{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T04:59:54Z","timestamp":1762491594947,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032093202","type":"print"},{"value":"9783032093219","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:00:00Z","timestamp":1762560000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:00:00Z","timestamp":1762560000000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-09321-9_23","type":"book-chapter","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T04:57:45Z","timestamp":1762491465000},"page":"337-350","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Semi-supervised Video Action Detection Using a\u00a0UNet-Like Architecture"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7327-1935","authenticated-orcid":false,"given":"Van-Khoa","family":"Duong","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0252-6519","authenticated-orcid":false,"given":"Ngoc-Thao","family":"Nguyen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,8]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5533\u20135541 (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L.D., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: European Conference on Computer Vision, pp. 318\u2013335 (2018)","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lucic, M., Schmid, C.: ViViT: a video vision transformer. In: IEEE\/CVF International Conference on Computer Vision, pp. 6816\u20136826 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"23_CR5","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: International Conference on Machine Learning, pp. 813\u2013824 (2021)"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Video swin transformer. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3192\u20133201 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Bello, I., Zoph, B., Le, Q., Vaswani, A., Shlens, J.: Attention augmented convolutional networks. In: IEEE\/CVF International Conference on Computer Vision, pp. 3285\u20133294 (2019)","DOI":"10.1109\/ICCV.2019.00338"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R.B., Gupta, A., He, K.: Non-local neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: IEEE\/CVF International Conference on Computer Vision, pp. 9992\u201310002 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Huang, H., et al.: UNet 3+: a full-scale connected unet for medical image segmentation. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1055\u20131059 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053405"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4724\u20134733 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"issue":"5","key":"23_CR12","doi-asserted-by":"publisher","first-page":"1366","DOI":"10.1007\/s11263-022-01594-9","volume":"130","author":"Y Kong","year":"2022","unstructured":"Kong, Y., Fu, Y.: Human action recognition and prediction: a survey. Int. J. Comput. Vis. 130(5), 1366\u20131401 (2022)","journal-title":"Int. J. Comput. Vis."},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Singh, G., Saha, S., Sapienza, M., Torr, P.H.S., Cuzzolin, F.: Online real-time multiple spatiotemporal action localisation and prediction. In: IEEE International Conference on Computer Vision, pp. 3657\u20133666 (2017)","DOI":"10.1109\/ICCV.2017.393"},{"key":"23_CR14","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. CoRR abs\/1212.0402 (2012)"},{"key":"23_CR15","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, pp. 3192\u20133199 (2013)","DOI":"10.1109\/ICCV.2013.396"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Kalogeiton, V., Weinzaepfel, P., Ferrari, V., Schmid, C.: Action tubelet detector for spatio-temporal action localization. In: IEEE International Conference on Computer Vision, pp. 4405\u20134413 (2017)","DOI":"10.1109\/ICCV.2017.472"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Song, L., Zhang, S., Yu, G., Sun, H.: TACNet: transition-aware context network for spatio-temporal action detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 11987\u201311995 (2019)","DOI":"10.1109\/CVPR.2019.01226"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Yang, X., Yang, X., Liu, M., Xiao, F., Davis, L.S., Kautz, J.: STEP: spatio-temporal progressive learning for video action detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 264\u2013272 (2019)","DOI":"10.1109\/CVPR.2019.00035"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Zhao, J., Snoek, C.G.M.: Dance with flow: two-in-one stream action detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 9935\u20139944 (2019)","DOI":"10.1109\/CVPR.2019.01017"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, Z., Wang, L., Wu, G.: Actions as moving points. In: European Conference on Computer Vision, pp. 68\u201384 (2020)","DOI":"10.1007\/978-3-030-58517-4_5"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Hou, R., Chen, C., Shah, M.: Tube convolutional neural network (T-CNN) for action detection in videos. In: IEEE International Conference on Computer Vision, pp. 5823\u20135832 (2017)","DOI":"10.1109\/ICCV.2017.620"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Kumar, A., Rawat, Y.S.: End-to-end semi-supervised learning for video action detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14680\u201314690 (2022)","DOI":"10.1109\/CVPR52688.2022.01429"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6047\u20136056 (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"23_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/978-3-030-01252-6_20","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Sun","year":"2018","unstructured":"Sun, C., Shrivastava, A., Vondrick, C., Murphy, K., Sukthankar, R., Schmid, C.: Actor-centric relation network. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 335\u2013351. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_20"},{"key":"23_CR25","unstructured":"Duarte, K., Rawat, Y.S., Shah, M.: VideoCapsuleNet: a simplified network for action detection. In: Advances in Neural Information Processing Systems, pp. 7621\u20137630 (2018)"},{"key":"23_CR26","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 464\u2013474 (2021)","DOI":"10.1109\/CVPR46437.2021.00053"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Escorcia, V., Duc Dao, C., Jain, M., Ghanem, B., Snoek, C.G.M.: Guess where? Actor-supervision for spatiotemporal action localization. Comput. Vis. Image Understand. 192, 102886 (2020)","DOI":"10.1016\/j.cviu.2019.102886"},{"key":"23_CR28","unstructured":"Ch\u00e9ron, G., Alayrac, J.B., Laptev, I., Schmid, C.: A flexible model for training action localization with varying levels of supervision. In: Advances in Neural Information Processing Systems, pp. 950\u2013961 (2018)"},{"issue":"10","key":"23_CR29","doi-asserted-by":"publisher","first-page":"2610","DOI":"10.1109\/TMM.2019.2959425","volume":"22","author":"S Zhang","year":"2020","unstructured":"Zhang, S., Song, L., Gao, C., Sang, N.: GLNet: global local network for weakly supervised action localization. IEEE Trans. Multimed. 22(10), 2610\u20132622 (2020)","journal-title":"IEEE Trans. Multimed."},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Arnab, A., Sun, C., Nagrani, A., Schmid, C.: Uncertainty-aware weakly supervised action detection from untrimmed videos. In: European Conference on Computer Vision, pp. 751\u2013768 (2020)","DOI":"10.1007\/978-3-030-58607-2_44"},{"key":"23_CR31","unstructured":"Berthelot, D., Carlini, N., Goodfellow, I.J., Papernot, N., Oliver, A., Raffel, C.: MixMatch: a holistic approach to semi-supervised learning. In: Advances in Neural Information Processing Systems, pp. 5050\u20135060 (2019)"},{"key":"23_CR32","unstructured":"Lee, D.H.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning. ICML (2013)"},{"key":"23_CR33","unstructured":"Jeong, J., Lee, S., Kim, J., Kwak, N.: Consistency-based semi-supervised learning for object detection. In: Advances in Neural Information Processing Systems, pp. 10758\u201310767 (2019)"},{"key":"23_CR34","unstructured":"Yun, S., Oh, S.J., Heo, B., Han, D., Kim, J.: VideoMix: rethinking data augmentation for video classification. CoRR abs\/2012.03457 (2020)"},{"key":"23_CR35","doi-asserted-by":"crossref","unstructured":"Jain, M., van Gemert, J.C., J\u00e9gou, H., Bouthemy, P., Snoek, C.G.M.: Action localization with tubelets from motion. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 740\u2013747 (2014)","DOI":"10.1109\/CVPR.2014.100"},{"key":"23_CR36","doi-asserted-by":"crossref","unstructured":"Shou, Z., Chan, J., Zareian, A., Miyazawa, K., Chang, S.F.: CDC: convolutional-de-convolutional networks for precise temporal action localization in untrimmed videos. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1417\u20131426 (2017)","DOI":"10.1109\/CVPR.2017.155"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Zeng, R., et al.: Graph convolutional networks for temporal action localization. In: IEEE\/CVF International Conference on Computer Vision, pp. 7093\u20137102 (2019)","DOI":"10.1109\/ICCV.2019.00719"},{"issue":"3","key":"23_CR38","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1109\/TMM.2018.2866370","volume":"21","author":"H Song","year":"2019","unstructured":"Song, H., Wu, X., Zhu, B., Wu, Y., Chen, M., Jia, Y.: Temporal action localization in untrimmed videos using action pattern trees. IEEE Trans. Multimed. 21(3), 717\u2013730 (2019)","journal-title":"IEEE Trans. Multimed."},{"key":"23_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"23_CR40","doi-asserted-by":"publisher","first-page":"31742","DOI":"10.1109\/ACCESS.2021.3061062","volume":"9","author":"J Gurrola-Ramos","year":"2021","unstructured":"Gurrola-Ramos, J., Dalmau, O.S., Alarc\u00f3n, T.E.: A residual dense u-net neural network for image denoising. IEEE Access 9, 31742\u201331754 (2021)","journal-title":"IEEE Access"},{"key":"23_CR41","unstructured":"Wang, F., Song, Y., Zhang, J., Han, J., Huang, D.: Temporal unet: sample level human action recognition using WiFi. CoRR abs\/1904.11953 (2019)"},{"key":"23_CR42","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1109\/TIP.2022.3228497","volume":"32","author":"X Wu","year":"2023","unstructured":"Wu, X., Hong, D., Chanussot, J.: UIU-net: u-net in u-net for infrared small object detection. IEEE Trans. Image Process. 32, 364\u2013376 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"23_CR43","doi-asserted-by":"crossref","unstructured":"Singh, A., Rana, A.J., Kumar, A., Vyas, S., Rawat, Y.S.: Semi-supervised active learning for video action detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 5, pp. 4891\u20134899 (2024)","DOI":"10.1609\/aaai.v38i5.28292"},{"key":"23_CR44","doi-asserted-by":"crossref","unstructured":"Lee, J., et al.: Classification matters: improving video action detection with class-specific attention. In: European Conference on Computer Vision, pp. 450\u2013467 (2024)","DOI":"10.1007\/978-3-031-72661-3_26"},{"key":"23_CR45","doi-asserted-by":"crossref","unstructured":"Chen, L., Tong, Z., Song, Y., Wu, G., Wang, L.: Efficient video action detection with token dropout and context refinement. In: IEEE\/CVF International Conference on Computer Vision, pp. 10388\u201310399 (2023)","DOI":"10.1109\/ICCV51070.2023.00953"},{"key":"23_CR46","doi-asserted-by":"crossref","unstructured":"Zhao, J., et al.: Tuber: tubelet transformer for video action detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13598\u201313607 (2022)","DOI":"10.1109\/CVPR52688.2022.01323"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Wu, T., Cao, M., Gao, Z., Wu, G., Wang, L.: Stmixer: a one-stage sparse action detector. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14720\u201314729 (2023)","DOI":"10.1109\/CVPR52729.2023.01414"}],"container-title":["Lecture Notes in Computer Science","Computational Collective Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-09321-9_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T04:58:06Z","timestamp":1762491486000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-09321-9_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,8]]},"ISBN":["9783032093202","9783032093219"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-09321-9_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,8]]},"assertion":[{"value":"8 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCCI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Collective Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ho Chi Minh City","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 November 2025","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":"iccci2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iccci.pwr.edu.pl\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}