{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T20:29:13Z","timestamp":1773865753128,"version":"3.50.1"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031220609","type":"print"},{"value":"9783031220616","type":"electronic"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-22061-6_3","type":"book-chapter","created":{"date-parts":[[2022,12,13]],"date-time":"2022-12-13T20:02:58Z","timestamp":1670961778000},"page":"29-40","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["IARG: Improved Actor Relation Graph Based Group Activity Recognition"],"prefix":"10.1007","author":[{"given":"Zijian","family":"Kuang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinran","family":"Tie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,14]]},"reference":[{"issue":"9","key":"3_CR1","doi-asserted-by":"publisher","first-page":"2045","DOI":"10.1109\/TMM.2017.2729019","volume":"19","author":"L Gao","year":"2017","unstructured":"Gao, L., Guo, Z., Zhang, H., Xu, X., Shen, H.T.: Video captioning with attention-based LSTM and semantic consistency. IEEE Trans. Multimedia 19(9), 2045\u20132055 (2017)","journal-title":"IEEE Trans. Multimedia"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Xu, H., Donahue, J., Rohrbach, M., Mooney, R., Saenko, K.: Translating videos to natural language using deep recurrent neural networks. In: Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (2015)","DOI":"10.3115\/v1\/N15-1173"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Rohrbach, M., Donahue, J., Mooney, R., Darrell, T., Saenko, K.: Sequence to sequence - video to text. In: 2015 IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.515"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Sherstinsky, A.: Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Phys. D Nonlinear Phenomena 404, 132306 (2020). https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0167278919305974","DOI":"10.1016\/j.physd.2019.132306"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Krishna, R. Hata, K., Ren, F., Fei-Fei, L., Niebles, J. C.: Dense-captioning events in videos. In: 2017 IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Fernando, B., Chet, C.T.Y., Bilen, H.: Weakly supervised gaussian networks for action detection. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) (2020)","DOI":"10.1109\/WACV45572.2020.9093263"},{"key":"3_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/978-3-030-20205-7_25","volume-title":"Image Analysis","author":"FM Noori","year":"2019","unstructured":"Noori, F.M., Wallace, B., Uddin, M.Z., Torresen, J.: A robust human activity recognition approach using openpose, motion features, and deep recurrent neural network. In: Felsberg, M., Forss\u00e9n, P.-E., Sintorn, I.-M., Unger, J. (eds.) SCIA 2019. LNCS, vol. 11482, pp. 299\u2013310. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20205-7_25"},{"key":"3_CR8","unstructured":"Cao, Z., Martinez, G.H., Simon, T., Wei, S.-E., Sheikh, Y.A.: Openpose: realtime multi-person 2D pose estimation using part affinity fields. IEEE Trans. Pattern Anal. Mach. Intell. PP, 1 (2019)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Wu, J., Wang, L., Wang, L., Guo, J., Wu, G.: Learning actor relation graphs for group activity recognition. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2019","DOI":"10.1109\/CVPR.2019.01020"},{"key":"3_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1007\/978-3-030-01219-9_44","volume-title":"Computer Vision \u2013 ECCV 2018","author":"MS Ibrahim","year":"2018","unstructured":"Ibrahim, M.S., Mori, G.: Hierarchical relational networks for group activity recognition and retrieval. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 742\u2013758. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_44"},{"key":"3_CR11","unstructured":"Howard, A.G., et al: MobileNets: efficient convolutional neural networks for mobile vision applications (2017).https:\/\/arxiv.org\/abs\/1704.04861"},{"issue":"2","key":"3_CR12","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1007\/s11280-018-0531-z","volume":"22","author":"X Li","year":"2018","unstructured":"Li, X., Zhou, Z., Chen, L., Gao, L.: Residual attention-based LSTM for video captioning. World Wide Web 22(2), 621\u2013636 (2018). https:\/\/doi.org\/10.1007\/s11280-018-0531-z","journal-title":"World Wide Web"},{"key":"3_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/978-3-030-54407-2_16","volume-title":"Smart Multimedia","author":"CDC Heath","year":"2020","unstructured":"Heath, C.D.C., Heath, T., McDaniel, T., Venkateswara, H., Panchanathan, S.: Using participatory design to create a user interface for analyzing pivotal response treatment video probes. In: McDaniel, T., Berretti, S., Curcio, I.D.D., Basu, A. (eds.) ICSM 2019. LNCS, vol. 12015, pp. 183\u2013198. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-54407-2_16"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Raaj, Y., Idrees, H., Hidalgo, G., Sheikh, Y.: Efficient online multi-person 2D pose tracking with recurrent spatio-temporal affinity fields. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00475"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Yuan, H., Ni, D., Wang, M.: Spatio-temporal dynamic inference network for group activity recognition. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00738"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Li, et al.: GroupFormer: group activity recognition with clustered spatial-temporal transformer. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01341"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: IEEE International Conference on Computer Vision (ICCV), vol. 2017, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Raghavender Rao, Y.: Application of normalized cross correlation to image registration. Int. J. Res. Eng. Technol. 03(17), 12\u201316 (2014)","DOI":"10.15623\/ijret.2014.0317003"},{"key":"3_CR19","unstructured":"Choi, W., Shahid, K., Savarese, S.: What are they doing?: collective activity classification using spatio-temporal relationship among people. In: 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops (2009)"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision, pp. 2818-2826 (2015). https:\/\/arxiv.org\/abs\/1512.00567","DOI":"10.1109\/CVPR.2016.308"}],"container-title":["Lecture Notes in Computer Science","Smart Multimedia"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-22061-6_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T07:04:01Z","timestamp":1675321441000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-22061-6_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031220609","9783031220616"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-22061-6_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"14 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICSM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Smart Multimedia","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Marseille","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icsm2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/smartmultimedia.org\/2021\/node\/3","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":"Papercept","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"68","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":"30","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":"44% - 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":"8","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}