{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T20:45:49Z","timestamp":1778359549301,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819607730","type":"print"},{"value":"9789819607747","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-0774-7_3","type":"book-chapter","created":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T13:46:02Z","timestamp":1737467162000},"page":"33-48","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["YOWOv2: A Stronger yet\u00a0Efficient Multi-level Detection Framework for\u00a0Real-Time Spatio-Temporal Action Detection"],"prefix":"10.1007","author":[{"given":"Zhiqiang","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nan","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuaiyan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lijun","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruifeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,21]]},"reference":[{"key":"3_CR1","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":"3_CR2","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: Watch only once: an end-to-end video action detection framework. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8178\u20138187 (2021)","DOI":"10.1109\/ICCV48922.2021.00807"},{"issue":"5","key":"3_CR3","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1007\/s00138-018-0931-1","volume":"29","author":"A Clap\u00e9s","year":"2018","unstructured":"Clap\u00e9s, A., Pardo, \u00c0., Pujol Vila, O., Escalera, S.: Action detection fusing multiple Kinects and a WIMU: an application to in-home assistive technology for the elderly. Mach. Vis. Appl. 29(5), 765\u2013788 (2018)","journal-title":"Mach. Vis. Appl."},{"key":"3_CR4","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":"3_CR5","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., Lu, H.: Dual attention network for scene segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"3_CR6","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Carreira, J., Doersch, C., Zisserman, A.: Video action transformer network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 244\u2013253 (2019)","DOI":"10.1109\/CVPR.2019.00033"},{"key":"3_CR8","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":"3_CR9","doi-asserted-by":"crossref","unstructured":"Hou, R., Chen, C., Shah, M.: Tube convolutional neural network (T-CNN) for action detection in videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5822\u20135831 (2017)","DOI":"10.1109\/ICCV.2017.620"},{"key":"3_CR10","doi-asserted-by":"publisher","first-page":"2547","DOI":"10.1109\/TAI.2023.3326120","volume":"5","author":"J Jiang","year":"2023","unstructured":"Jiang, J., Cao, G., Deng, J., Do, T.T., Luo, S.: Robotic perception of transparent objects: a review. IEEE Trans. Artif. Intell. 5, 2547\u20132567 (2023)","journal-title":"IEEE Trans. Artif. Intell."},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Kalogeiton, V., Weinzaepfel, P., Ferrari, V., Schmid, C.: Action tubelet detector for spatio-temporal action localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4405\u20134413 (2017)","DOI":"10.1109\/ICCV.2017.472"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Kopuklu, O., Kose, N., Gunduz, A., Rigoll, G.: Resource efficient 3D convolutional neural networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00240"},{"key":"3_CR13","unstructured":"K\u00f6p\u00fckl\u00fc, O., Wei, X., Rigoll, G.: You only watch once: a unified CNN architecture for real-time spatiotemporal action localization. arXiv preprint arXiv:1911.06644 (2019)"},{"key":"3_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1007\/978-3-030-58517-4_5","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Li","year":"2020","unstructured":"Li, Y., Wang, Z., Wang, L., Wu, G.: Actions as moving points. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 68\u201384. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_5"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"3_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"3_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Ma, X., Luo, Z., Zhang, X., Liao, Q., Shen, X., Wang, M.: Spatio-temporal action detector with self-attention. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20138. IEEE (2021)","DOI":"10.1109\/IJCNN52387.2021.9533300"},{"key":"3_CR19","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, pp. 464\u2013474 (2021)","DOI":"10.1109\/CVPR46437.2021.00053"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Song, L., Zhang, S., Yu, G., Sun, H.: TACNet: transition-aware context network for spatio-temporal action detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11987\u201311995 (2019)","DOI":"10.1109\/CVPR.2019.01226"},{"key":"3_CR23","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":"3_CR24","doi-asserted-by":"crossref","unstructured":"Sui, L., Zhang, C.L., Gu, L., Han, F.: A simple and efficient pipeline to build an end-to-end spatial-temporal action detector. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5999\u20136008 (2023)","DOI":"10.1109\/WACV56688.2023.00594"},{"key":"3_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: YOLOV7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696 (2022)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"3_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1007\/978-3-030-58595-2_27","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Wu","year":"2020","unstructured":"Wu, J., Kuang, Z., Wang, L., Zhang, W., Wu, G.: Context-Aware RCNN: a baseline for action detection in videos. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 440\u2013456. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_27"},{"issue":"1","key":"3_CR28","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1109\/TMM.2019.2924576","volume":"22","author":"C Yan","year":"2019","unstructured":"Yan, C., et al.: STAT: spatial-temporal attention mechanism for video captioning. IEEE Trans. Multimedia 22(1), 229\u2013241 (2019)","journal-title":"IEEE Trans. Multimedia"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Zhao, J., et\u00a0al.: TubeR: tubelet transformer for video action detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13598\u201313607 (2022)","DOI":"10.1109\/CVPR52688.2022.01323"},{"key":"3_CR30","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"}],"container-title":["Lecture Notes in Computer Science","Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0774-7_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T13:46:22Z","timestamp":1737467182000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0774-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819607730","9789819607747"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0774-7_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"21 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIRA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Robotics and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xi'an","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 July 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icira2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icira2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}