{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T17:01:11Z","timestamp":1771520471458,"version":"3.50.1"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031783531","type":"print"},{"value":"9783031783548","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"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\/978-3-031-78354-8_22","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T10:31:00Z","timestamp":1733221860000},"page":"343-359","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["ActNetFormer: Transformer-ResNet Hybrid Method for Semi-supervised Action Recognition in Videos"],"prefix":"10.1007","author":[{"given":"Sharana Dharshikgan Suresh","family":"Dass","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hrishav Bakul","family":"Barua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ganesh","family":"Krishnasamy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raveendran","family":"Paramesran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rapha\u00ebl C.-W.","family":"Phan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Deghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Scmid, C.: Vivit: A video vision transformer. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 6936\u20136946 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"22_CR2","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space - time attention all you need for video understanding? In: ICML. vol.\u00a03, p.\u00a04 (2021)"},{"issue":"2","key":"22_CR3","doi-asserted-by":"publisher","first-page":"2873","DOI":"10.1007\/s11227-021-03957-4","volume":"78","author":"M Bilal","year":"2022","unstructured":"Bilal, M., Maqsood, M., Yasmin, S., Hasan, N.U., Rho, S.: A transfer learning-based efficient spatiotemporal human action recognition framework for long and overlapping action classes. J. Supercomput. 78(2), 2873\u20132908 (2022)","journal-title":"J. Supercomput."},{"key":"22_CR4","unstructured":"Bouthillier, X., Konda, K., Vincent, P., Memisevic, R.: Dropout as data augmentation (2016)"},{"key":"22_CR5","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: III, H.D., Singh, A. (eds.) Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0119, pp. 1597\u20131607. PMLR (13\u201318 Jul 2020), https:\/\/proceedings.mlr.press\/v119\/chen20j.html"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: Autoaugment: Learning augmentation strategies from data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (June 2019)","DOI":"10.1109\/CVPR.2019.00020"},{"key":"22_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103406","volume":"219","author":"I Dave","year":"2022","unstructured":"Dave, I., Gupta, R., Rizve, M.N., Shah, M.: Tclr: Temporal contrastive learning for video representation. Comput. Vis. Image Underst. 219, 103406 (2022)","journal-title":"Comput. Vis. Image Underst."},{"key":"22_CR8","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"22_CR9","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":"22_CR10","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1016\/j.neunet.2022.11.009","volume":"158","author":"G Gao","year":"2023","unstructured":"Gao, G., Liu, Z., Zhang, G., Li, J., Qin, A.K.: Danet: Semi-supervised differentiated auxiliaries guided network for video action recognition. Neural Netw. 158, 121\u2013131 (2023)","journal-title":"Neural Netw."},{"key":"22_CR11","doi-asserted-by":"publisher","unstructured":"Guo, T., Liu, H., Chen, Z., Liu, M., Wang, T., Ding, R.: Contrastive learning from extremely augmented skeleton sequences for self-supervised action recognition. Proceedings of the AAAI Conference on Artificial Intelligence 36(1), 762\u2013770 (2022). https:\/\/doi.org\/10.1609\/aaai.v36i1.19957. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/19957","DOI":"10.1609\/aaai.v36i1.19957"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Hu, Z., Yang, Z., Hu, X., Nevatie, R.: Simple: Similar pseudo label exploittation for semi - supervised clasiffication. In: Procedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 15099\u201315107 (June 2021)","DOI":"10.1109\/CVPR46437.2021.01485"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Jing, Y., Wang, F.: Tp-vit: A two-pathway vision transformer for video action recognition. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 2185\u20132189. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747276"},{"key":"22_CR14","unstructured":"Kay, W., Carreira, J., Simonyan, K., Zhang, B., Hillier, C., Vijayanarasimhan, S., Viola, F., Green, T., Back, T., Natsev, P., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: Hmdb: a large video database for human motion recognition. In: 2011 International conference on computer vision. pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"22_CR16","doi-asserted-by":"publisher","first-page":"193907","DOI":"10.1109\/ACCESS.2020.3031549","volume":"8","author":"PH Le-Khac","year":"2020","unstructured":"Le-Khac, P.H., Healy, G., Smeaton, A.F.: Contrastive representation learning: A framework and review. Ieee Access 8, 193907\u2013193934 (2020)","journal-title":"Ieee Access"},{"key":"22_CR17","doi-asserted-by":"publisher","first-page":"2259","DOI":"10.1007\/s10462-020-09904-8","volume":"54","author":"P Pareek","year":"2021","unstructured":"Pareek, P., Thakkar, A.: A survey on video-based human action recognition: recent updates, datasets, challenges, and applications. Artif. Intell. Rev. 54, 2259\u20132322 (2021)","journal-title":"Artif. Intell. Rev."},{"key":"22_CR18","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.ins.2021.04.023","volume":"569","author":"H Rao","year":"2021","unstructured":"Rao, H., Xu, S., Hu, X., Cheng, J., Hu, B.: Augmented skeleton based contrastive action learning with momentum lstm for unsupervised action recognition. Inf. Sci. 569, 90\u2013109 (2021)","journal-title":"Inf. Sci."},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Shah, A., Sra, S., Chellappa, R., Cherian, A.: Max-margin contrastive learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a036, pp. 8220\u20138230 (2022)","DOI":"10.1609\/aaai.v36i8.20796"},{"key":"22_CR20","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/s11042-014-1936-z","volume":"74","author":"H Shen","year":"2015","unstructured":"Shen, H., Yan, Y., Xu, S., Ballas, N., Chen, W.: Evaluation of semi-supervised learning method on action recognition. Multimedia Tools and Applications 74, 523\u2013542 (2015)","journal-title":"Multimedia Tools and Applications"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Singh, A., Chakaborty, O., Varshney, A., Panda, R., Feris, R., Senko, K., Das, A.: Semi - supervised action recognition with temporal contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10389\u201310399 (2021)","DOI":"10.1109\/CVPR46437.2021.01025"},{"key":"22_CR22","first-page":"596","volume":"33","author":"K Sohn","year":"2020","unstructured":"Sohn, K., Berthelot, D., Carlini, N., Zhang, Z., Zhang, H., Raffel, C.A., Cubuk, E.D., Kurakin, A., Li, C.L.: Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Adv. Neural. Inf. Process. Syst. 33, 596\u2013608 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_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":"22_CR24","first-page":"6837","volume":"33","author":"Y Tian","year":"2020","unstructured":"Tian, Y., Sun, C., Poole, B., Krishnan, D., Schmmid, C., Isola, P.: What makes for good views for contrastive learning? Adv. Neural. Inf. Process. Syst. 33, 6837\u20136839 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR25","first-page":"19511","volume":"35","author":"Y Tian","year":"2022","unstructured":"Tian, Y.: Understanding deep contrastive learning via coordinate-wise optimization. Adv. Neural. Inf. Process. Syst. 35, 19511\u201319522 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"3","key":"22_CR26","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1109\/TCSVT.2022.3310271","volume":"33","author":"A Tong","year":"2023","unstructured":"Tong, A., Tang, C., Weng, W.: Semi - supervised action recognition from temporal augmentation using curriculum learning. IEEE Trans. Circuits Syst. Video Technol. 33(3), 1301\u20131312 (2023). https:\/\/doi.org\/10.1109\/TCSVT.2022.3310271","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"22_CR27","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jegou, H.: Training data-efficient image transformers & distillation through attention. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 10347\u201310357. PMLR (18\u201324 Jul 2021), https:\/\/proceedings.mlr.press\/v139\/touvron21a.html"},{"issue":"29","key":"22_CR28","doi-asserted-by":"publisher","first-page":"42117","DOI":"10.1007\/s11042-021-11220-4","volume":"81","author":"N Varshney","year":"2022","unstructured":"Varshney, N., Bakariya, B.: Deep convolutional neural model for human activities recognition in a sequence of video by combining multiple cnn streams. Multimedia Tools and Applications 81(29), 42117\u201342129 (2022)","journal-title":"Multimedia Tools and Applications"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, H., Shen, Y., Fei, J., Li, W., Jin, G., Wu, L., Zhao, R., Le, X.: Semi-supervised semantic segmentation using unreliable pseudo-labels. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 4248\u20134257 (June 2022)","DOI":"10.1109\/CVPR52688.2022.00421"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Wu, J., Sun, W., Gan, T., Ding, N., Jiang, F., Shen, J., Nie, L.: Neighbor-guided consistent and contrastive learning for semi-supervised action recognition. IEEE Transactions on Image Processing (2023)","DOI":"10.1109\/TIP.2023.3265261"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Xiao, J., Jing, L., Zhang, L., He, J., She, Q., Zho, Z., Yuile, A., Li, Y.: Learning from temporal gradient for semi - supervised action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 3252\u20133262 (2022)","DOI":"10.1109\/CVPR52688.2022.00325"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Xiong, B., Fan, H., Grauman, K., Feichtenhofer, C.: Multiview pseudo-labeling for semi-supervised learning from video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). pp. 7209\u20137219 (October 2021)","DOI":"10.1109\/ICCV48922.2021.00712"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Xu, Y., Wei, F., Sun, X., Yang, C., Shen, Y., Dai, B., Zhou, B., Lin, S.: Cross-model pseudo-labeling for semi-supervised action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 2959\u20132968 (2022)","DOI":"10.1109\/CVPR52688.2022.00297"},{"key":"22_CR35","unstructured":"Yang, C., Xu, Y., Dai, B., Zho, B.: Video representation learning with visual temporal consistency. arXiv preprint arXiv:2006.15599 (2020)"},{"key":"22_CR36","first-page":"18408","volume":"34","author":"B Zhang","year":"2021","unstructured":"Zhang, B., Wang, Y., Hou, W., Wu, H., Wang, J., Okumura, M., Shinozaki, T.: Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling. Adv. Neural. Inf. Process. Syst. 34, 18408\u201318419 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"10\u201311","key":"22_CR37","doi-asserted-by":"publisher","first-page":"2334","DOI":"10.1016\/j.patcog.2010.06.018","volume":"44","author":"T Zhang","year":"2011","unstructured":"Zhang, T., Liu, S., Xu, C., Lu, H.: Boosted multi-class semi-supervised learning for human action recognition. Pattern Recogn. 44(10\u201311), 2334\u20132342 (2011)","journal-title":"Pattern Recogn."},{"key":"22_CR38","doi-asserted-by":"crossref","unstructured":"Zheng, S., Chen, S., Jin, Q.: Few-shot action recognition with hierarchical matching and contrastive learning. In: European Conference on Computer Vision. pp. 297\u2013313. Springer (2022)","DOI":"10.1007\/978-3-031-19772-7_18"},{"key":"22_CR39","unstructured":"Zhu, Y., Li, X., Liu, C., Zolfaghari, M., Xiong, Y., Wu, C., Zhang, Z., Tighe, J., Manmatha, R., Li, M.: A comprehensive study of deep video action recognition. arXiv preprint arXiv:2012.06567 (2020)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78354-8_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T11:31:28Z","timestamp":1733225488000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78354-8_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031783531","9783031783548"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78354-8_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}