{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T15:46:43Z","timestamp":1743004003217,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031581809"},{"type":"electronic","value":"9783031581816"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-58181-6_50","type":"book-chapter","created":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T10:03:42Z","timestamp":1719914622000},"page":"586-599","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Actor-Centric Spatio-Temporal Feature Extraction for\u00a0Action Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1894-3360","authenticated-orcid":false,"given":"Kunchala","family":"Anil","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5039-0815","authenticated-orcid":false,"given":"M\u00e9lanie","family":"Bouroche","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8487-3690","authenticated-orcid":false,"given":"Bianca","family":"Schoen-Phelan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,7,3]]},"reference":[{"key":"50_CR1","doi-asserted-by":"crossref","unstructured":"Bewley, A., Ge, Z., Ott, L., Ramos, F., Upcroft, B.: Simple online and realtime tracking. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 3464\u20133468. IEEE (2016)","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"50_CR2","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"50_CR3","doi-asserted-by":"crossref","unstructured":"Dave, I., Scheffer, Z., Kumar, A., Shiraz, S., Rawat, Y.S., Shah, M.: Gabriellav2: towards better generalization in surveillance videos for action detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 122\u2013132 (2022)","DOI":"10.1109\/WACVW54805.2022.00018"},{"key":"50_CR4","doi-asserted-by":"crossref","unstructured":"Duan, H., Zhao, Y., Chen, K., Lin, D., Dai, B.: Revisiting skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2969\u20132978 (2022)","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"50_CR5","doi-asserted-by":"crossref","unstructured":"Ehsanpour, M., Saleh, F., Savarese, S., Reid, I., Rezatofighi, H.: JRDB-act: a large-scale dataset for spatio-temporal action, social group and activity detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20983\u201320992 (2022)","DOI":"10.1109\/CVPR52688.2022.02031"},{"key":"50_CR6","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3D: expanding architectures for efficient video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 203\u2013213 (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"50_CR7","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"50_CR8","unstructured":"Girdhar, R., Carreira, J., Doersch, C., Zisserman, A.: A better baseline for ava. arXiv preprint arXiv:1807.10066 (2018)"},{"key":"50_CR9","doi-asserted-by":"crossref","unstructured":"Gkountakos, K., Touska, D., Ioannidis, K., Tsikrika, T., Vrochidis, S., Kompatsiaris, I.: Spatio-temporal activity detection and recognition in untrimmed surveillance videos. In: Proceedings of the 2021 International Conference on Multimedia Retrieval, pp. 451\u2013455 (2021)","DOI":"10.1145\/3460426.3463591"},{"key":"50_CR10","doi-asserted-by":"crossref","unstructured":"Gleason, J., Castillo, C.D., Chellappa, R.: Real-time detection of activities in untrimmed videos. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops, pp. 117\u2013125 (2020)","DOI":"10.1109\/WACVW50321.2020.9096937"},{"key":"50_CR11","doi-asserted-by":"crossref","unstructured":"Gleason, J., Ranjan, R., Schwarcz, S., Castillo, C., Chen, J.C., Chellappa, R.: A proposal-based solution to spatio-temporal action detection in untrimmed videos. In: 2019 IEEE winter conference on applications of computer vision (WACV), pp. 141\u2013150. IEEE (2019)","DOI":"10.1109\/WACV.2019.00021"},{"key":"50_CR12","doi-asserted-by":"crossref","unstructured":"Gu, C., et\u00a0al.: Ava: a video dataset of spatio-temporally localized atomic visual actions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6047\u20136056 (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"50_CR13","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"50_CR14","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.223"},{"issue":"10","key":"50_CR15","doi-asserted-by":"publisher","first-page":"2684","DOI":"10.1109\/TPAMI.2019.2916873","volume":"42","author":"J Liu","year":"2019","unstructured":"Liu, J., Shahroudy, A., Perez, M., Wang, G., Duan, L.Y., Kot, A.C.: Ntu rgb+ d 120: a large-scale benchmark for 3D human activity understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2684\u20132701 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"50_CR16","doi-asserted-by":"crossref","unstructured":"Liu, W., et al.: Argus: efficient activity detection system for extended video analysis. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops, pp. 126\u2013133 (2020)","DOI":"10.1109\/WACVW50321.2020.9096929"},{"key":"50_CR17","doi-asserted-by":"crossref","unstructured":"Mavroudi, E., Bindal, P., Vidal, R.: Actor-centric tubelets for real-time activity detection in extended videos. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 172\u2013181 (2022)","DOI":"10.1109\/WACVW54805.2022.00023"},{"key":"50_CR18","doi-asserted-by":"crossref","unstructured":"Oh, S., et\u00a0al.: A large-scale benchmark dataset for event recognition in surveillance video. In: CVPR 2011, pp. 3153\u20133160. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995586"},{"key":"50_CR19","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"50_CR20","doi-asserted-by":"crossref","unstructured":"Singh, G., Choutas, V., Saha, S., Yu, F., Van\u00a0Gool, L.: Spatio-temporal action detection under large motion. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 6009\u20136018 (2023)","DOI":"10.1109\/WACV56688.2023.00595"},{"key":"50_CR21","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"50_CR22","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 IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"50_CR23","doi-asserted-by":"publisher","first-page":"105055","DOI":"10.1016\/j.engappai.2022.105055","volume":"114","author":"B Zhang","year":"2022","unstructured":"Zhang, B., Wan, J., Zhao, Y., Tong, Z., Du, Y.: Multi-actor activity detection by modeling object relationships in extended videos based on deep learning. Eng. Appl. Artif. Intell. 114, 105055 (2022)","journal-title":"Eng. Appl. Artif. Intell."}],"container-title":["Communications in Computer and Information Science","Computer Vision and Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-58181-6_50","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T10:14:01Z","timestamp":1719915241000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-58181-6_50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031581809","9783031581816"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-58181-6_50","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"3 July 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Vision and Image Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jammu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"3 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iitjammu.ac.in\/cvip2023\/","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":"Online CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"461","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":"140","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":"30% - 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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}