{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T09:19:06Z","timestamp":1754558346768,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031442223"},{"type":"electronic","value":"9783031442230"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-44223-0_45","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T05:01:41Z","timestamp":1695272501000},"page":"563-575","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Temporal Deformable Transformer for\u00a0Action Localization"],"prefix":"10.1007","author":[{"given":"Haoying","family":"Wang","sequence":"first","affiliation":[]},{"given":"Ping","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Meiqin","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Nanning","family":"Zheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Alwassel, H., Giancola, S., Ghanem, B.: TSP: temporally-sensitive pretraining of video encoders for localization tasks. In: International Conference on Computer Vision, pp. 3173\u20133183 (2021)","key":"45_CR1","DOI":"10.1109\/ICCVW54120.2021.00356"},{"key":"45_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-improving object detection with one line of code. In: International Conference on Computer Vision, pp. 5561\u20135569 (2017)","key":"45_CR3","DOI":"10.1109\/ICCV.2017.593"},{"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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","key":"45_CR4","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"45_CR5","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"},{"doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","key":"45_CR6","DOI":"10.1109\/CVPR.2017.502"},{"doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Vijayanarasimhan, S., Seybold, B., Ross, D.A., Deng, J., Sukthankar, R.: Rethinking the faster R-CNN architecture for temporal action localization. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)","key":"45_CR7","DOI":"10.1109\/CVPR.2018.00124"},{"doi-asserted-by":"crossref","unstructured":"Chen, G., Zheng, Y.D., Wang, L., Lu, T.: DCAN: improving temporal action detection via dual context aggregation. In: AAAI Conference on Artificial Intelligence, vol. 36, pp. 248\u2013257 (2022)","key":"45_CR8","DOI":"10.1609\/aaai.v36i1.19900"},{"unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint: arXiv:2010.11929 (2020)","key":"45_CR9"},{"doi-asserted-by":"crossref","unstructured":"Gao, J., et al.: Accurate temporal action proposal generation with relation-aware pyramid network. In: AAAI Conference on Artificial Intelligence, vol. 34, pp. 10810\u201310817 (2020)","key":"45_CR10","DOI":"10.1609\/aaai.v34i07.6711"},{"key":"45_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cviu.2016.10.018","volume":"155","author":"H Idrees","year":"2017","unstructured":"Idrees, H., et al.: The Thumos challenge on action recognition for videos \u201cin the wild\u2019\u2019. Comput. Vis. Image Underst. 155, 1\u201323 (2017)","journal-title":"Comput. Vis. Image Underst."},{"unstructured":"Kinga, D., et al.: A method for stochastic optimization. In: International Conference on Learning Representations, vol. 5, p. 6 (2015)","key":"45_CR12"},{"key":"45_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/978-3-031-19833-5_8","volume-title":"Computer Vision \u2013 ECCV 2022","author":"H Li","year":"2022","unstructured":"Li, H., Wei, P., Li, J., Ma, Z., Shang, J., Zheng, N.: Asymmetric relation consistency reasoning for video relation grounding. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. Lecture Notes in Computer Science, vol. 13695, pp. 125\u2013141. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_8"},{"doi-asserted-by":"crossref","unstructured":"Lin, C., et al.: Learning salient boundary feature for anchor-free temporal action localization. In: IEEE Conference on Computer Vision and Pattern Recognition (2021)","key":"45_CR14","DOI":"10.1109\/CVPR46437.2021.00333"},{"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: International Conference on Computer Vision, pp. 3889\u20133898 (2019)","key":"45_CR15","DOI":"10.1109\/ICCV.2019.00399"},{"key":"45_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01225-0_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Lin","year":"2018","unstructured":"Lin, T., Zhao, X., Su, H., Wang, C., Yang, M.: BSN: boundary sensitive network for temporal action proposal generation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 3\u201321. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_1"},{"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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","key":"45_CR17","DOI":"10.1109\/CVPR.2017.106"},{"doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: International Conference on Computer Vision, pp. 2980\u20132988 (2017)","key":"45_CR18","DOI":"10.1109\/ICCV.2017.324"},{"key":"45_CR19","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."},{"doi-asserted-by":"crossref","unstructured":"Ma, Z., Wei, P., Li, H., Zheng, N.: HOIG: end-to-end human-object interactions grounding with transformers. In: IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136 (2022)","key":"45_CR20","DOI":"10.1109\/ICME52920.2022.9859803"},{"doi-asserted-by":"crossref","unstructured":"Qing, Z., et al.: Temporal context aggregation network for temporal action proposal refinement. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 485\u2013494 (2021)","key":"45_CR21","DOI":"10.1109\/CVPR46437.2021.00055"},{"unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)","key":"45_CR22"},{"key":"45_CR23","doi-asserted-by":"publisher","first-page":"104589","DOI":"10.1016\/j.imavis.2022.104589","volume":"129","author":"J Shang","year":"2023","unstructured":"Shang, J., Wei, P., Li, H., Zheng, N.: Multi-scale interaction transformer for temporal action proposal generation. Image Vis. Comput. 129, 104589 (2023)","journal-title":"Image Vis. Comput."},{"doi-asserted-by":"crossref","unstructured":"Tran, D., et al.: A closer look at spatiotemporal convolutions for action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","key":"45_CR24","DOI":"10.1109\/CVPR.2018.00675"},{"unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)","key":"45_CR25"},{"key":"45_CR26","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"},{"doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, Y., Zheng, Y., Pan, P.: RCL: recurrent continuous localization for temporal action detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 13566\u201313575 (2022)","key":"45_CR27","DOI":"10.1109\/CVPR52688.2022.01320"},{"unstructured":"Xiong, Y., et al.: Cuhk & ethz & siat submission to activitynet challenge 2016. arXiv preprint: arXiv:1608.00797 (2016)","key":"45_CR28"},{"doi-asserted-by":"crossref","unstructured":"Xu, H., Das, A., Saenko, K.: R-c3d: region convolutional 3d network for temporal activity detection. In: International Conference on Computer Vision, pp. 5783\u20135792 (2017)","key":"45_CR29","DOI":"10.1109\/ICCV.2017.617"},{"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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 10156\u201310165 (2020)","key":"45_CR30","DOI":"10.1109\/CVPR42600.2020.01017"},{"doi-asserted-by":"crossref","unstructured":"Yang, H., et al.: Temporal action proposal generation with background constraint. In: AAAI Conference on Artificial Intelligence, vol. 36, pp. 3054\u20133062 (2022)","key":"45_CR31","DOI":"10.1609\/aaai.v36i3.20212"},{"key":"45_CR32","doi-asserted-by":"publisher","first-page":"8535","DOI":"10.1109\/TIP.2020.3016486","volume":"29","author":"L Yang","year":"2020","unstructured":"Yang, L., Peng, H., Zhang, D., Fu, J., Han, J.: Revisiting anchor mechanisms for temporal action localization. IEEE Trans. Image Process. 29, 8535\u20138548 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"45_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1007\/978-3-031-19772-7_29","volume-title":"Computer Vision \u2013 ECCV 2022","author":"CL Zhang","year":"2022","unstructured":"Zhang, C.L., Wu, J., Li, Y.: ActionFormer: localizing moments of actions with transformers. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) 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-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-IoU loss: faster and better learning for bounding box regression. In: AAAI Conference on Artificial Intelligence, vol. 34, pp. 12993\u201313000 (2020)","key":"45_CR34","DOI":"10.1609\/aaai.v34i07.6999"},{"unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv:2010.04159 (2020)","key":"45_CR35"},{"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: International Conference on Computer Vision, pp. 13516\u201313525 (2021)","key":"45_CR36","DOI":"10.1109\/ICCV48922.2021.01326"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44223-0_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T06:17:17Z","timestamp":1695277037000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44223-0_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031442223","9783031442230"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44223-0_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","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":"426","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":"22","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":"45% - 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":"2.4","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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"type of other papers accepted  : 9 Abstract","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}