{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T18:31:26Z","timestamp":1762108286303,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031734038"},{"type":"electronic","value":"9783031734045"}],"license":[{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"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\/978-3-031-73404-5_19","type":"book-chapter","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T16:03:13Z","timestamp":1730217793000},"page":"320-338","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Long-Tail Temporal Action Segmentation with\u00a0Group-Wise Temporal Logit Adjustment"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8320-1727","authenticated-orcid":false,"given":"Zhanzhong","family":"Pang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5004-6005","authenticated-orcid":false,"given":"Fadime","family":"Sener","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0825-6775","authenticated-orcid":false,"given":"Shrinivas","family":"Ramasubramanian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7418-6141","authenticated-orcid":false,"given":"Angela","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,30]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Alayrac, J.B., Bojanowski, P., Agrawal, N., Sivic, J., Laptev, I., Lacoste-Julien, S.: Unsupervised learning from narrated instruction videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4575\u20134583 (2016)","DOI":"10.1109\/CVPR.2016.495"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Bhattacharya, S., Kalayeh, M.M., Sukthankar, R., Shah, M.: Recognition of complex events: exploiting temporal dynamics between underlying concepts. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2235\u20132242 (2014)","DOI":"10.1109\/CVPR.2014.287"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Brodersen, K.H., Ong, C.S., Stephan, K.E., Buhmann, J.M.: The balanced accuracy and its posterior distribution. In: 2010 20th International Conference on Pattern Recognition, pp. 3121\u20133124. IEEE (2010)","DOI":"10.1109\/ICPR.2010.764"},{"key":"19_CR4","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.neunet.2018.07.011","volume":"106","author":"M Buda","year":"2018","unstructured":"Buda, M., Maki, A., Mazurowski, M.A.: A systematic study of the class imbalance problem in convolutional neural networks. Neural Netw. 106, 249\u2013259 (2018)","journal-title":"Neural Netw."},{"key":"19_CR5","unstructured":"Byrd, J., Lipton, Z.: What is the effect of importance weighting in deep learning? In: International Conference on Machine Learning, pp. 872\u2013881. PMLR (2019)"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Cai, J., Wang, Y., Hwang, J.N.: ACE: ally complementary experts for solving long-tailed recognition in one-shot. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 112\u2013121 (2021)","DOI":"10.1109\/ICCV48922.2021.00018"},{"key":"19_CR7","unstructured":"Cao, K., Wei, C., Gaidon, A., Arechiga, N., Ma, T.: Learning imbalanced datasets with label-distribution-aware margin loss. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"19_CR8","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":"19_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Fan, Q., Pankanti, S., Choudhary, A.: Temporal sequence modeling for video event detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2227\u20132234 (2014)","DOI":"10.1109\/CVPR.2014.286"},{"key":"19_CR10","unstructured":"Collell, G., Prelec, D., Patil, K.: Reviving threshold-moving: a simple plug-in bagging ensemble for binary and multiclass imbalanced data. arXiv preprint arXiv:1606.08698 (2016)"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jia, M., Lin, T.Y., Song, Y., Belongie, S.: Class-balanced loss based on effective number of samples. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9268\u20139277 (2019)","DOI":"10.1109\/CVPR.2019.00949"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Ding, G., Sener, F., Yao, A.: Temporal action segmentation: an analysis of modern techniques. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3327284"},{"key":"19_CR13","unstructured":"Drummond, C., Holte, R.C., et\u00a0al.: C4. 5, class imbalance, and cost sensitivity: why under-sampling beats over-sampling. In: Workshop on Learning from Imbalanced Datasets II, vol.\u00a011, pp.\u00a01\u20138 (2003)"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Farha, Y.A., Gall, J.: MS-TCN: multi-stage temporal convolutional network for action segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3575\u20133584 (2019)","DOI":"10.1109\/CVPR.2019.00369"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Fathi, A., Farhadi, A., Rehg, J.M.: Understanding egocentric activities. In: 2011 International Conference on Computer Vision, pp. 407\u2013414. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126269"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Fathi, A., Ren, X., Rehg, J.M.: Learning to recognize objects in egocentric activities. In: CVPR 2011, pp. 3281\u20133288. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"19_CR17","doi-asserted-by":"crossref","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16805\u201316814 (2021)","DOI":"10.1109\/CVPR46437.2021.01653"},{"key":"19_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"878","DOI":"10.1007\/11538059_91","volume-title":"Advances in Intelligent Computing","author":"H Han","year":"2005","unstructured":"Han, H., Wang, W.-Y., Mao, B.-H.: Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning. In: Huang, D.-S., Zhang, X.-P., Huang, G.-B. (eds.) ICIC 2005. LNCS, vol. 3644, pp. 878\u2013887. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/11538059_91"},{"issue":"9","key":"19_CR19","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","volume":"21","author":"H He","year":"2009","unstructured":"He, H., Garcia, E.A.: Learning from imbalanced data. IEEE Trans. Knowl. Data Eng. 21(9), 1263\u20131284 (2009)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Hu, X., Jiang, Y., Tang, K., Chen, J., Miao, C., Zhang, H.: Learning to segment the tail. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14045\u201314054 (2020)","DOI":"10.1109\/CVPR42600.2020.01406"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Huang, C., Li, Y., Loy, C.C., Tang, X.: Learning deep representation for imbalanced classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5375\u20135384 (2016)","DOI":"10.1109\/CVPR.2016.580"},{"key":"19_CR22","unstructured":"Kang, B., et al.: Decoupling representation and classifier for long-tailed recognition. arXiv preprint arXiv:1910.09217 (2019)"},{"key":"19_CR23","doi-asserted-by":"publisher","first-page":"81674","DOI":"10.1109\/ACCESS.2020.2991231","volume":"8","author":"B Kim","year":"2020","unstructured":"Kim, B., Kim, J.: Adjusting decision boundary for class imbalanced learning. IEEE Access 8, 81674\u201381685 (2020)","journal-title":"IEEE Access"},{"issue":"2","key":"19_CR24","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1093\/oxfordjournals.pan.a004868","volume":"9","author":"G King","year":"2001","unstructured":"King, G., Zeng, L.: Logistic regression in rare events data. Polit. Anal. 9(2), 137\u2013163 (2001)","journal-title":"Polit. Anal."},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Arslan, A., Serre, T.: The language of actions: recovering the syntax and semantics of goal-directed human activities. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 780\u2013787 (2014)","DOI":"10.1109\/CVPR.2014.105"},{"issue":"4","key":"19_CR26","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1109\/TPAMI.2018.2884469","volume":"42","author":"H Kuehne","year":"2018","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 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Lea, C., Flynn, M.D., Vidal, R., Reiter, A., Hager, G.D.: Temporal convolutional networks for action segmentation and detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 156\u2013165 (2017)","DOI":"10.1109\/CVPR.2017.113"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Lei, P., Todorovic, S.: Temporal deformable residual networks for action segmentation in videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6742\u20136751 (2018)","DOI":"10.1109\/CVPR.2018.00705"},{"key":"19_CR29","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 Trans. Pattern Anal. Machine Intell. 1 (2020). https:\/\/doi.org\/10.1109\/TPAMI.2020.3021756","DOI":"10.1109\/TPAMI.2020.3021756"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Overcoming classifier imbalance for long-tail object detection with balanced group softmax. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10991\u201311000 (2020)","DOI":"10.1109\/CVPR42600.2020.01100"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Liu, D., Li, Q., Dinh, A.D., Jiang, T., Shah, M., Xu, C.: Diffusion action segmentation. In: International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00930"},{"key":"19_CR33","unstructured":"Menon, A., Narasimhan, H., Agarwal, S., Chawla, S.: On the statistical consistency of algorithms for binary classification under class imbalance. In: International Conference on Machine Learning, pp. 603\u2013611. PMLR (2013)"},{"key":"19_CR34","unstructured":"Menon, A.K., Jayasumana, S., Rawat, A.S., Jain, H., Veit, A., Kumar, S.: Long-tail learning via logit adjustment. arXiv preprint arXiv:2007.07314 (2020)"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Perrett, T., Damen, D.: Recurrent assistance: cross-dataset training of LSTMs on kitchen tasks. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 1354\u20131362 (2017)","DOI":"10.1109\/ICCVW.2017.161"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Perrett, T., Sinha, S., Burghardt, T., Mirmehdi, M., Damen, D.: Use your head: improving long-tail video recognition. arXiv preprint arXiv:2304.01143 (2023)","DOI":"10.1109\/CVPR52729.2023.00239"},{"key":"19_CR37","unstructured":"Ren, M., Zeng, W., Yang, B., Urtasun, R.: Learning to reweight examples for robust deep learning. In: International Conference on Machine Learning, pp. 4334\u20134343. PMLR (2018)"},{"key":"19_CR38","doi-asserted-by":"crossref","unstructured":"Sener, F., et al.: Assembly101: a large-scale multi-view video dataset for understanding procedural activities. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21096\u201321106 (2022)","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"19_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1007\/978-3-319-46478-7_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Shen","year":"2016","unstructured":"Shen, L., Lin, Z., Huang, Q.: Relay backpropagation for effective learning of deep convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 467\u2013482. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_29"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Singh, B., Marks, T.K., Jones, M., Tuzel, O., Shao, M.: A multi-stream bi-directional recurrent neural network for fine-grained action detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1961\u20131970 (2016)","DOI":"10.1109\/CVPR.2016.216"},{"key":"19_CR41","unstructured":"Singhania, D., Rahaman, R., Yao, A.: Coarse to fine multi-resolution temporal convolutional network. arXiv preprint arXiv:2105.10859 (2021)"},{"key":"19_CR42","doi-asserted-by":"crossref","unstructured":"Stein, S., McKenna, S.J.: Combining embedded accelerometers with computer vision for recognizing food preparation activities. In: Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing, pp. 729\u2013738 (2013)","DOI":"10.1145\/2493432.2493482"},{"key":"19_CR43","doi-asserted-by":"crossref","unstructured":"Tan, J., et al.: Equalization loss for long-tailed object recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11662\u201311671 (2020)","DOI":"10.1109\/CVPR42600.2020.01168"},{"key":"19_CR44","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Seesaw loss for long-tailed instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9695\u20139704 (2021)","DOI":"10.1109\/CVPR46437.2021.00957"},{"key":"19_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1007\/978-3-030-58568-6_43","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Wang","year":"2020","unstructured":"Wang, T., et al.: The devil is in classification: a simple framework for long-tail instance segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 728\u2013744. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_43"},{"key":"19_CR46","unstructured":"Wang, Y.X., Ramanan, D., Hebert, M.: Learning to model the tail. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"19_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1007\/978-3-030-58595-2_3","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Wang","year":"2020","unstructured":"Wang, Z., Gao, Z., Wang, L., Li, Z., Wu, G.: Boundary-aware cascade networks for temporal action segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 34\u201351. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_3"},{"key":"19_CR48","unstructured":"Yi, F., Wen, H., Jiang, T.: Asformer: transformer for action segmentation. arXiv preprint arXiv:2110.08568 (2021)"},{"key":"19_CR49","unstructured":"Zhang, J., Liu, L., Wang, P., Shen, C.: To balance or not to balance: a simple-yet-effective approach for learning with long-tailed distributions. arXiv preprint arXiv:1912.04486 (2019)"},{"key":"19_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: Videolt: large-scale long-tailed video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7960\u20137969 (2021)","DOI":"10.1109\/ICCV48922.2021.00786"},{"key":"19_CR51","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Chen, W., Tan, X., Huang, K., Zhu, J.: Adaptive logit adjustment loss for long-tailed visual recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 3472\u20133480 (2022)","DOI":"10.1609\/aaai.v36i3.20258"},{"key":"19_CR52","doi-asserted-by":"crossref","unstructured":"Zhou, B., Cui, Q., Wei, X.S., Chen, Z.M.: BBN: bilateral-branch network with cumulative learning for long-tailed visual recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9719\u20139728 (2020)","DOI":"10.1109\/CVPR42600.2020.00974"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73404-5_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T19:44:39Z","timestamp":1745523879000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73404-5_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,30]]},"ISBN":["9783031734038","9783031734045"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73404-5_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,30]]},"assertion":[{"value":"30 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}