{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:23:37Z","timestamp":1740108217227,"version":"3.37.3"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,1,27]],"date-time":"2024-01-27T00:00:00Z","timestamp":1706313600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,27]],"date-time":"2024-01-27T00:00:00Z","timestamp":1706313600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Beijing Natural Science Foundation","award":["4222037","L181010"],"award-info":[{"award-number":["4222037","L181010"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972035"],"award-info":[{"award-number":["61972035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1007\/s00138-023-01505-z","type":"journal-article","created":{"date-parts":[[2024,1,27]],"date-time":"2024-01-27T20:02:11Z","timestamp":1706385731000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Tackling confusion among actions for action segmentation with adaptive margin and energy-driven refinement"],"prefix":"10.1007","volume":"35","author":[{"given":"Zhichao","family":"Ma","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3528-4739","authenticated-orcid":false,"given":"Kan","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,27]]},"reference":[{"key":"1505_CR1","doi-asserted-by":"publisher","unstructured":"Lv, H., Chen, C., Cui, Z., Xu, C., Li, Y., Yang, J.: Learning normal dynamics in videos with meta prototype network. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15420\u201315429 (2021). https:\/\/doi.org\/10.1109\/cvpr46437.2021.01517","DOI":"10.1109\/cvpr46437.2021.01517"},{"issue":"3","key":"1505_CR2","doi-asserted-by":"publisher","first-page":"1070","DOI":"10.1109\/tpami.2019.2944377","volume":"43","author":"W Luo","year":"2021","unstructured":"Luo, W., Liu, W., Lian, D., Tang, J., Duan, L., Peng, X., Gao, S.: Video anomaly detection with sparse coding inspired deep neural networks. IEEE Trans. Pattern Anal. Mach. Intell. 43(3), 1070\u20131084 (2021). https:\/\/doi.org\/10.1109\/tpami.2019.2944377","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1505_CR3","doi-asserted-by":"publisher","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4724\u20134733 (2017). https:\/\/doi.org\/10.1109\/cvpr.2017.502","DOI":"10.1109\/cvpr.2017.502"},{"key":"1505_CR4","doi-asserted-by":"publisher","unstructured":"Mac, K.-N., Joshi, D., Yeh, R., Xiong, J., Feris, R., Do, M.: Learning motion in feature space: Locally-consistent deformable convolution networks for fine-grained action detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6281\u20136290 (2019). https:\/\/doi.org\/10.1109\/iccv.2019.00638","DOI":"10.1109\/iccv.2019.00638"},{"key":"1505_CR5","doi-asserted-by":"crossref","unstructured":"Wang, D., Hu, D., Li, X., Dou, D.: Temporal relational modeling with self-supervision for action segmentation. In: Thirty-Fifth AAAI Conference on Artificial Intelligence, Virtual Event, February 2-9, 2021, pp. 2729\u20132737 (2021)","DOI":"10.1609\/aaai.v35i4.16377"},{"key":"1505_CR6","doi-asserted-by":"publisher","unstructured":"Farha, Y.A., Gall, J.: MS-TCN: Multi-stage temporal convolutional network for action segmentation. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3570\u20133579 (2019). https:\/\/doi.org\/10.1109\/cvpr.2019.00369","DOI":"10.1109\/cvpr.2019.00369"},{"key":"1505_CR7","doi-asserted-by":"publisher","unstructured":"Li, S.-J., AbuFarha, Y., Liu, Y., Cheng, M.-M., Gall, J.: MS-TCN++: Multi-stage temporal convolutional network for action segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1\u20131 (2020). https:\/\/doi.org\/10.1109\/tpami.2020.3021756","DOI":"10.1109\/tpami.2020.3021756"},{"key":"1505_CR8","doi-asserted-by":"publisher","unstructured":"Lea, C., Flynn, M.D., Vidal, R., Reiter, A., Hager, G.D.: Temporal convolutional networks for action segmentation and detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1003\u20131012 (2017). https:\/\/doi.org\/10.1109\/cvpr.2017.113","DOI":"10.1109\/cvpr.2017.113"},{"key":"1505_CR9","doi-asserted-by":"publisher","unstructured":"Huang, Y., Sugano, Y., Sato, Y.: Improving action segmentation via graph-based temporal reasoning. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14021\u201314031 (2020). https:\/\/doi.org\/10.1109\/cvpr42600.2020.01404","DOI":"10.1109\/cvpr42600.2020.01404"},{"key":"1505_CR10","doi-asserted-by":"publisher","unstructured":"Lei, P., Todorovic, S.: Temporal deformable residual networks for action segmentation in videos. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6742\u20136751 (2018). https:\/\/doi.org\/10.1109\/cvpr.2018.00705","DOI":"10.1109\/cvpr.2018.00705"},{"key":"1505_CR11","doi-asserted-by":"publisher","unstructured":"Wang, Z., Gao, Z., Wang, L., Li, Z., Wu, G.: Boundary-aware cascade networks for temporal action segmentation. In: Computer Vision \u2013 ECCV 2020, pp. 34\u201351 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_3","DOI":"10.1007\/978-3-030-58595-2_3"},{"key":"1505_CR12","doi-asserted-by":"publisher","unstructured":"Gao, S.-H., Han, Q., Li, Z.-Y., Peng, P., Wang, L., Cheng, M.-M.: Global2local: Efficient structure search for video action segmentation. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16800\u201316809 (2021). https:\/\/doi.org\/10.1109\/cvpr46437.2021.01653","DOI":"10.1109\/cvpr46437.2021.01653"},{"key":"1505_CR13","doi-asserted-by":"publisher","unstructured":"Chen, M.-H., Li, B., Bao, Y., AlRegib, G., Kira, Z.: Action segmentation with joint self-supervised temporal domain adaptation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9451\u20139460 (2020). https:\/\/doi.org\/10.1109\/cvpr42600.2020.00947","DOI":"10.1109\/cvpr42600.2020.00947"},{"key":"1505_CR14","doi-asserted-by":"publisher","unstructured":"Chen, L., Li, M., Duan, Y., Zhou, J., Lu, J.: Uncertainty-aware representation learning for action segmentation. In: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pp. 820\u2013826 (2022). https:\/\/doi.org\/10.24963\/ijcai.2022\/115","DOI":"10.24963\/ijcai.2022\/115"},{"key":"1505_CR15","doi-asserted-by":"publisher","unstructured":"Ishikawa, Y., Kasai, S., Aoki, Y., Kataoka, H.: Alleviating over-segmentation errors by detecting action boundaries. In: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 2321\u20132330 (2021). https:\/\/doi.org\/10.1109\/wacv48630.2021.00237","DOI":"10.1109\/wacv48630.2021.00237"},{"key":"1505_CR16","doi-asserted-by":"publisher","unstructured":"Zhang, S., Li, Z., Yan, S., He, X., Sun, J.: Distribution alignment: A unified framework for long-tail visual recognition. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2361\u20132370 (2021). https:\/\/doi.org\/10.1109\/cvpr46437.2021.00239","DOI":"10.1109\/cvpr46437.2021.00239"},{"key":"1505_CR17","doi-asserted-by":"publisher","unstructured":"Cui, Y., Jia, M., Lin, T.-Y., Song, Y., Belongie, S.: Class-balanced loss based on effective number of samples. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9268\u20139277 (2019). https:\/\/doi.org\/10.1109\/cvpr.2019.00949","DOI":"10.1109\/cvpr.2019.00949"},{"key":"1505_CR18","doi-asserted-by":"publisher","unstructured":"Wang, T., Zhu, Y., Zhao, C., Zeng, W., Wang, J., Tang, M.: Adaptive class suppression loss for long-tail object detection. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3103\u20133112 (2021). https:\/\/doi.org\/10.1109\/cvpr46437.2021.00312","DOI":"10.1109\/cvpr46437.2021.00312"},{"key":"1505_CR19","doi-asserted-by":"publisher","unstructured":"Zhou, B., Cui, Q., Wei, X.-S., Chen, Z.-M.: BBN: Bilateral-branch network with cumulative learning for long-tailed visual recognition. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9716\u20139725 (2020). https:\/\/doi.org\/10.1109\/cvpr42600.2020.00974","DOI":"10.1109\/cvpr42600.2020.00974"},{"key":"1505_CR20","doi-asserted-by":"publisher","unstructured":"Liu, J., Sun, Y., Han, C., Dou, Z., Li, W.: Deep representation learning on long-tailed data: A learnable embedding augmentation perspective. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2967\u20132976 (2020). https:\/\/doi.org\/10.1109\/cvpr42600.2020.00304","DOI":"10.1109\/cvpr42600.2020.00304"},{"key":"1505_CR21","doi-asserted-by":"publisher","unstructured":"Xiang, L., Ding, G., Han, J.: Learning from multiple experts: Self-paced knowledge distillation for long-tailed classification. In: Computer Vision \u2013 ECCV 2020, pp. 247\u2013263 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_15","DOI":"10.1007\/978-3-030-58558-7_15"},{"key":"1505_CR22","doi-asserted-by":"publisher","unstructured":"Chen, J., Wang, X., Guo, Z., Zhang, X., Sun, J.: Dynamic region-aware convolution. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8060\u20138069 (2021). https:\/\/doi.org\/10.1109\/cvpr46437.2021.00797","DOI":"10.1109\/cvpr46437.2021.00797"},{"issue":"10","key":"1505_CR23","doi-asserted-by":"publisher","first-page":"2522","DOI":"10.1109\/tpami.2017.2756936","volume":"40","author":"T Chen","year":"2018","unstructured":"Chen, T., Lu, S., Fan, J.: S-CNN: Subcategory-aware convolutional networks for object detection. IEEE Trans. Pattern Anal. Mach. Intell. 40(10), 2522\u20132528 (2018). https:\/\/doi.org\/10.1109\/tpami.2017.2756936","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"1505_CR24","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1109\/TPAMI.2018.2884469","volume":"42","author":"H Kuehne","year":"2020","unstructured":"Kuehne, H., Richard, A., Gall, J.: A hybrid rnn-hmm approach for weakly supervised temporal action segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 42(4), 765\u2013779 (2020). https:\/\/doi.org\/10.1109\/TPAMI.2018.2884469","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1505_CR25","doi-asserted-by":"publisher","unstructured":"Richard, A., Kuehne, H., Gall, J.: Weakly supervised action learning with RNN based fine-to-coarse modeling. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1273\u20131282 (2017). https:\/\/doi.org\/10.1109\/cvpr.2017.140","DOI":"10.1109\/cvpr.2017.140"},{"key":"1505_CR26","doi-asserted-by":"publisher","unstructured":"Fayyaz, M., Gall, J.: SCT: Set constrained temporal transformer for set supervised action segmentation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 498\u2013507 (2020). https:\/\/doi.org\/10.1109\/cvpr42600.2020.00058","DOI":"10.1109\/cvpr42600.2020.00058"},{"key":"1505_CR27","doi-asserted-by":"publisher","unstructured":"Ghosh, P., Yao, Y., Davis, L.S., Divakaran, A.: Stacked spatio-temporal graph convolutional networks for action segmentation. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 565\u2013574 (2020). https:\/\/doi.org\/10.1109\/wacv45572.2020.9093361","DOI":"10.1109\/wacv45572.2020.9093361"},{"key":"1505_CR28","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Tang, S., Muandet, K., Jarvers, C., Neumann, H.: Local temporal bilinear pooling for fine-grained action parsing. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11997\u201312007 (2019). https:\/\/doi.org\/10.1109\/cvpr.2019.01228","DOI":"10.1109\/cvpr.2019.01228"},{"key":"1505_CR29","unstructured":"Yi, F., Wen, H., Jiang, T.: Asformer: Transformer for action segmentation. In: The British Machine Vision Conference (2021)"},{"key":"1505_CR30","doi-asserted-by":"crossref","unstructured":"Du, D., Su, B., Li, Y., Qi, Z., Si, L., Shan, Y.: Do we really need temporal convolutions in action segmentation? (2022)","DOI":"10.1109\/ICME55011.2023.00178"},{"key":"1505_CR31","doi-asserted-by":"publisher","unstructured":"Behrmann, N., Golestaneh, S.A., Kolter, Z., Gall, J., Noroozi, M.: Unified fully and timestamp supervised temporal action segmentation via sequence to sequence translation. In: Computer Vision - ECCV 2022 - 17th European Conference, vol. 13695, pp. 52\u201368 (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_4","DOI":"10.1007\/978-3-031-19833-5_4"},{"key":"1505_CR32","doi-asserted-by":"publisher","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: Learning a discriminative feature network for semantic segmentation. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1857\u20131866 (2018). https:\/\/doi.org\/10.1109\/cvpr.2018.00199","DOI":"10.1109\/cvpr.2018.00199"},{"key":"1505_CR33","doi-asserted-by":"publisher","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: Additive angular margin loss for deep face recognition. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4685\u20134694 (2019). https:\/\/doi.org\/10.1109\/cvpr.2019.00482","DOI":"10.1109\/cvpr.2019.00482"},{"key":"1505_CR34","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event, vol. 119, pp. 1597\u20131607 (2020)"},{"key":"1505_CR35","doi-asserted-by":"publisher","unstructured":"Wang, Z., Wang, S., Yang, S., Li, H., Li, J., Li, Z.: Weakly supervised fine-grained image classification via guassian mixture model oriented discriminative learning. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9746\u20139755 (2020). https:\/\/doi.org\/10.1109\/cvpr42600.2020.00977","DOI":"10.1109\/cvpr42600.2020.00977"},{"key":"1505_CR36","doi-asserted-by":"publisher","unstructured":"Zhu, J., Liu, Y., Zhang, Y., Chen, Z., Wu, X.: Multi-attribute discriminative representation learning for prediction of adverse drug-drug interaction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1\u20131 (2022). https:\/\/doi.org\/10.1109\/tpami.2021.3135841","DOI":"10.1109\/tpami.2021.3135841"},{"issue":"2","key":"1505_CR37","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1109\/tpami.2019.2937292","volume":"43","author":"J Wang","year":"2021","unstructured":"Wang, J., Cherian, A.: Discriminative video representation learning using support vector classifiers. IEEE Trans. Pattern Anal. Mach. Intell. 43(2), 420\u2013433 (2021). https:\/\/doi.org\/10.1109\/tpami.2019.2937292","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1505_CR38","doi-asserted-by":"publisher","unstructured":"Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: SphereFace: Deep hypersphere embedding for face recognition. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6738\u20136746 (2017). https:\/\/doi.org\/10.1109\/cvpr.2017.713","DOI":"10.1109\/cvpr.2017.713"},{"issue":"7","key":"1505_CR39","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1109\/lsp.2018.2822810","volume":"25","author":"F Wang","year":"2018","unstructured":"Wang, F., Cheng, J., Liu, W., Liu, H.: Additive margin softmax for face verification. IEEE Signal Process. Lett. 25(7), 926\u2013930 (2018). https:\/\/doi.org\/10.1109\/lsp.2018.2822810","journal-title":"IEEE Signal Process. Lett."},{"key":"1505_CR40","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.isatra.2021.02.006","volume":"118","author":"O Tutsoy","year":"2021","unstructured":"Tutsoy, O., Barkana, D.E.: Model free adaptive control of the under-actuated robot manipulator with the chaotic dynamics. ISA Trans. 118, 106\u2013115 (2021). https:\/\/doi.org\/10.1016\/j.isatra.2021.02.006","journal-title":"ISA Trans."},{"issue":"12","key":"1505_CR41","doi-asserted-by":"publisher","first-page":"9477","DOI":"10.1109\/TPAMI.2021.3127674","volume":"44","author":"O Tutsoy","year":"2022","unstructured":"Tutsoy, O.: Pharmacological, non-pharmacological policies and mutation: An artificial intelligence based multi-dimensional policy making algorithm for controlling the casualties of the pandemic diseases. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 9477\u20139488 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2021.3127674","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"1505_CR42","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/tpami.2017.2699184","volume":"40","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2018). https:\/\/doi.org\/10.1109\/tpami.2017.2699184","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1505_CR43","doi-asserted-by":"publisher","unstructured":"Zhang, H., Dana, K., Shi, J., Zhang, Z., Wang, X., Tyagi, A., Agrawal, A.: Context encoding for semantic segmentation. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7151\u20137160 (2018). https:\/\/doi.org\/10.1109\/cvpr.2018.00747","DOI":"10.1109\/cvpr.2018.00747"},{"key":"1505_CR44","doi-asserted-by":"publisher","unstructured":"Yu, F., Koltun, V., Funkhouser, T.: Dilated residual networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 636\u2013644 (2017). https:\/\/doi.org\/10.1109\/cvpr.2017.75","DOI":"10.1109\/cvpr.2017.75"},{"issue":"2","key":"1505_CR45","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1109\/tpami.2019.2934852","volume":"43","author":"J Xie","year":"2021","unstructured":"Xie, J., Zhu, S.-C., Wu, Y.N.: Learning energy-based spatial-temporal generative ConvNets for dynamic patterns. IEEE Trans. Pattern Anal. Mach. Intell. 43(2), 516\u2013531 (2021). https:\/\/doi.org\/10.1109\/tpami.2019.2934852","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1505_CR46","doi-asserted-by":"publisher","unstructured":"Bond-Taylor, S., Leach, A., Long, Y., Willcocks, C.G.: Deep generative modelling: A comparative review of VAEs, GANs, normalizing flows, energy-based and autoregressive models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1\u20131 (2021). https:\/\/doi.org\/10.1109\/tpami.2021.3116668","DOI":"10.1109\/tpami.2021.3116668"},{"key":"1505_CR47","unstructured":"Liu, W., Wang, X., Owens, J., Li, Y.: Energy-based out-of-distribution detection. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 21464\u201321475 (2020)"},{"key":"1505_CR48","doi-asserted-by":"crossref","unstructured":"Stein, S., Mckenna, S.J.: Combining embedded accelerometers with computer vision for recognizing food preparation activities. In: The 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp\u2019 13, Zurich, Switzerland, September 8-12, 2013, vol. 33, pp. 3281\u20133288 (2013)","DOI":"10.1145\/2493432.2493482"},{"key":"1505_CR49","doi-asserted-by":"publisher","unstructured":"Fathi, A., Ren, X., Rehg, J.M.: Learning to recognize objects in egocentric activities. In: CVPR 2011, pp. 3281\u20133288 (2011). https:\/\/doi.org\/10.1109\/cvpr.2011.5995444","DOI":"10.1109\/cvpr.2011.5995444"},{"key":"1505_CR50","doi-asserted-by":"publisher","unstructured":"Kuehne, H., Arslan, A., Serre, T.: The language of actions: Recovering the syntax and semantics of goal-directed human activities. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 780\u2013787 (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.105","DOI":"10.1109\/CVPR.2014.105"},{"key":"1505_CR51","doi-asserted-by":"publisher","unstructured":"Kuehne, H., Gall, J., Serre, T.: An end-to-end generative framework for video segmentation and recognition. In: 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1\u20138 (2016). https:\/\/doi.org\/10.1109\/WACV.2016.7477701","DOI":"10.1109\/WACV.2016.7477701"},{"key":"1505_CR52","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., K\u00f6pf, A., Yang, E.Z., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J., Chintala, S.: Pytorch: An imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems 32, pp. 8024\u20138035 (2019)"},{"issue":"3","key":"1505_CR53","doi-asserted-by":"publisher","first-page":"2984","DOI":"10.1109\/TPAMI.2022.3183829","volume":"45","author":"S Gao","year":"2023","unstructured":"Gao, S., Li, Z.-Y., Han, Q., Cheng, M.-M., Wang, L.: Rf-next: Efficient receptive field search for convolutional neural networks. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 2984\u20133002 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2022.3183829","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1505_CR54","doi-asserted-by":"publisher","unstructured":"Ahn, H., Lee, D.: Refining action segmentation with hierarchical video representations. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 16282\u201316290 (2021). https:\/\/doi.org\/10.1109\/iccv48922.2021.01599","DOI":"10.1109\/iccv48922.2021.01599"},{"issue":"12","key":"1505_CR55","doi-asserted-by":"publisher","first-page":"1573","DOI":"10.1007\/s10489-022-03382-x","volume":"52","author":"W Chen","year":"2022","unstructured":"Chen, W., Chai, Y., Qi, M., Sun, H., Pu, Q., Kong, J., Zheng, C.: Bottom-up improved multistage temporal convolutional network for action segmentation. Appl. Intell. 52(12), 1573\u20137497 (2022)","journal-title":"Appl. Intell."}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-023-01505-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-023-01505-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-023-01505-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,23]],"date-time":"2024-03-23T06:35:56Z","timestamp":1711175756000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-023-01505-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,27]]},"references-count":55,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["1505"],"URL":"https:\/\/doi.org\/10.1007\/s00138-023-01505-z","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"type":"print","value":"0932-8092"},{"type":"electronic","value":"1432-1769"}],"subject":[],"published":{"date-parts":[[2024,1,27]]},"assertion":[{"value":"26 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 December 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 December 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 January 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"21"}}