{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T18:37:45Z","timestamp":1743014265362,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030863616"},{"type":"electronic","value":"9783030863623"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/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":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86362-3_29","type":"book-chapter","created":{"date-parts":[[2021,9,11]],"date-time":"2021-09-11T11:02:35Z","timestamp":1631358155000},"page":"357-368","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multimode Two-Stream Network for\u00a0Egocentric Action Recognition"],"prefix":"10.1007","author":[{"given":"Ying","family":"Li","sequence":"first","affiliation":[]},{"given":"Jie","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Xiong","sequence":"additional","affiliation":[]},{"given":"Wei","family":"He","sequence":"additional","affiliation":[]},{"given":"Peng","family":"Li","sequence":"additional","affiliation":[]},{"given":"Wenjie","family":"Yan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,7]]},"reference":[{"key":"29_CR1","unstructured":"Attention is all we need: Nailing down object-centric attention for egocentric activity recognition (2018)"},{"key":"29_CR2","unstructured":"Baradel, F., Wolf, C., Mille, J.: Pose-conditioned spatio-temporal attention for human action recognition (2017)"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Bobick, A.F., Davis, J.W.: The Recognition of Human Movement Using Temporal Templates. The Recognition of Human Movement Using Temporal Templates (2001)","DOI":"10.1109\/34.910878"},{"key":"29_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. arXiv e-prints (2016)","DOI":"10.1109\/CVPR.2017.143"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Choutas, V., Weinzaepfel, P., Revaud, J., Schmid, C.: Potion: pose motion representation for action recognition. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00734"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Du, W., Wang, Y., Yu, Q.: RPAN: an end-to-end recurrent pose-attention network for action recognition in videos (2017)","DOI":"10.1109\/ICCV.2017.402"},{"issue":"4","key":"29_CR7","doi-asserted-by":"publisher","first-page":"1307","DOI":"10.1007\/s10044-018-0727-y","volume":"22","author":"M Farrajota","year":"2019","unstructured":"Farrajota, M., Rodrigues, J., Buf, J.: Human action recognition in videos with articulated pose information by deep networks. Pattern Anal. Appl. 22(4), 1307\u20131318 (2019)","journal-title":"Pattern Anal. Appl."},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions (2017)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"29_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1007\/978-3-030-61609-0_23","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2020","author":"S Hahner","year":"2020","unstructured":"Hahner, S., Iza-Teran, R., Garcke, J.: Analysis and prediction of deforming 3D shapes using oriented bounding boxes and LSTM autoencoders. In: Farka\u0161, I., Masulli, P., Wermter, S. (eds.) ICANN 2020. LNCS, vol. 12396, pp. 284\u2013296. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-61609-0_23"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Hou, R., Chen, C., Shah, M.: Tube convolutional neural network (T-CNN) for action detection in videos, pp. 5823\u20135832. IEEE Computer Society (2017)","DOI":"10.1109\/ICCV.2017.620"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.J.: Towards understanding action recognition. In: IEEE International Conference on Computer Vision (2014)","DOI":"10.1109\/ICCV.2013.396"},{"key":"29_CR12","unstructured":"Klser, A., Marszalek, M., Schmid, C.: A spatio-temporal descriptor based on 3d-gradients. In: British Machine Vision Conference (2010)"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Kozlov, A., Andronov, V., Gritsenko, Y.: Lightweight network architecture for real-time action recognition (2020)","DOI":"10.1145\/3341105.3373906"},{"key":"29_CR14","unstructured":"Laha, A., Raykar, V.: An empirical evaluation of various deep learning architectures for bi-sequence classification tasks (2016)"},{"key":"29_CR15","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1016\/j.neucom.2020.02.026","volume":"395","author":"Y Li","year":"2020","unstructured":"Li, Y., Wang, Z., Wang, L., Wu, G.: Actions as moving points. Neurocomputing 395, 138\u2013149 (2020)","journal-title":"Neurocomputing"},{"key":"29_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1007\/978-3-319-46487-9_50","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Liu","year":"2016","unstructured":"Liu, J., Shahroudy, A., Xu, D., Wang, G.: Spatio-temporal LSTM with trust gates for 3D human action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 816\u2013833. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_50"},{"key":"29_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1007\/978-3-319-46493-0_45","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Peng","year":"2016","unstructured":"Peng, X., Schmid, C.: Multi-region two-stream R-CNN for action detection. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 744\u2013759. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_45"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Piergiovanni, A.J., Ryoo, M.S.: Representation flow for action recognition. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR.2019.01018"},{"issue":"2","key":"29_CR19","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1111\/mice.12579","volume":"36","author":"J Shen","year":"2021","unstructured":"Shen, J., Xiong, X., Li, Y., He, W., Li, P., Zheng, X.: Detecting safety helmet wearing on construction sites with bounding-box regression and deep transfer learning. Comput. Aided Civil Infrastruc. Eng. 36(2), 180\u2013196 (2021)","journal-title":"Comput. Aided Civil Infrastruc. Eng."},{"issue":"10","key":"29_CR20","doi-asserted-by":"publisher","first-page":"897","DOI":"10.1111\/mice.12454","volume":"34","author":"J Shen","year":"2019","unstructured":"Shen, J., Xiong, X., Xue, Z., Bian, Y.: A convolutional neural-network-based pedestrian counting model for various crowded scenes. Comput. Aided Civil Infrastruc. Eng. 34(10), 897\u2013914 (2019)","journal-title":"Comput. Aided Civil Infrastruc. Eng."},{"key":"29_CR21","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems 1 (2014)"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Sudhakaran, S., Escalera, S., Lanz, O.: LSTA: long short-term attention for egocentric action recognition. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01019"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Sun, B., Liu, M., Zheng, R., Zhang, S.: Attention-based LSTM network for wearable human activity recognition. In: 2019 Chinese Control Conference (CCC) (2019)","DOI":"10.23919\/ChiCC.2019.8865360"},{"key":"29_CR24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_20","volume-title":"Actor-Centric Relation Network","author":"C Sun","year":"2018","unstructured":"Sun, C., Shrivastava, A., Vondrick, C., Murphy, K., Sukthankar, R., Schmid, C.: Actor-Centric Relation Network. Springer, Cham (2018)"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Tang, J., Xia, J., Mu, X., Pang, B., Lu, C.: Asynchronous interaction aggregation for action detection (2020)","DOI":"10.1007\/978-3-030-58555-6_5"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. IEEE (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"29_CR28","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)"},{"key":"29_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1007\/978-3-030-61609-0_21","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2020","author":"M V\u00e9ges","year":"2020","unstructured":"V\u00e9ges, M., L\u0151rincz, A.: Multi-person absolute 3D human pose estimation with weak depth supervision. In: Farka\u0161, I., Masulli, P., Wermter, S. (eds.) ICANN 2020. LNCS, vol. 12396, pp. 258\u2013270. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-61609-0_21"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Wu, J., Kuang, Z., Wang, L., Zhang, W., Wu, G.: Context-aware RCNN: a baseline for action detection in videos (2020)","DOI":"10.1007\/978-3-030-58595-2_27"},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Zhao, J., Snoek, C.: Dance with flow: two-in-one stream action detection. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR.2019.01017"},{"key":"29_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1007\/978-3-030-30508-6_40","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2019: Image Processing","author":"Z Zheng","year":"2019","unstructured":"Zheng, Z., Shi, L., Wang, C., Sun, L., Pan, G.: LSTM with uniqueness attention for human activity recognition. In: Tetko, I.V., K\u016frkov\u00e1, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11729, pp. 498\u2013509. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30508-6_40"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86362-3_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,11]],"date-time":"2021-09-11T11:08:35Z","timestamp":1631358515000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86362-3_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863616","9783030863623"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86362-3_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"7 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bratislava","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovakia","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":"14 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2021\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"496","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":"265","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":"4","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":"53% - 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":"2.5","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":"Conference was held online due to the COVID-19 pandemic.","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)"}}]}}