{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:18:50Z","timestamp":1780762730912,"version":"3.54.1"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200793","type":"print"},{"value":"9783031200809","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20080-9_33","type":"book-chapter","created":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T19:59:12Z","timestamp":1667419152000},"page":"567-584","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Weakly-Supervised Temporal Action Detection for\u00a0Fine-Grained Videos with\u00a0Hierarchical Atomic Actions"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3693-1750","authenticated-orcid":false,"given":"Zhi","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huijuan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,3]]},"reference":[{"key":"33_CR1","unstructured":"Abu-El-Haija, S., et al.: YouTube-8M: a large-scale video classification benchmark. arXiv preprint arXiv:1609.08675 (2016)"},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: Activitynet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"33_CR3","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1016\/j.patcog.2017.10.009","volume":"77","author":"MA Carbonneau","year":"2018","unstructured":"Carbonneau, M.A., Cheplygina, V., Granger, E., Gagnon, G.: Multiple instance learning: a survey of problem characteristics and applications. Pattern Recogn. 77, 329\u2013353 (2018)","journal-title":"Pattern Recogn."},{"key":"33_CR4","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":"33_CR5","unstructured":"Chen, C., Li, O., Tao, D., Barnett, A., Rudin, C., Su, J.K.: This looks like that: deep learning for interpretable image recognition. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"33_CR6","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: Infogan: interpretable representation learning by information maximizing generative adversarial nets. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, pp. 2180\u20132188 (2016)"},{"issue":"1","key":"33_CR7","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s11263-021-01531-2","volume":"130","author":"D Damen","year":"2022","unstructured":"Damen, D., et al.: Rescaling egocentric vision: collection, pipeline and challenges for epic-kitchens-100. Int. J. Comput. Vision 130(1), 33\u201355 (2022)","journal-title":"Int. J. Comput. Vision"},{"issue":"1","key":"33_CR8","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/S0004-3702(96)00034-3","volume":"89","author":"TG Dietterich","year":"1997","unstructured":"Dietterich, T.G., Lathrop, R.H., Lozano-P\u00e9rez, T.: Solving the multiple instance problem with axis-parallel rectangles. Artif. Intell. 89(1), 31\u201371 (1997)","journal-title":"Artif. Intell."},{"key":"33_CR9","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"},{"issue":"11","key":"33_CR10","doi-asserted-by":"publisher","first-page":"2782","DOI":"10.1109\/TPAMI.2013.65","volume":"35","author":"A Gaidon","year":"2013","unstructured":"Gaidon, A., Harchaoui, Z., Schmid, C.: Temporal localization of actions with actoms. IEEE Trans. Pattern Anal. Mach. Intell. 35(11), 2782\u20132795 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Ghoddoosian, R., Sayed, S., Athitsos, V.: Hierarchical modeling for task recognition and action segmentation in weakly-labeled instructional videos. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1922\u20131932 (2022)","DOI":"10.1109\/WACV51458.2022.00020"},{"key":"33_CR12","unstructured":"Ghorbani, A., Wexler, J., Kim, B.: Automating interpretability: discovering and testing visual concepts learned by neural networks. arXiv abs\/1902.03129 (2019)"},{"key":"33_CR13","unstructured":"Higgins, I., et al.: Scan: learning hierarchical compositional visual concepts. arXiv preprint arXiv:1707.03389 (2017)"},{"key":"33_CR14","unstructured":"Ilse, M., Tomczak, J., Welling, M.: Attention-based deep multiple instance learning. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 80, pp. 2127\u20132136. PMLR (2018)"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Ji, J., Krishna, R., Fei-Fei, L., Niebles, J.C.: Action genome: actions as compositions of spatio-temporal scene graphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10236\u201310247 (2020)","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"33_CR16","unstructured":"Jiang, Y.G., et al.: Thumos challenge: action recognition with a large number of classes (2014)"},{"issue":"2","key":"33_CR17","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1109\/TPAMI.2017.2670560","volume":"40","author":"YG Jiang","year":"2018","unstructured":"Jiang, Y.G., Wu, Z., Wang, J., Xue, X., Chang, S.F.: Exploiting feature and class relationships in video categorization with regularized deep neural networks. IEEE Trans. Pattern Anal. Mach. Intell. 40(2), 352\u2013364 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"33_CR18","unstructured":"Kim, B., Wattenberg, M., Gilmer, J., Cai, C., Wexler, J., Viegas, F., et al.: Interpretability beyond feature attribution: quantitative testing with concept activation vectors (TCAV). In: International Conference on Machine Learning, pp. 2668\u20132677. PMLR (2018)"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Lee, P., Wang, J., Lu, Y., Byun, H.: Weakly-supervised temporal action localization by uncertainty modeling. In: AAAI Conference on Artificial Intelligence, vol. 2 (2021)","DOI":"10.1609\/aaai.v35i3.16280"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Lillo, I., Soto, A., Carlos Niebles, J.: Discriminative hierarchical modeling of spatio-temporally composable human activities. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 812\u2013819 (2014)","DOI":"10.1109\/CVPR.2014.109"},{"key":"33_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T., Liu, X., Li, X., Ding, E., Wen, S.: BMN: boundary-matching network for temporal action proposal generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3889\u20133898 (2019)","DOI":"10.1109\/ICCV.2019.00399"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Liu, D., Jiang, T., Wang, Y.: Completeness modeling and context separation for weakly supervised temporal action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1298\u20131307 (2019)","DOI":"10.1109\/CVPR.2019.00139"},{"key":"33_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, L., Ma, X., Wang, Y., Qiao, Y.: Fineaction: a fine-grained video dataset for temporal action localization. arXiv preprint arXiv:2105.11107 (2021)","DOI":"10.1109\/TIP.2022.3217368"},{"key":"33_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"729","DOI":"10.1007\/978-3-030-58526-6_43","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Luo","year":"2020","unstructured":"Luo, Z., et al.: Weakly-supervised action localization with expectation-maximization multi-instance learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12374, pp. 729\u2013745. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58526-6_43"},{"key":"33_CR25","doi-asserted-by":"crossref","unstructured":"Ma, J., Gorti, S.K., Volkovs, M., Yu, G.: Weakly supervised action selection learning in video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7587\u20137596 (2021)","DOI":"10.1109\/CVPR46437.2021.00750"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Mac, K.N.C., Joshi, D., Yeh, R.A., Xiong, J., Feris, R.S., Do, M.N.: Learning motion in feature space: locally-consistent deformable convolution networks for fine-grained action detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6282\u20136291 (2019)","DOI":"10.1109\/ICCV.2019.00638"},{"key":"33_CR27","unstructured":"MacQueen, J.: Classification and analysis of multivariate observations. In: 5th Berkeley Symposium on Mathematical Statistics and Probability, pp. 281\u2013297 (1967)"},{"key":"33_CR28","doi-asserted-by":"crossref","unstructured":"Mavroudi, E., Bhaskara, D., Sefati, S., Ali, H., Vidal, R.: End-to-end fine-grained action segmentation and recognition using conditional random field models and discriminative sparse coding. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1558\u20131567. IEEE (2018)","DOI":"10.1109\/WACV.2018.00174"},{"key":"33_CR29","doi-asserted-by":"crossref","unstructured":"Narayan, S., Cholakkal, H., Hayat, M., Khan, F.S., Yang, M.H., Shao, L.: D2-Net: weakly-supervised action localization via discriminative embeddings and denoised activations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13608\u201313617 (2021)","DOI":"10.1109\/ICCV48922.2021.01335"},{"key":"33_CR30","doi-asserted-by":"crossref","unstructured":"Narayan, S., Cholakkal, H., Khan, F.S., Shao, L.: 3C-Net: category count and center loss for weakly-supervised action localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8679\u20138687 (2019)","DOI":"10.1109\/ICCV.2019.00877"},{"key":"33_CR31","doi-asserted-by":"crossref","unstructured":"Nguyen, P., Liu, T., Prasad, G., Han, B.: Weakly supervised action localization by sparse temporal pooling network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6752\u20136761 (2018)","DOI":"10.1109\/CVPR.2018.00706"},{"key":"33_CR32","doi-asserted-by":"crossref","unstructured":"Ni, B., Paramathayalan, V.R., Moulin, P.: Multiple granularity analysis for fine-grained action detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 756\u2013763 (2014)","DOI":"10.1109\/CVPR.2014.102"},{"key":"33_CR33","doi-asserted-by":"crossref","unstructured":"Pardo, A., Alwassel, H., Caba, F., Thabet, A., Ghanem, B.: Refineloc: iterative refinement for weakly-supervised action localization. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3319\u20133328 (2021)","DOI":"10.1109\/WACV48630.2021.00336"},{"key":"33_CR34","doi-asserted-by":"crossref","unstructured":"Paul, S., Roy, S., Roy-Chowdhury, A.K.: W-TALC: weakly-supervised temporal activity localization and classification. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 563\u2013579 (2018)","DOI":"10.1007\/978-3-030-01225-0_35"},{"key":"33_CR35","doi-asserted-by":"crossref","unstructured":"Piergiovanni, A.J., Ryoo, M.S.: Fine-grained activity recognition in baseball videos. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1821\u201318218 (2018)","DOI":"10.1109\/CVPRW.2018.00226"},{"key":"33_CR36","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1007\/978-0-387-73003-5_196","volume":"741","author":"DA Reynolds","year":"2009","unstructured":"Reynolds, D.A.: Gaussian mixture models. Encyclopedia Biometrics 741, 659\u2013663 (2009)","journal-title":"Encyclopedia Biometrics"},{"key":"33_CR37","doi-asserted-by":"crossref","unstructured":"Richard, A., Kuehne, H., Gall, J.: Weakly supervised action learning with RNN based fine-to-coarse modeling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 754\u2013763 (2017)","DOI":"10.1109\/CVPR.2017.140"},{"key":"33_CR38","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Amin, S., Andriluka, M., Schiele, B.: A database for fine grained activity detection of cooking activities. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1194\u20131201. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"33_CR39","doi-asserted-by":"crossref","unstructured":"Shao, D., Zhao, Y., Dai, B., Lin, D.: Finegym: a hierarchical video dataset for fine-grained action understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2616\u20132625 (2020)","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"33_CR40","doi-asserted-by":"crossref","unstructured":"Shou, Z., Gao, H., Zhang, L., Miyazawa, K., Chang, S.F.: Autoloc: weakly-supervised temporal action localization in untrimmed videos. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 154\u2013171 (2018)","DOI":"10.1007\/978-3-030-01270-0_10"},{"key":"33_CR41","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":"33_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":"33_CR43","doi-asserted-by":"crossref","unstructured":"Sun, C., Shetty, S., Sukthankar, R., Nevatia, R.: Temporal localization of fine-grained actions in videos by domain transfer from web images. In: Proceedings of the 23rd ACM International Conference on Multimedia, pp. 371\u2013380 (2015)","DOI":"10.1145\/2733373.2806226"},{"key":"33_CR44","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Lin, D., Van Gool, L.: Untrimmednets for weakly supervised action recognition and detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4325\u20134334 (2017)","DOI":"10.1109\/CVPR.2017.678"},{"key":"33_CR45","unstructured":"Whitney, W.F., Chang, M., Kulkarni, T., Tenenbaum, J.B.: Understanding visual concepts with continuation learning. arXiv preprint arXiv:1602.06822 (2016)"},{"key":"33_CR46","unstructured":"Yuan, Y., Lyu, Y., Shen, X., Tsang, I., Yeung, D.Y.: Marginalized average attentional network for weakly-supervised learning. In: ICLR 2019-Seventh International Conference on Learning Representations (2019)"},{"issue":"2","key":"33_CR47","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1145\/235968.233324","volume":"25","author":"T Zhang","year":"1996","unstructured":"Zhang, T., Ramakrishnan, R., Livny, M.: Birch: an efficient data clustering method for very large databases. ACM SIGMOD Rec. 25(2), 103\u2013114 (1996)","journal-title":"ACM SIGMOD Rec."},{"key":"33_CR48","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2914\u20132923 (2017)","DOI":"10.1109\/ICCV.2017.317"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20080-9_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,7]],"date-time":"2022-11-07T00:32:47Z","timestamp":1667781167000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20080-9_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200793","9783031200809"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20080-9_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"3 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","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":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}