{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T06:33:17Z","timestamp":1775197997979,"version":"3.50.1"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030377304","type":"print"},{"value":"9783030377311","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,12,24]],"date-time":"2019-12-24T00:00:00Z","timestamp":1577145600000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-37731-1_58","type":"book-chapter","created":{"date-parts":[[2019,12,27]],"date-time":"2019-12-27T01:02:51Z","timestamp":1577408571000},"page":"714-726","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Cross Fusion for Egocentric Interactive Action Recognition"],"prefix":"10.1007","author":[{"given":"Haiyu","family":"Jiang","sequence":"first","affiliation":[]},{"given":"Yan","family":"Song","sequence":"additional","affiliation":[]},{"given":"Jiang","family":"He","sequence":"additional","affiliation":[]},{"given":"Xiangbo","family":"Shu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,12,24]]},"reference":[{"key":"58_CR1","doi-asserted-by":"crossref","unstructured":"Tsutsui, S., Bambach, S., Crandall, D., Yu, C.: Estimating head motion from egocentric vision. In: Proceedings of the 20th ACM International Conference on Multimodal Interaction, ICMI 2018, pp. 342\u2013346. ACM, New York (2018)","DOI":"10.1145\/3242969.3242982"},{"key":"58_CR2","doi-asserted-by":"crossref","unstructured":"Ryoo, M.S., Matthies, L.: First-person activity recognition: what are they doing to me? In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2730\u20132737, June 2013","DOI":"10.1109\/CVPR.2013.352"},{"key":"58_CR3","doi-asserted-by":"crossref","unstructured":"Xia, L., Gori, I., Aggarwal, J.K., Ryoo, M.S.: Robot-centric activity recognition from first-person RGB-D videos. In: 2015 IEEE Winter Conference on Applications of Computer Vision, pp. 357\u2013364, January 2015","DOI":"10.1109\/WACV.2015.54"},{"key":"58_CR4","doi-asserted-by":"crossref","unstructured":"Mishra, S.R., Mishra, T.K., Sarkar, A., Sanyal, G.: PSO based combined kernel learning framework for recognition of first-person activity in a video. Evol. Intell. (2018)","DOI":"10.1007\/s12065-018-0177-x"},{"issue":"5","key":"58_CR5","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.3390\/s19051005","volume":"19","author":"Hong-Bo Zhang","year":"2019","unstructured":"Zhang, H.B., Zhang, Y.X., Zhong, B., Lei, Q., Yang, L., Du, J.X., Chen, D.S.: A comprehensive survey of vision-based human action recognition methods. Sensors 19(5) (2019)","journal-title":"Sensors"},{"key":"58_CR6","doi-asserted-by":"crossref","unstructured":"Zaki, H.F.M., Shafait, F., Mian, A.: Modeling sub-event dynamics in first-person action recognition. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1619\u20131628, July 2017","DOI":"10.1109\/CVPR.2017.176"},{"key":"58_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/978-3-319-73600-6_14","volume-title":"MultiMedia Modeling","author":"L Fa","year":"2018","unstructured":"Fa, L., Song, Y., Shu, X.: Global and local C3D ensemble system for first person interactive action recognition. In: Schoeffmann, K., Chalidabhongse, T.H., Ngo, C.W., Aramvith, S., O\u2019Connor, N.E., Ho, Y.-S., Gabbouj, M., Elgammal, A. (eds.) MMM 2018. LNCS, vol. 10705, pp. 153\u2013164. Springer, Cham (2018). \nhttps:\/\/doi.org\/10.1007\/978-3-319-73600-6_14"},{"key":"58_CR8","doi-asserted-by":"crossref","unstructured":"Ma, M., Fan, H., Kitani, K.M.: Going deeper into first-person activity recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1894\u20131903, June 2016","DOI":"10.1109\/CVPR.2016.209"},{"key":"58_CR9","doi-asserted-by":"crossref","unstructured":"Abebe, G., Cavallaro, A.: A long short-term memory convolutional neural network for first-person vision activity recognition. In: 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 1339\u20131346, October 2017","DOI":"10.1109\/ICCVW.2017.159"},{"key":"58_CR10","doi-asserted-by":"crossref","unstructured":"Iwashita, Y., Takamine, A., Kurazume, R., Ryoo, M.S.: First-person animal activity recognition from egocentric videos. In: 2014 22nd International Conference on Pattern Recognition, pp. 4310\u20134315, August 2014","DOI":"10.1109\/ICPR.2014.739"},{"key":"58_CR11","doi-asserted-by":"crossref","unstructured":"Yudistira, N., Kurita, T.: Temporal evolution of motion superpixel for video classification. In: 2017 3rd IEEE International Conference on Cybernetics (CYBCONF), pp. 1\u20136, June 2017","DOI":"10.1109\/CYBConf.2017.7985816"},{"key":"58_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., Van Gool, L.: 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). \nhttps:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"58_CR13","doi-asserted-by":"crossref","unstructured":"Song, S., Chandrasekhar, V., Mandal, B., Li, L., Lim, J., Babu, G.S., San, P.P., Cheung, N.: Multimodal multi-stream deep learning for egocentric activity recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 378\u2013385, June 2016","DOI":"10.1109\/CVPRW.2016.54"},{"key":"58_CR14","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Proceedings of the 27th International Conference on Neural Information Processing Systems, Cambridge, MA, USA, pp. 568\u2013576 (2014)"},{"key":"58_CR15","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of the 2013 IEEE International Conference on Computer Vision, ICCV 2013, pp. 3551\u20133558. IEEE Computer Society, Washington, DC (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"58_CR16","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), ICCV 2015, pp. 4489\u20134497. IEEE Computer Society, Washington, DC (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"58_CR17","doi-asserted-by":"crossref","unstructured":"Khong, V., Tran, T.: Improving human action recognition with two-stream 3D convolutional neural network. In: 2018 1st International Conference on Multimedia Analysis and Pattern Recognition (MAPR), pp. 1\u20136, April 2018","DOI":"10.1109\/MAPR.2018.8337518"},{"key":"58_CR18","doi-asserted-by":"crossref","unstructured":"Poleg, Y., Ephrat, A., Peleg, S., Arora, C.: Compact CNN for indexing egocentric videos. In: 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1\u20139, March 2016","DOI":"10.1109\/WACV.2016.7477708"},{"key":"58_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/978-3-642-27355-1_18","volume-title":"Advances in Multimedia Modeling","author":"Z Lan","year":"2012","unstructured":"Lan, Z., Bao, L., Yu, S.-I., Liu, W., Hauptmann, A.G.: Double fusion for multimedia event detection. In: Schoeffmann, K., Merialdo, B., Hauptmann, A.G., Ngo, C.-W., Andreopoulos, Y., Breiteneder, C. (eds.) MMM 2012. LNCS, vol. 7131, pp. 173\u2013185. Springer, Heidelberg (2012). \nhttps:\/\/doi.org\/10.1007\/978-3-642-27355-1_18"},{"issue":"6","key":"58_CR20","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/TPAMI.2017.2712608","volume":"40","author":"G Varol","year":"2018","unstructured":"Varol, G., Laptev, I., Schmid, C.: Long-term temporal convolutions for action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1510\u20131517 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"58_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1007\/978-3-319-46478-7_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Shen","year":"2016","unstructured":"Shen, L., Lin, Z., Huang, Q.: Relay backpropagation for effective learning of deep convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 467\u2013482. Springer, Cham (2016). \nhttps:\/\/doi.org\/10.1007\/978-3-319-46478-7_29"},{"key":"58_CR22","doi-asserted-by":"crossref","unstructured":"Moreira, T.P., Menotti, D., Pedrini, H.: First-person action recognition through visual rhythm texture description. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2627\u20132631, March 2017","DOI":"10.1109\/ICASSP.2017.7952632"},{"key":"58_CR23","doi-asserted-by":"crossref","unstructured":"Takamine, A., Iwashita, Y., Kurazume, R.: First-person activity recognition with C3D features from optical flow images. In: 2015 IEEE\/SICE International Symposium on System Integration (SII), pp. 619\u2013622, December 2015","DOI":"10.1109\/SII.2015.7405050"},{"key":"58_CR24","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.patrec.2018.07.011","volume":"112","author":"H Kwon","year":"2018","unstructured":"Kwon, H., Kim, Y., Lee, J.S., Cho, M.: First person action recognition via two-stream convnet with long-term fusion pooling. Pattern Recogn. Lett. 112, 161\u2013167 (2018)","journal-title":"Pattern Recogn. Lett."}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-37731-1_58","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,6]],"date-time":"2020-02-06T11:24:17Z","timestamp":1580988257000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-37731-1_58"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,24]]},"ISBN":["9783030377304","9783030377311"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-37731-1_58","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12,24]]},"assertion":[{"value":"24 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 January 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 January 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.mmm2020.kr\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"171","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":"40","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":"23% - 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":"5","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Of the 171 submissions, 46 were accepted as poster papers; of the 49 special session paper submissions, 28 were accepted for oral presentation and 8 for poster presentation; 9 demo papers and 10 VBS papers were also accepted.","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)"}}]}}