{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T23:09:34Z","timestamp":1788995374431,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375766","type":"print"},{"value":"9783032375773","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37577-3_30","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T23:03:15Z","timestamp":1788994995000},"page":"549-566","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SV-TAD: Native Sparse Convs for\u00a0Efficient Temporal Action Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7894-0236","authenticated-orcid":false,"given":"Ricardo","family":"Pizarro","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1423-1478","authenticated-orcid":false,"given":"Roberto","family":"Valle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4308-9653","authenticated-orcid":false,"given":"Jos\u00e9 M.","family":"Buenaposada","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0087-3077","authenticated-orcid":false,"given":"Luis M.","family":"Bergasa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6910-4359","authenticated-orcid":false,"given":"Luis","family":"Baumela","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"30_CR1","doi-asserted-by":"publisher","unstructured":"Aganian, D., Stephan, B., Eisenbach, M., Stretz, C., Gross, H.M.: Attach dataset: annotated two-handed assembly actions for human action understanding. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 11367\u201311373 (2023). https:\/\/doi.org\/10.1109\/ICRA48891.2023.10160633","DOI":"10.1109\/ICRA48891.2023.10160633"},{"key":"30_CR2","doi-asserted-by":"publisher","unstructured":"Beyer, L., Zhai, X., Royer, A., Markeeva, L., Anil, R., Kolesnikov, A.: Knowledge distillation: a good teacher is patient and consistent. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, 18\u201324 June 2022, pp. 10915\u201310924. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01065","DOI":"10.1109\/CVPR52688.2022.01065"},{"key":"30_CR3","unstructured":"Bolya, D., Fu, C., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your vit but faster. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, 1\u20135 May 2023. OpenReview.net (2023). https:\/\/openreview.net\/forum?id=JroZRaRw7Eu"},{"key":"30_CR4","doi-asserted-by":"publisher","unstructured":"Cheng, F., Bertasius, G.: Tallformer: temporal action localization with a long-memory transformer. In: Avidan, S., Brostow, G.J., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, 23\u201327 October 2022, Proceedings, Part XXXIV. LNCS, vol. 13694, pp. 503\u2013521. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19830-4_29","DOI":"10.1007\/978-3-031-19830-4_29"},{"key":"30_CR5","unstructured":"Child, R., Gray, S., Radford, A., Sutskever, I.: Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509 (2019)"},{"key":"30_CR6","doi-asserted-by":"publisher","unstructured":"Choy, C.B., Gwak, J., Savarese, S.: 4d spatio-temporal convnets: Minkowski convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, 16\u201320 June 2019, pp. 3075\u20133084. Computer Vision Foundation\/IEEE (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00319, http:\/\/openaccess.thecvf.com\/content_CVPR_2019\/html\/Choy_4D_Spatio-Temporal_ConvNets_Minkowski_Convolutional_Neural_Networks_CVPR_2019_paper.html","DOI":"10.1109\/CVPR.2019.00319"},{"key":"30_CR7","doi-asserted-by":"publisher","first-page":"16344","DOI":"10.52202\/068431-1189","volume":"35","author":"T Dao","year":"2022","unstructured":"Dao, T., Fu, D., Ermon, S., Rudra, A., R\u00e9, C.: Flashattention: fast and memory-efficient exact attention with io-awareness. Adv. Neural. Inf. Process. Syst. 35, 16344\u201316359 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"30_CR8","unstructured":"Graham, B., Van\u00a0der Maaten, L.: Submanifold sparse convolutional networks. arXiv preprint arXiv:1706.01307 (2017)"},{"key":"30_CR9","doi-asserted-by":"publisher","unstructured":"Gupta, A., Mittal, G., Magooda, A., Yu, Y., Taylor, G.W., Chen, M.: Losa: long-short-range adapter for scaling end-to-end temporal action localization. In: IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV 2025, Tucson, AZ, USA, February 26 - March 6, 2025, pp. 2092\u20132102. IEEE (2025). https:\/\/doi.org\/10.1109\/WACV61041.2025.00210","DOI":"10.1109\/WACV61041.2025.00210"},{"key":"30_CR10","doi-asserted-by":"publisher","unstructured":"Heilbron, F.C., Escorcia, V., Ghanem, B., Niebles, J.C.: Activitynet: a large-scale video benchmark for human activity understanding. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, 7\u201312 June 2015, pp. 961\u2013970. IEEE Computer Society (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298698","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"30_CR11","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA. Proceedings of Machine Learning Research, vol.\u00a097, pp. 2790\u20132799. PMLR (2019). http:\/\/proceedings.mlr.press\/v97\/houlsby19a.html"},{"key":"30_CR12","doi-asserted-by":"publisher","unstructured":"Idrees, H., et al.: The THUMOS challenge on action recognition for videos \u201cin the wild\u201d. Comput. Vis. Image Underst. 155, 1\u201323 (2017). https:\/\/doi.org\/10.1016\/J.CVIU.2016.10.018","DOI":"10.1016\/J.CVIU.2016.10.018"},{"key":"30_CR13","doi-asserted-by":"publisher","unstructured":"Kim, K., Park, J., Kim, J., Kwon, H., Sohn, K.: Faster parameter-efficient tuning with token redundancy reduction. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025, Nashville, TN, USA, 11\u201315 June 2025, pp. 30189\u201330198. Computer Vision Foundation\/IEEE (2025). https:\/\/doi.org\/10.1109\/CVPR52734.2025.02810, https:\/\/openaccess.thecvf.com\/content\/CVPR2025\/html\/Kim_Faster_Parameter-Efficient_Tuning_with_Token_Redundancy_Reduction_CVPR_2025_paper.html","DOI":"10.1109\/CVPR52734.2025.02810"},{"key":"30_CR14","unstructured":"Liang, Y., Ge, C., Tong, Z., Song, Y., Wang, J., Xie, P.: Evit: expediting vision transformers via token reorganizations. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, 25\u201329 April 2022. OpenReview.net (2022). https:\/\/openreview.net\/forum?id=BjyvwnXXVn_"},{"key":"30_CR15","doi-asserted-by":"publisher","unstructured":"Lin, C., et al.: Learning salient boundary feature for anchor-free temporal action localization. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, 19\u201325 June 2021, pp. 3320\u20133329. Computer Vision Foundation\/IEEE (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00333","DOI":"10.1109\/CVPR46437.2021.00333"},{"key":"30_CR16","doi-asserted-by":"publisher","unstructured":"Liu, S., Zhang, C., Zhao, C., Ghanem, B.: End-to-end temporal action detection with 1b parameters across 1000 frames. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, 16\u201322 June 2024, pp. 18591\u201318601. IEEE (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.01759","DOI":"10.1109\/CVPR52733.2024.01759"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Opentad: a unified framework and comprehensive study of temporal action detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2025, Nashville, TN, USA, 11\u201315 June 2025, pp. 2625\u20132635. Computer Vision Foundation\/IEEE (2025). https:\/\/openaccess.thecvf.com\/content\/CVPR2025W\/PVUW\/html\/Liu_OpenTAD_A_Unified_Framework_and_Comprehensive_Study_of_Temporal_Action_CVPRW_2025_paper.html","DOI":"10.1109\/CVPRW67362.2025.00247"},{"key":"30_CR18","doi-asserted-by":"publisher","unstructured":"Liu, X., Bai, S., Bai, X.: An empirical study of end-to-end temporal action detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, 18\u201324 June 2022, pp. 19978\u201319987. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01938","DOI":"10.1109\/CVPR52688.2022.01938"},{"key":"30_CR19","unstructured":"Pan, J., Lin, Z., Zhu, X., Shao, J., Li, H.: St-adapter: parameter-efficient image-to-video transfer learning. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28\u2013December 9, 2022 (2022). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/a92e9165b22d4456fc6d87236e04c266-Abstract-Conference.html"},{"key":"30_CR20","doi-asserted-by":"publisher","unstructured":"Pizarro, R., Valle, R., Buenaposada, J.M., Bergasa, L.M., Baumela, L.: Pose-guided token selection for the recognition of activities of daily living. Image Vis. Comput. 162, 105686 (2025). https:\/\/doi.org\/10.1016\/j.imavis.2025.105686, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0262885625002744","DOI":"10.1016\/j.imavis.2025.105686"},{"key":"30_CR21","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.: Dynamicvit: efficient vision transformers with dynamic token sparsification. In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, 6\u201314 December 2021, virtual, pp. 13937\u201313949 (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/747d3443e319a22747fbb873e8b2f9f2-Abstract.html"},{"key":"30_CR22","unstructured":"Ryoo, M.S., Piergiovanni, A.J., Arnab, A., Dehghani, M., Angelova, A.: Tokenlearner: adaptive space-time tokenization for videos. In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, 6\u201314 December 2021, virtual, pp. 12786\u201312797 (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/6a30e32e56fce5cf381895dfe6ca7b6f-Abstract.html"},{"key":"30_CR23","doi-asserted-by":"publisher","unstructured":"Tay, Y., Dehghani, M., Bahri, D., Metzler, D.: Efficient transformers: a survey. ACM Comput. Surv. 55(6), 109:1\u2013109:28 (2023). https:\/\/doi.org\/10.1145\/3530811","DOI":"10.1145\/3530811"},{"key":"30_CR24","unstructured":"Wang, C., et al.: Internvideo-next: towards general video foundation models without video-text supervision. arXiv preprint arXiv:2512.01342 (2025)"},{"key":"30_CR25","doi-asserted-by":"publisher","unstructured":"Wang, J., Yang, X., Li, H., Liu, L., Wu, Z., Jiang, Y.: Efficient video transformers with spatial-temporal token selection. In: Avidan, S., Brostow, G.J., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, 23\u201327 October 2022, Proceedings, Part XXXV. LNCS, vol. 13695, pp. 69\u201386. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_5","DOI":"10.1007\/978-3-031-19833-5_5"},{"key":"30_CR26","doi-asserted-by":"publisher","unstructured":"Wang, L., et al.: Videomae V2: scaling video masked autoencoders with dual masking. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, 17\u201324 June 2023, pp. 14549\u201314560. IEEE (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01398","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"30_CR27","doi-asserted-by":"publisher","unstructured":"Yan, Y., Mao, Y., Li, B.: SECOND: sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018). https:\/\/doi.org\/10.3390\/S18103337","DOI":"10.3390\/S18103337"},{"key":"30_CR28","doi-asserted-by":"publisher","unstructured":"Yang, M., Chen, G., Zheng, Y., Lu, T., Wang, L.: Basictad: an astounding rgb-only baseline for temporal action detection. Comput. Vis. Image Underst. 232, 103692 (2023). https:\/\/doi.org\/10.1016\/J.CVIU.2023.103692","DOI":"10.1016\/J.CVIU.2023.103692"},{"key":"30_CR29","doi-asserted-by":"publisher","unstructured":"Yang, M., Gao, H., Guo, P., Wang, L.: Adapting short-term transformers for action detection in untrimmed videos. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, 16\u201322 June 2024. pp. 18570\u201318579. IEEE (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.01757","DOI":"10.1109\/CVPR52733.2024.01757"},{"key":"30_CR30","unstructured":"Yang, T., Zhu, Y., Xie, Y., Zhang, A., Chen, C., Li, M.: AIM: adapting image models for efficient video action recognition. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, 1\u20135 May 2023. OpenReview.net (2023). https:\/\/openreview.net\/forum?id=CIoSZ_HKHS7"},{"key":"30_CR31","doi-asserted-by":"publisher","unstructured":"Yuan, X., Fei, H., Baek, J.: Efficient transformer adaptation with soft token merging. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024 - Workshops, Seattle, WA, USA, 17\u201318 June 2024, pp. 3658\u20133668. IEEE (2024). https:\/\/doi.org\/10.1109\/CVPRW63382.2024.00369","DOI":"10.1109\/CVPRW63382.2024.00369"},{"key":"30_CR32","doi-asserted-by":"publisher","unstructured":"Zhang, C., Wu, J., Li, Y.: Actionformer: localizing moments of actions with transformers. In: Avidan, S., Brostow, G.J., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, 23\u201327 October 2022, Proceedings, Part IV. LNCS, vol. 13664, pp. 492\u2013510. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19772-7_29","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"30_CR33","doi-asserted-by":"publisher","unstructured":"Zhao, C., Liu, S., Mangalam, K., Ghanem, B.: Re$$ ^{\\text{2}}$$tal: rewiring pretrained video backbones for reversible temporal action localization. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, 17\u201324 June 2023, pp. 10637\u201310647. IEEE (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01025","DOI":"10.1109\/CVPR52729.2023.01025"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37577-3_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T23:03:19Z","timestamp":1788994999000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37577-3_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375766","9783032375773"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37577-3_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","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":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}