:\/\/doi.org\/10.1109\/FG.2015.7285023","DOI":"10.1109\/FG.2015.7285023"},{"key":"9_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/978-3-540-24673-2_3","volume-title":"Computer Vision - ECCV 2004","author":"T Brox","year":"2004","unstructured":"Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25\u201336. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-24673-2_3"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"9_CR5","unstructured":"Carol Neidle, A.T., Sclaroff, S.: 5th Workshop on the Representation and Processing of Sign Languages: Interactions Between Corpus and Lexicon, May 2012"},{"issue":"6","key":"9_CR6","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1016\/j.cviu.2013.01.013","volume":"117","author":"JM Chaquet","year":"2013","unstructured":"Chaquet, J.M., Carmona, E.J., Fern\u00e1ndez-Caballero, A.: A survey of video datasets for human action and activity recognition. Comput. Vis. Image Underst. 117(6), 633\u2013659 (2013). https:\/\/doi.org\/10.1016\/j.cviu.2013.01.013. http:\/\/www.sciencedirect.com\/science\/article\/pii\/S1077314213000295","journal-title":"Comput. Vis. Image Underst."},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Chatfield, K., Simonyan, K., Vedaldi, A., Zisserman, A.: Return of the devil in the details: delving deep into convolutional nets. CoRR abs\/1405.3531 (2014). http:\/\/arxiv.org\/abs\/1405.3531","DOI":"10.5244\/C.28.6"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Cherian, A., Mairal, J., Alahari, K., Schmid, C.: Mixing body-part sequences for human pose estimation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2014","DOI":"10.1109\/CVPR.2014.302"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Cheron, G., Laptev, I., Schmid, C.: P-CNN: pose-based CNN features for action recognition. In: The IEEE International Conference on Computer Vision (ICCV), December 2015","DOI":"10.1109\/ICCV.2015.368"},{"key":"9_CR10","doi-asserted-by":"publisher","unstructured":"Costante, G., Bellocchio, E., Valigi, P., Ricci, E.: Personalizing vision-based gestural interfaces for HRI with UAVs: a transfer learning approach. In: 2014 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 3319\u20133326, September 2014. https:\/\/doi.org\/10.1109\/IROS.2014.6943024","DOI":"10.1109\/IROS.2014.6943024"},{"key":"9_CR11","unstructured":"Girdhar, R., Ramanan, D.: Attentional pooling for action recognition. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 34\u201345. Curran Associates, Inc. (2017). http:\/\/papers.nips.cc\/paper\/6609-attentional-pooling-for-action-recognition.pdf"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Malik, J.: Finding action tubes. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015","DOI":"10.1109\/CVPR.2015.7298676"},{"issue":"8","key":"9_CR13","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1007\/s00138-014-0596-3","volume":"25","author":"I Guyon","year":"2014","unstructured":"Guyon, I., Athitsos, V., Jangyodsuk, P., Escalante, H.J.: The ChaLearn gesture dataset (CGD 2011). Mach. Vis. Appl. 25(8), 1929\u20131951 (2014)","journal-title":"Mach. Vis. Appl."},{"key":"9_CR14","doi-asserted-by":"publisher","unstructured":"Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.J.: Towards understanding action recognition. In: 2013 IEEE International Conference on Computer Vision, pp. 3192\u20133199, December 2013. https:\/\/doi.org\/10.1109\/ICCV.2013.396","DOI":"10.1109\/ICCV.2013.396"},{"key":"9_CR15","unstructured":"Kang, S., Wildes, R.P.: Review of action recognition and detection methods. CoRR abs\/1610.06906 (2016). http:\/\/arxiv.org\/abs\/org\/1610.06906"},{"key":"9_CR16","doi-asserted-by":"publisher","unstructured":"Lee, J., Tan, H., Crandall, D., \u0160abanovi\u0107, S.: Forecasting hand gestures for human-drone interaction. In: Companion of the 2018 ACM\/IEEE International Conference on Human-Robot Interaction, HRI 2018, pp. 167\u2013168. ACM, New York (2018). https:\/\/doi.org\/10.1145\/3173386.3176967","DOI":"10.1145\/3173386.3176967"},{"key":"9_CR17","doi-asserted-by":"publisher","unstructured":"Lin, Z., Jiang, Z., Davis, L.S.: Recognizing actions by shape-motion prototype trees. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 444\u2013451, September 2009. https:\/\/doi.org\/10.1109\/ICCV.2009.5459184","DOI":"10.1109\/ICCV.2009.5459184"},{"key":"9_CR18","doi-asserted-by":"publisher","unstructured":"Oh, S., et al.: A large-scale benchmark dataset for event recognition in surveillance video. In: CVPR 2011, pp. 3153\u20133160 (2011). https:\/\/doi.org\/10.1109\/CVPR.2011.5995586","DOI":"10.1109\/CVPR.2011.5995586"},{"key":"9_CR19","doi-asserted-by":"publisher","unstructured":"Pfeil, K., Koh, S.L., LaViola, J.: Exploring 3D gesture metaphors for interaction with unmanned aerial vehicles. In: Proceedings of the 2013 International Conference on Intelligent User Interfaces, IUI 2013, pp. 257\u2013266. ACM, New York (2013). https:\/\/doi.org\/10.1145\/2449396.2449429","DOI":"10.1145\/2449396.2449429"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Piergiovanni, A.J., Ryoo, M.S.: Fine-grained activity recognition in baseball videos. CoRR abs\/1804.03247 (2018). http:\/\/arxiv.org\/abs\/1804.03247","DOI":"10.1109\/CVPRW.2018.00226"},{"key":"9_CR21","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/j.cviu.2015.08.004","volume":"141","author":"PK Pisharady","year":"2015","unstructured":"Pisharady, P.K., Saerbeck, M.: Recent methods and databases in vision-based hand gesture recognition: a review. Comput. Vis. Image Underst. 141, 152\u2013165 (2015). https:\/\/doi.org\/10.1016\/j.cviu.2015.08.004. http:\/\/www.sciencedirect.com\/science\/article\/pii\/S1077314215001794","journal-title":"Comput. Vis. Image Underst."},{"key":"9_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/978-3-319-46484-8_33","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Robicquet","year":"2016","unstructured":"Robicquet, A., Sadeghian, A., Alahi, A., Savarese, S.: Learning social etiquette: human trajectory understanding in crowded scenes. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 549\u2013565. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_33"},{"key":"9_CR23","doi-asserted-by":"publisher","unstructured":"Rohrbach, M., Amin, S., Andriluka, M., Schiele, B.: A database for fine grained activity detection of cooking activities. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1194\u20131201, June 2012. https:\/\/doi.org\/10.1109\/CVPR.2012.6247801","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"9_CR24","doi-asserted-by":"publisher","unstructured":"Ruffieux, S., Lalanne, D., Mugellini, E.: ChAirGest: a challenge for multimodal mid-air gesture recognition for close HCI. In: Proceedings of the 15th ACM on International Conference on Multimodal Interaction, ICMI 2013, pp. 483\u2013488. ACM, New York (2013). https:\/\/doi.org\/10.1145\/2522848.2532590","DOI":"10.1145\/2522848.2532590"},{"key":"9_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1007\/978-3-319-07230-2_33","volume-title":"Human-Computer Interaction. Advanced Interaction Modalities and Techniques","author":"S Ruffieux","year":"2014","unstructured":"Ruffieux, S., Lalanne, D., Mugellini, E., Abou Khaled, O.: A survey of datasets for human gesture recognition. In: Kurosu, M. (ed.) HCI 2014. LNCS, vol. 8511, pp. 337\u2013348. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-07230-2_33"},{"key":"9_CR26","doi-asserted-by":"publisher","unstructured":"Ryoo, M.S., Aggarwal, J.K.: Spatio-temporal relationship match: video structure comparison for recognition of complex human activities. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 1593\u20131600, September 2009. https:\/\/doi.org\/10.1109\/ICCV.2009.5459361","DOI":"10.1109\/ICCV.2009.5459361"},{"key":"9_CR27","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: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016","DOI":"10.1109\/CVPR.2016.115"},{"key":"9_CR28","doi-asserted-by":"publisher","unstructured":"Song, Y., Demirdjian, D., Davis, R.: Tracking body and hands for gesture recognition: NATOPS aircraft handling signals database. In: Face and Gesture 2011, pp. 500\u2013506, March 2011. https:\/\/doi.org\/10.1109\/FG.2011.5771448","DOI":"10.1109\/FG.2011.5771448"},{"key":"9_CR29","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. Technical report. UCF Center for Research in Computer Vision (2012)"},{"key":"9_CR30","unstructured":"University of Central Florida: UCF aerial action dataset, November 2011. http:\/\/crcv.ucf.edu\/data\/UCF_Aerial_Action.php"},{"key":"9_CR31","unstructured":"University of Central Florida: UCF-ARG Data Set, November 2011. http:\/\/crcv.ucf.edu\/data\/UCF-ARG.php"},{"key":"9_CR32","unstructured":"U.S. Navy: Aircraft signals NATOPS manual, NAVAIR 00\u201380t-113 (1997). http:\/\/www.navybmr.com\/study%20material\/NAVAIR_113.pdf"},{"issue":"1","key":"9_CR33","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1007\/s11263-012-0564-1","volume":"101","author":"C Vondrick","year":"2013","unstructured":"Vondrick, C., Patterson, D., Ramanan, D.: Efficiently scaling up crowdsourced video annotation. Int. J. Comput. Vis. 101(1), 184\u2013204 (2013). https:\/\/doi.org\/10.1007\/s11263-012-0564-1","journal-title":"Int. J. Comput. Vis."},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016","DOI":"10.1109\/CVPR.2016.511"},{"key":"9_CR35","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. CoRR abs\/1801.07455 (2018). http:\/\/arxiv.org\/abs\/1801.07455"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-11012-3_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,28]],"date-time":"2023-01-28T03:10:47Z","timestamp":1674875447000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-11012-3_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030110116","9783030110123"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-11012-3_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"29 January 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}