{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T06:45:58Z","timestamp":1785653158954,"version":"3.56.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032316653","type":"print"},{"value":"9783032316660","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-31666-0_7","type":"book-chapter","created":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:47:47Z","timestamp":1785649667000},"page":"96-111","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EvoStruggle: A Dataset Capturing the Evolution of Struggle Across Activities and Skill Levels"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8115-8795","authenticated-orcid":false,"given":"Shijia","family":"Feng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5918-9029","authenticated-orcid":false,"given":"Michael","family":"Wray","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8973-1931","authenticated-orcid":false,"given":"Walterio","family":"Mayol-Cuevas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: CVPR, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Cheng, F., Bertasius, G.: Tallformer: temporal action localization with a long-memory transformer. arXiv:2204.01680 (2022)","DOI":"10.1007\/978-3-031-19830-4_29"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Doughty, H., Damen, D., Mayol-Cuevas, W.: Who\u2019s better? Who\u2019s best? pairwise deep ranking for skill determination. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00634"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Doughty, H., Mayol-Cuevas, W., Damen, D.: The pros and cons: rank-aware temporal attention for skill determination in long videos. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00805"},{"key":"7_CR5","doi-asserted-by":"publisher","unstructured":"Dutta, A., Zisserman, A.: The VIA annotation software for images, audio and video. In: MM \u201919. ACM, New York, NY, USA (2019). https:\/\/doi.org\/10.1145\/3343031.3350535","DOI":"10.1145\/3343031.3350535"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Fabian Caba Heilbron, V., Escorcia, B.G., Niebles, J.C.: ActivityNet: a large-scale video benchmark for human activity understanding. In: CVPR, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Farha, Y.A., Gall, J.: MS-TCN: multi-stage temporal convolutional network for action segmentation. In: CVPR, pp. 3575\u20133584 (2019)","DOI":"10.1109\/CVPR.2019.00369"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., et al.: Slowfast networks for video recognition. arXiv:1812.03982 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"7_CR9","unstructured":"Feng, S., et al.: Are you struggling? Dataset and baselines for struggle determination in assembly videos. arXiv:2402.11057 (2024)"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Flaborea, A., et al.: Prego: online mistake detection in procedural egocentric videos. In: CVPR, pp. 18483\u201318492 (2024)","DOI":"10.1109\/CVPR52733.2024.01749"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Ghoddoosian, R., et al.: Weakly-supervised action segmentation and unseen error detection in anomalous instructional videos. In: ICCV, pp. 10128\u201310138 (2023)","DOI":"10.1109\/ICCV51070.2023.00929"},{"key":"7_CR12","unstructured":"Grauman, K., et al.: Ego-Exo4D: understanding skilled human activity from first- and third-person perspectives. arXiv:2311.18259 (2024)"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Jang, Y., et al.: Epic-tent: an egocentric video dataset for camping tent assembly. In: ICCVW, pp. 4461\u20134469. IEEE Computer Society, Los Alamitos, CA, USA (2019)","DOI":"10.1109\/ICCVW.2019.00547"},{"key":"7_CR14","unstructured":"Jiang, Y.G., et al.: THUMOS challenge: action recognition with a large number of classes (2014). http:\/\/crcv.ucf.edu\/THUMOS14\/"},{"key":"7_CR15","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv:1705.06950 (2017)"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Lin, C., et al.: Learning salient boundary feature for anchor-free temporal action localization. In: CVPR, pp. 3320\u20133329 (2021)","DOI":"10.1109\/CVPR46437.2021.00333"},{"key":"7_CR17","doi-asserted-by":"publisher","unstructured":"Liu, X., et al.: End-to-end temporal action detection with transformer. TIP 31, 5427\u20135441 (2022). https:\/\/doi.org\/10.1109\/TIP.2022.3195321","DOI":"10.1109\/TIP.2022.3195321"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: FineAction: a fine-grained video dataset for temporal action localization. arXiv:2105.11107 (2022)","DOI":"10.1109\/TIP.2022.3217368"},{"issue":"1","key":"7_CR19","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1146\/annurev.ps.42.020191.001241","volume":"42","author":"K Newell","year":"1991","unstructured":"Newell, K.: Motor skill acquisition. Annu. Rev. Psychol. 42(1), 213\u2013237 (1991)","journal-title":"Annu. Rev. Psychol."},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Parmar, P., Morris, B.: Action quality assessment across multiple actions. In: WACV, pp. 1468\u20131476. IEEE (2019)","DOI":"10.1109\/WACV.2019.00161"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Parmar, P., Tran Morris, B.: What and how well you performed? A multitask learning approach to action quality assessment. In: CVPR, pp. 304\u2013313 (2019)","DOI":"10.1109\/CVPR.2019.00039"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Sener, F., et al.: Assembly101: a large-scale multi-view video dataset for understanding procedural activities. arXiv:2203.14712 (2022)","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Shao, D., et al.: FineGym: a hierarchical video dataset for fine-grained action understanding. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Shi, D., et al.: TriDet: temporal action detection with relative boundary modeling. In: CVPR, pp. 18857\u201318866 (2023)","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"7_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Holoassist: an egocentric human interaction dataset for interactive AI assistants in the real world. In: ICCV, pp. 20270\u201320281 (2023)","DOI":"10.1109\/ICCV51070.2023.01854"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: FineDiving: a fine-grained dataset for procedure-aware action quality assessment. arXiv:2204.03646 (2022)","DOI":"10.1109\/CVPR52688.2022.00296"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Yang, M., et al.: Adapting short-term transformers for action detection in untrimmed videos. In: CVPR, pp. 18570\u201318579 (2024)","DOI":"10.1109\/CVPR52733.2024.01757"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Yi, F., Wen, H., Jiang, T.: ASFormer: transformer for action segmentation. In: BMVC (2021)","DOI":"10.5244\/C.35.49"},{"key":"7_CR30","doi-asserted-by":"publisher","unstructured":"Zhang, C.L., Wu, J., Li, Y.: ActionFormer: localizing moments of actions with transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol. 13664, pp. 492\u2013510. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19772-7_29","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Zhao, C., et al.: Re2TAL: rewiring pretrained video backbones for reversible temporal action localization. In: CVPR, pp. 10637\u201310647 (2023)","DOI":"10.1109\/CVPR52729.2023.01025"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31666-0_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:47:49Z","timestamp":1785649669000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31666-0_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,3]]},"ISBN":["9783032316653","9783032316660"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31666-0_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,3]]},"assertion":[{"value":"3 August 2026","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":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}