{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T16:44:55Z","timestamp":1779122695369,"version":"3.51.4"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030687984","type":"print"},{"value":"9783030687991","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","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":[[2021]]},"DOI":"10.1007\/978-3-030-68799-1_18","type":"book-chapter","created":{"date-parts":[[2021,3,4]],"date-time":"2021-03-04T08:03:53Z","timestamp":1614845033000},"page":"250-264","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Skeleton-Based Methods for Speaker Action Classification on Lecture Videos"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9353-9528","authenticated-orcid":false,"given":"Fei","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6308-7113","authenticated-orcid":false,"given":"Kenny","family":"Davila","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7118-9280","authenticated-orcid":false,"given":"Srirangaraj","family":"Setlur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5318-7409","authenticated-orcid":false,"given":"Venu","family":"Govindaraju","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,3,5]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Xu, F., Davila, K., Setlur, S., Govindaraju, V.: Content extraction from lecture video via speaker action classification based on pose information. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1047\u20131054. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00171"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Davila, K., Agarwal, A., Gaborski, R., Zanibbi, R., Ludi, S.: Accessmath: indexing and retrieving video segments containing math expressions based on visual similarity. In: 2013 Western New York Image Processing Workshop (WNYIPW), pp. 14\u201317. IEEE (2013)","DOI":"10.1109\/WNYIPW.2013.6890981"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: 2019 Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12018\u201312027. IEEE\/CVF (2019)","DOI":"10.1109\/CVPR.2019.01230"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Cao, Z., Hidalgo, G., Simon, T., Wei, S., Sheikh, Y.: Openpose: realtime multi-person 2d pose estimation using part affinity fields. arXiv preprint arXiv:1812.08008 (2018)","DOI":"10.1109\/CVPR.2017.143"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: 2019 Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5693\u20135703. IEEE\/CVF (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"18_CR6","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.-Y., Girshick, R.: Detectron2 (2019). https:\/\/github.com\/facebookresearch\/detectron2"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Fang, H.-S., Xie, S., Tai, Y.-W., Lu., C.: Rmpe: regional multi-person pose estimation. In: 2017 International Conference on Computer Vision (ICCV), pp. 2353\u20132362. IEEE\/CVF (2017)","DOI":"10.1109\/ICCV.2017.256"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., Tian, Y., He, M.: Monocular human pose estimation: a survey of deep learning-based methods. Computer Vision and Image Understanding, pp. 102897 (2020)","DOI":"10.1016\/j.cviu.2019.102897"},{"issue":"1\u20132","key":"18_CR9","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The hungarian method for the assignment problem. Naval Res. Logistics Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logistics Q."},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: 2017 International Conference on Computer Vision (ICCV), pp. 2961\u20132969. IEEE\/CVF (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"18_CR11","unstructured":"Max Jaderberg, Karen Simonyan, Andrew Zisserman, et al. Spatial transformer networks. In Advances in neural information processing systems, pages 2017\u20132025, 2015"},{"key":"18_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked Hourglass Networks for Human Pose Estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"issue":"1","key":"18_CR13","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1109\/TCSVT.2014.2333151","volume":"25","author":"TV Nguyen","year":"2014","unstructured":"Nguyen, T.V., Song, Z., Yan, S.: Stap: spatial-temporal attention-aware pooling for action recognition. IEEE Trans. Circuits Syst. Video Technol. 25(1), 77\u201386 (2014)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"18_CR14","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1016\/j.eswa.2017.01.008","volume":"75","author":"Y Yi","year":"2017","unstructured":"Yi, Y., Zheng, Z., Lin, M.: Realistic action recognition with salient foreground trajectories. Expert Syst. Appl. 75, 44\u201355 (2017)","journal-title":"Expert Syst. Appl."},{"key":"18_CR15","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.knosys.2018.05.029","volume":"158","author":"P Wang","year":"2018","unstructured":"Wang, P., Li, W., Li, C., Hou, Y.: Action recognition based on joint trajectory maps with convolutional neural networks. Knowl.-Based Syst. 158, 43\u201353 (2018)","journal-title":"Knowl.-Based Syst."},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-second Conference on Artificial Intelligence (AAAI) (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Ma, D., Xie, B., Agam, G.: A machine learning based lecture video segmentation and indexing algorithm. In: Document Recognition and Retrieval XXI, vol. 9021, pp. 90210V. International Society for Optics and Photonics (2014)","DOI":"10.1117\/12.2042602"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Davila, K., Zanibbi, R.: Whiteboard video summarization via spatio-temporal conflict minimization. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 355\u2013362. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.66"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Davila, K., Zanibbi, R.: Visual search engine for handwritten and typeset math in lecture videos and latex notes. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 50\u201355. IEEE (2018)","DOI":"10.1109\/ICFHR-2018.2018.00018"},{"issue":"3","key":"18_CR20","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/s10032-019-00327-y","volume":"22","author":"BU Kota","year":"2019","unstructured":"Kota, B.U., Davila, K., Stone, A., Setlur, S., Govindaraju, V.: Generalized framework for summarization of fixed-camera lecture videos by detecting and binarizing handwritten content. Int. J. Doc. Anal. Recogn. (IJDAR) 22(3), 221\u2013233 (2019)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Soares, E.R., Barr\u00e9re, E.: An optimization model for temporal video lecture segmentation using word2vec and acoustic features. In: 25th Brazillian Symposium on Multimedia and the Web, pp. 513\u2013520 (2019)","DOI":"10.1145\/3323503.3349548"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Shah, R.R., Yu, Y., Shaikh, A.D., Zimmermann, R.: Trace: linguistic-based approach for automatic lecture video segmentation leveraging wikipedia texts. In: 2015 IEEE International Symposium on Multimedia (ISM), pp. 217\u2013220. IEEE (2015)","DOI":"10.1109\/ISM.2015.18"},{"issue":"2","key":"18_CR23","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/TLT.2014.2307305","volume":"7","author":"H Yang","year":"2014","unstructured":"Yang, H., Meinel, C.: Content based lecture video retrieval using speech and video text information. IEEE Trans. Learn. Technol. 7(2), 142\u2013154 (2014)","journal-title":"IEEE Trans. Learn. Technol."},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Radha, N.: Video retrieval using speech and text in video. In: 2016 International Conference on Inventive Computation Technologies (ICICT), vol. 2, pp. 1\u20136. IEEE (2016)","DOI":"10.1109\/INVENTIVE.2016.7824801"},{"key":"18_CR25","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"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition. ICPR International Workshops and Challenges"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-68799-1_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,20]],"date-time":"2022-12-20T00:10:23Z","timestamp":1671495023000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-68799-1_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030687984","9783030687991"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-68799-1_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"5 March 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 January 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ICPR2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icpr2020.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}