{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:07:03Z","timestamp":1783530423549,"version":"3.55.0"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726606","type":"print"},{"value":"9783031726613","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"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\/978-3-031-72661-3_26","type":"book-chapter","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T07:47:40Z","timestamp":1732607260000},"page":"450-467","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Classification Matters: Improving Video Action Detection with\u00a0Class-Specific Attention"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0782-8651","authenticated-orcid":false,"given":"Jinsung","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7252-5525","authenticated-orcid":false,"given":"Taeoh","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4356-7616","authenticated-orcid":false,"given":"Inwoong","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9637-4909","authenticated-orcid":false,"given":"Minho","family":"Shim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0359-146X","authenticated-orcid":false,"given":"Dongyoon","family":"Wee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7030-1958","authenticated-orcid":false,"given":"Minsu","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4567-9091","authenticated-orcid":false,"given":"Suha","family":"Kwak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"26_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Chen, L., Tong, Z., Song, Y., Wu, G., Wang, L.: Efficient video action detection with token dropout and context refinement. arXiv preprint arXiv:2304.08451 (2023)","DOI":"10.1109\/ICCV51070.2023.00953"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: Watch only once: an end-to-end video action detection framework. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8178\u20138187 (2021)","DOI":"10.1109\/ICCV48922.2021.00807"},{"key":"26_CR4","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3d: expanding architectures for efficient video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 203\u2013213 (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"26_CR6","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":"26_CR7","doi-asserted-by":"crossref","unstructured":"Ghadiyaram, D., Tran, D., Mahajan, D.: Large-scale weakly-supervised pre-training for video action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12046\u201312055 (2019)","DOI":"10.1109\/CVPR.2019.01232"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Gu, C., et\u00a0al.: Ava: A video dataset of spatio-temporally localized atomic visual actions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6047\u20136056 (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Guo, C., Fan, B., Zhang, Q., Xiang, S., Pan, C.: AugFPN: improving multi-scale feature learning for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12595\u201312604 (2020)","DOI":"10.1109\/CVPR42600.2020.01261"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Herzig, R., et al.: Object-region video transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3148\u20133159 (2022)","DOI":"10.1109\/CVPR52688.2022.00315"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.J.: Towards understanding action recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3192\u20133199 (2013)","DOI":"10.1109\/ICCV.2013.396"},{"key":"26_CR12","unstructured":"Josmy\u00a0Faure, G., Chen, M.H., Lai, S.H.: Holistic interaction transformer network for action detection. arXiv e-prints pp. arXiv\u20132210 (2022)"},{"key":"26_CR13","unstructured":"Kay, W., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"26_CR14","unstructured":"K\u00f6p\u00fckl\u00fc, O., Wei, X., Rigoll, G.: You only watch once: a unified CNN architecture for real-time spatiotemporal action localization. arXiv preprint arXiv:1911.06644 (2019)"},{"issue":"1\u20132","key":"26_CR15","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logist. Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logist. Q."},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: DN-DETR: accelerate DETR training by introducing query denoising. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13619\u201313627 (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"26_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1007\/978-3-030-58517-4_5","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Li","year":"2020","unstructured":"Li, Y., Wang, Z., Wang, L., Wu, G.: Actions as moving points. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XVI. LNCS, vol. 12361, pp. 68\u201384. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_5"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"26_CR19","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":"26_CR20","unstructured":"Liu, S., et al.: Dab-DETR: Dynamic anchor boxes are better queries for DETR. In: ICLR (2022)"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Meng, D., et al.: Conditional DETR for fast training convergence. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3651\u20133660 (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Pan, J., Chen, S., Shou, M.Z., Liu, Y., Shao, J., Li, H.: Actor-context-actor relation network for spatio-temporal action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 464\u2013474 (2021)","DOI":"10.1109\/CVPR46437.2021.00053"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Pang, Y., Zhao, X., Zhang, L., Lu, H.: Multi-scale interactive network for salient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9413\u20139422 (2020)","DOI":"10.1109\/CVPR42600.2020.00943"},{"key":"26_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1007\/978-3-319-46493-0_45","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Peng","year":"2016","unstructured":"Peng, X., Schmid, C.: Multi-region two-stream R-CNN for action detection. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part IV. LNCS, vol. 9908, pp. 744\u2013759. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_45"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Saha, S., Singh, G., Sapienza, M., Torr, P.H., Cuzzolin, F.: Deep learning for detecting multiple space-time action tubes in videos. arXiv preprint arXiv:1608.01529 (2016)","DOI":"10.5244\/C.30.58"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Singh, G., Saha, S., Sapienza, M., Torr, P.H., Cuzzolin, F.: Online real-time multiple spatiotemporal action localisation and prediction. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3637\u20133646 (2017)","DOI":"10.1109\/ICCV.2017.393"},{"key":"26_CR28","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":"26_CR29","doi-asserted-by":"crossref","unstructured":"Sui, L., Zhang, C.L., Gu, L., Han, F.: A simple and efficient pipeline to build an end-to-end spatial-temporal action detector. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5999\u20136008 (2023)","DOI":"10.1109\/WACV56688.2023.00594"},{"key":"26_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/978-3-030-01252-6_20","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Sun","year":"2018","unstructured":"Sun, C., Shrivastava, A., Vondrick, C., Murphy, K., Sukthankar, R., Schmid, C.: Actor-centric relation network. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 335\u2013351. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_20"},{"key":"26_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/978-3-030-58555-6_5","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Tang","year":"2020","unstructured":"Tang, J., Xia, J., Mu, X., Pang, B., Lu, C.: Asynchronous interaction aggregation for action detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XV. LNCS, vol. 12360, pp. 71\u201387. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_5"},{"key":"26_CR32","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training. In: Advances in Neural Information Processing Systems, vol. 35, pp. 10078\u201310093 (2022)"},{"key":"26_CR33","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Feiszli, M.: Video classification with channel-separated convolutional networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5552\u20135561 (2019)","DOI":"10.1109\/ICCV.2019.00565"},{"key":"26_CR34","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"26_CR35","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Videomae v2: scaling video masked autoencoders with dual masking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14549\u201314560 (2023)","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Wang, T., Borji, A., Zhang, L., Zhang, P., Lu, H.: A stagewise refinement model for detecting salient objects in images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4019\u20134028 (2017)","DOI":"10.1109\/ICCV.2017.433"},{"key":"26_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, X., Yang, T., Sun, J.: Anchor DETR: query design for transformer-based detector. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 2567\u20132575 (2022)","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., Harchaoui, Z., Schmid, C.: Learning to track for spatio-temporal action localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3164\u20133172 (2015)","DOI":"10.1109\/ICCV.2015.362"},{"key":"26_CR39","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., Girshick, R.: Long-term feature banks for detailed video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 284\u2013293 (2019)","DOI":"10.1109\/CVPR.2019.00037"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., et al.: MemVIT: memory-augmented multiscale vision transformer for efficient long-term video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13587\u201313597 (2022)","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"26_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1007\/978-3-030-58595-2_27","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Wu","year":"2020","unstructured":"Wu, J., Kuang, Z., Wang, L., Zhang, W., Wu, G.: Context-aware RCNN: a baseline for action detection in videos. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XXV. LNCS, vol. 12370, pp. 440\u2013456. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_27"},{"key":"26_CR42","doi-asserted-by":"crossref","unstructured":"Wu, T., Cao, M., Gao, Z., Wu, G., Wang, L.: Stmixer: a one-stage sparse action detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14720\u201314729 (2023)","DOI":"10.1109\/CVPR52729.2023.01414"},{"key":"26_CR43","doi-asserted-by":"crossref","unstructured":"Zhao, J., et\u00a0al.: Tuber: tubelet transformer for video action detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13598\u201313607 (2022)","DOI":"10.1109\/CVPR52688.2022.01323"},{"key":"26_CR44","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: ICLR (2021)"}],"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\/978-3-031-72661-3_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T08:24:23Z","timestamp":1732609463000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72661-3_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"ISBN":["9783031726606","9783031726613"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72661-3_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,27]]},"assertion":[{"value":"27 November 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"}}]}}