{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T23:53:58Z","timestamp":1742946838408,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031479687"},{"type":"electronic","value":"9783031479694"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-47969-4_12","type":"book-chapter","created":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T20:02:06Z","timestamp":1701374526000},"page":"147-159","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Local and\u00a0Global Context Reasoning for\u00a0Spatio-Temporal Action Localization"],"prefix":"10.1007","author":[{"given":"Ryuhei","family":"Ando","sequence":"first","affiliation":[]},{"given":"Yasunori","family":"Babazaki","sequence":"additional","affiliation":[]},{"given":"Katsuhiko","family":"Takahashi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,1]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: ViViT: a video vision transformer. In: Proceedings of the International Conference on Computer Vision (ICCV), pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Choutas, V., Weinzaepfel, P., Revaud, J., Schmid, C.: PoTion: pose motion representation for action recognition. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7024\u20137033 (2018)","DOI":"10.1109\/CVPR.2018.00734"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Dai, X., Singh, B., Zhang, G., Davis, L.S., Qiu Chen, Y.: Temporal context network for activity localization in videos. In: Proceedings of the International Conference on Computer Vision (ICCV), pp. 5793\u20135802 (2017)","DOI":"10.1109\/ICCV.2017.610"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: Proceedings of the International Conference on Computer Vision (ICCV), pp. 6824\u20136835 (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the International Conference on Computer Vision (ICCV), pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1933\u20131941 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Carreira, J., Doersch, C., Zisserman, A.: Video action transformer network. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), pp. 244\u2013253 (2019)","DOI":"10.1109\/CVPR.2019.00033"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6047\u20136056 (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.J.: Towards understanding action recognition. In: Proceedings of the International Conference on Computer Vision (ICCV), pp. 3192\u20133199 (2013)","DOI":"10.1109\/ICCV.2013.396"},{"key":"12_CR10","doi-asserted-by":"publisher","unstructured":"Jocher, G.: YOLOv5 by Ultralytics (2020). https:\/\/doi.org\/10.5281\/zenodo.3908559, https:\/\/github.com\/ultralytics\/yolov5. Accessed July 2023","DOI":"10.5281\/zenodo.3908559"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Li, D., Qiu, Z., Dai, Q., Yao, T., Mei, T.: Recurrent tubelet proposal and recognition networks for action detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 303\u2013318 (2018)","DOI":"10.1007\/978-3-030-01231-1_19"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: Proceedings of the International Conference on Computer Vision (CVPR), pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Pan, J., Chen, S., Shou, M.Z., Liu, Y., Shao, J., Li, H.: Actor-context-actor relation network for spatio-temporal action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 464\u2013474 (2021)","DOI":"10.1109\/CVPR46437.2021.00053"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Rajasegaran, J., Pavlakos, G., Kanazawa, A., Feichtenhofer, C., Malik, J.: On the benefits of 3D pose and tracking for human action recognition. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), pp. 640\u2013649 (2023)","DOI":"10.1109\/CVPR52729.2023.00069"},{"key":"12_CR15","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems (NeurlPS), vol. 27 (2014)"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Vondrick, C., Murphy, K., Sukthankar, R., Schmid, C.: Actor-centric relation network. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 318\u2013334 (2018)","DOI":"10.1007\/978-3-030-01252-6_20"},{"key":"12_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/978-3-030-58555-6_5","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Tang","year":"2020","unstructured":"Tang, J., Xia, J., Mu, X., Pang, B., Lu, C.: Asynchronous interaction aggregation for action detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 71\u201387. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_5"},{"key":"12_CR18","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 International Conference on Computer Vision (ICCV), pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"issue":"10","key":"12_CR19","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2020","unstructured":"Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., Liu, D., Mu, Y., Tan, M., Wang, X., et al.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 43(10), 3349\u20133364 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (PAMI)"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., Girshick, R.: Long-term feature banks for detailed video understanding. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), pp. 284\u2013293 (2019)","DOI":"10.1109\/CVPR.2019.00037"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Xu, H., Das, A., Saenko, K.: R-C3D: Region convolutional 3D network for temporal activity detection. In: Proceedings of the International Conference on Computer Vision (CVPR), pp. 5783\u20135792 (2017)","DOI":"10.1109\/ICCV.2017.617"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Yang, X., Yang, X., Liu, M.Y., Xiao, F., Davis, L.S., Kautz, J.: STEP: spatio-temporal progressive learning for video action detection. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), pp. 264\u2013272 (2019)","DOI":"10.1109\/CVPR.2019.00035"},{"key":"12_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/978-3-031-19833-5_15","volume-title":"Computer Vision - ECCV 2022","author":"H Zhou","year":"2022","unstructured":"Zhou, H., et al.: Composer: compositional reasoning of group activity in videos with keypoint-only modality. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13695, pp. 249\u2013266. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_15"}],"container-title":["Lecture Notes in Computer Science","Advances in Visual Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-47969-4_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T20:03:10Z","timestamp":1701374590000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-47969-4_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031479687","9783031479694"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-47969-4_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISVC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Visual Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lake Tahoe, NV","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isvc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.isvc.net\/","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":"25","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":"58","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":"232% - 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":"2.3","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)"}},{"value":"43 (oral), 15 (poster),  25 (special tracks) out of 34 submissions","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)"}}]}}