{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T05:47:49Z","timestamp":1761198469029,"version":"3.44.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031915802"},{"type":"electronic","value":"9783031915819"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-91581-9_23","type":"book-chapter","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T11:22:10Z","timestamp":1748344930000},"page":"322-334","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Introducing Gating and Context Into Temporal Action Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6841-2984","authenticated-orcid":false,"given":"Aglind","family":"Reka","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0276-7243","authenticated-orcid":false,"given":"Diana Laura","family":"Borza","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3959-8032","authenticated-orcid":false,"given":"Dominick","family":"Reilly","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7153-9984","authenticated-orcid":false,"given":"Michal","family":"Balazia","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2988-2142","authenticated-orcid":false,"given":"Francois","family":"Bremond","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Alwassel, H., Giancola, S., Ghanem, B.: Tsp: temporally-sensitive pretraining of video encoders for localization tasks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3173\u20133183 (2021)","key":"23_CR1","DOI":"10.1109\/ICCVW54120.2021.00356"},{"key":"23_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-030-58604-1_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Bai","year":"2020","unstructured":"Bai, Y., Wang, Y., Tong, Y., Yang, Y., Liu, Q., Liu, J.: Boundary content graph neural network for temporal action proposal generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 121\u2013137. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58604-1_8"},{"doi-asserted-by":"crossref","unstructured":"Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-nms\u2013improving object detection with one line of code. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5561\u20135569 (2017)","key":"23_CR3","DOI":"10.1109\/ICCV.2017.593"},{"doi-asserted-by":"crossref","unstructured":"Buch, S., Escorcia, V., Shen, C., Ghanem, B., Carlos\u00a0Niebles, J.: SST: single-stream temporal action proposals. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2911\u20132920 (2017)","key":"23_CR4","DOI":"10.1109\/CVPR.2017.675"},{"doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","key":"23_CR5","DOI":"10.1007\/978-3-030-58452-8_13"},{"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)","key":"23_CR6","DOI":"10.1109\/CVPR.2017.502"},{"doi-asserted-by":"crossref","unstructured":"Cheng, F., Bertasius, G.: Tallformer: Temporal action localization with a long-memory transformer. In: European Conference on Computer Vision. pp. 503\u2013521. Springer (2022)","key":"23_CR7","DOI":"10.1007\/978-3-031-19830-4_29"},{"doi-asserted-by":"crossref","unstructured":"Dai, R., Das, S., Minciullo, L., Garattoni, L., Francesca, G., Bremond, F.: PDAN: pyramid dilated attention network for action detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2970\u20132979 (2021)","key":"23_CR8","DOI":"10.1109\/WACV48630.2021.00301"},{"doi-asserted-by":"crossref","unstructured":"Damen, D., et\u00a0al.: Rescaling egocentric vision: collection, pipeline and challenges for epic-kitchens-100. Int. J. Comput. Vis. 1\u201323 (2022)","key":"23_CR9","DOI":"10.1007\/s11263-021-01531-2"},{"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)","key":"23_CR10","DOI":"10.1109\/ICCV.2019.00630"},{"doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","key":"23_CR11","DOI":"10.1109\/CVPR.2018.00745"},{"doi-asserted-by":"crossref","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)","key":"23_CR12","DOI":"10.1016\/j.cviu.2016.10.018"},{"doi-asserted-by":"crossref","unstructured":"Lin, C., et al.: Fast learning of temporal action proposal via dense boundary generator. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 11499\u201311506 (2020)","key":"23_CR13","DOI":"10.1609\/aaai.v34i07.6815"},{"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)","key":"23_CR14","DOI":"10.1109\/ICCV.2019.00399"},{"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)","key":"23_CR15","DOI":"10.1109\/ICCV.2017.324"},{"key":"23_CR16","doi-asserted-by":"publisher","first-page":"5427","DOI":"10.1109\/TIP.2022.3195321","volume":"31","author":"X Liu","year":"2022","unstructured":"Liu, X., et al.: End-to-end temporal action detection with transformer. IEEE Trans. Image Process. 31, 5427\u20135441 (2022)","journal-title":"IEEE Trans. Image Process."},{"unstructured":"Loshchilov, I., Hutter, F.: Sgdr: stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)","key":"23_CR17"},{"doi-asserted-by":"crossref","unstructured":"Qing, Z., et al.: Temporal context aggregation network for temporal action proposal refinement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 485\u2013494 (2021)","key":"23_CR18","DOI":"10.1109\/CVPR46437.2021.00055"},{"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)","key":"23_CR19","DOI":"10.1109\/CVPR.2019.00075"},{"unstructured":"Shi, D., et al.: Temporal action localization with enhanced instant discriminability. arXiv preprint arXiv:2309.05590 (2023)","key":"23_CR20"},{"doi-asserted-by":"crossref","unstructured":"Shi, D., Zhong, Y., Cao, Q., Ma, L., Li, J., Tao, D.: Tridet: temporal action detection with relative boundary modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18857\u201318866 (2023)","key":"23_CR21","DOI":"10.1109\/CVPR52729.2023.01808"},{"doi-asserted-by":"crossref","unstructured":"Shi, D., et al.: React: temporal action detection with relational queries. In: European Conference on Computer Vision, pp. 105\u2013121. Springer (2022)","key":"23_CR22","DOI":"10.1007\/978-3-031-20080-9_7"},{"key":"23_CR23","first-page":"34899","volume":"35","author":"Z Tian","year":"2022","unstructured":"Tian, Z., Chu, X., Wang, X., Wei, X., Shen, C.: Fully convolutional one-stage 3d object detection on lidar range images. Adv. Neural Inf. Process. Syst. 35, 34899\u201334911 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: Cbam: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","key":"23_CR24","DOI":"10.1007\/978-3-030-01234-2_1"},{"unstructured":"Wu, Y., Rabe, M.N., Hutchins, D., Szegedy, C.: Memorizing transformers. arXiv preprint arXiv:2203.08913 (2022)","key":"23_CR25"},{"doi-asserted-by":"crossref","unstructured":"Xu, M., Zhao, C., Rojas, D.S., Thabet, A., Ghanem, B.: G-tad: sub-graph localization for temporal action detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10156\u201310165 (2020)","key":"23_CR26","DOI":"10.1109\/CVPR42600.2020.01017"},{"doi-asserted-by":"crossref","unstructured":"Zeng, R., et al.: Graph convolutional networks for temporal action localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7094\u20137103 (2019)","key":"23_CR27","DOI":"10.1109\/ICCV.2019.00719"},{"doi-asserted-by":"crossref","unstructured":"Zhang, C.L., Wu, J., Li, Y.: Actionformer: localizing moments of actions with transformers. In: European Conference on Computer Vision, pp. 492\u2013510. Springer (2022)","key":"23_CR28","DOI":"10.1007\/978-3-031-19772-7_29"},{"issue":"2","key":"23_CR29","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/s11063-024-11547-7","volume":"56","author":"L Zhou","year":"2024","unstructured":"Zhou, L., Lu, Y., Jiang, H.: FEASE: feature selection and enhancement networks for action recognition. Neural Process. Lett. 56(2), 87 (2024)","journal-title":"Neural Process. Lett."},{"doi-asserted-by":"crossref","unstructured":"Zhu, Z., Tang, W., Wang, L., Zheng, N., Hua, G.: Enriching local and global contexts for temporal action localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13516\u201313525 (2021)","key":"23_CR30","DOI":"10.1109\/ICCV48922.2021.01326"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91581-9_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T15:51:18Z","timestamp":1757173878000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91581-9_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031915802","9783031915819"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91581-9_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}