{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:41:20Z","timestamp":1783183280560,"version":"3.54.6"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031441943","type":"print"},{"value":"9783031441950","type":"electronic"}],"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\/978-3-031-44195-0_36","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T12:04:08Z","timestamp":1695297848000},"page":"439-450","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Learning Video Localization on\u00a0Segment-Level Video Copy Detection with\u00a0Transformer"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8705-2814","authenticated-orcid":false,"given":"Chi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8204-424X","authenticated-orcid":false,"given":"Jie","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuwu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2150-2088","authenticated-orcid":false,"given":"Zhi","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"36_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"},{"issue":"3","key":"36_CR2","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1109\/TMM.2015.2391674","volume":"17","author":"CL Chou","year":"2015","unstructured":"Chou, C.L., Chen, H.T., Lee, S.Y.: Pattern-based near-duplicate video retrieval and localization on web-scale videos. IEEE Trans. Multimedia 17(3), 382\u2013395 (2015)","journal-title":"IEEE Trans. Multimedia"},{"key":"36_CR3","unstructured":"Code, P.W.: Object detection on coco test-dev (2018). https:\/\/paperswithcode.com\/sota\/object-detection-on-coco"},{"issue":"4","key":"36_CR4","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/TMM.2010.2046265","volume":"12","author":"M Douze","year":"2010","unstructured":"Douze, M., J\u00e9gou, H., Schmid, C.: An image-based approach to video copy detection with spatio-temporal post-filtering. IEEE Trans. Multimedia 12(4), 257\u2013266 (2010)","journal-title":"IEEE Trans. Multimedia"},{"key":"36_CR5","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"36_CR6","doi-asserted-by":"crossref","unstructured":"Han, Z., He, X., Tang, M., Lv, Y.: Video similarity and alignment learning on partial video copy detection. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 4165\u20134173 (2021)","DOI":"10.1145\/3474085.3475549"},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"36_CR8","unstructured":"He, S., et al.: TransVCL: attention-enhanced video copy localization network with flexible supervision. arXiv preprint arXiv:2211.13090 (2022)"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"He, S., et al.: A large-scale comprehensive dataset and copy-overlap aware evaluation protocol for segment-level video copy detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21086\u201321095 (2022)","DOI":"10.1109\/CVPR52688.2022.02041"},{"key":"36_CR10","doi-asserted-by":"crossref","unstructured":"Hu, Y., Mu, Z., Ai, X.: STRNN: end-to-end deep learning framework for video partial copy detection. In: Journal of Physics: Conference Series, vol. 1237, p. 022112. IOP Publishing (2019)","DOI":"10.1088\/1742-6596\/1237\/2\/022112"},{"key":"36_CR11","doi-asserted-by":"crossref","unstructured":"Jiang, C., et al.: Learning segment similarity and alignment in large-scale content based video retrieval. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1618\u20131626 (2021)","DOI":"10.1145\/3474085.3475301"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Jiang, Q.Y., He, Y., Li, G., Lin, J., Li, L., Li, W.J.: SVD: a large-scale short video dataset for near-duplicate video retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5281\u20135289 (2019)","DOI":"10.1109\/ICCV.2019.00538"},{"key":"36_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1007\/978-3-319-10593-2_24","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Y-G Jiang","year":"2014","unstructured":"Jiang, Y.-G., Jiang, Y., Wang, J.: VCDB: a large-scale database for partial copy detection in videos. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 357\u2013371. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10593-2_24"},{"issue":"10","key":"36_CR14","doi-asserted-by":"publisher","first-page":"2638","DOI":"10.1109\/TMM.2019.2905741","volume":"21","author":"G Kordopatis-Zilos","year":"2019","unstructured":"Kordopatis-Zilos, G., Papadopoulos, S., Patras, I., Kompatsiaris, I.: FIVR: fine-grained incident video retrieval. IEEE Trans. Multimedia 21(10), 2638\u20132652 (2019)","journal-title":"IEEE Trans. Multimedia"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Mao, H., Girshick, R., He, K.: Exploring plain vision transformer backbones for object detection. arXiv preprint arXiv:2203.16527 (2022)","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"36_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"36_CR17","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"36_CR18","doi-asserted-by":"crossref","unstructured":"Tan, H.K., Ngo, C.W., Hong, R., Chua, T.S.: Scalable detection of partial near-duplicate videos by visual-temporal consistency. In: Proceedings of the 17th ACM International Conference on Multimedia, pp. 145\u2013154 (2009)","DOI":"10.1145\/1631272.1631295"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Tan, W., Guo, H., Liu, R.: A fast partial video copy detection using KNN and global feature database. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2191\u20132199 (2022)","DOI":"10.1109\/WACV51458.2022.00053"},{"key":"36_CR20","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"36_CR21","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. 36, pp. 2567\u20132575 (2022)","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"36_CR22","unstructured":"Zhang, H., et al.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)"},{"key":"36_CR23","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"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\/978-3-031-44195-0_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T12:09:25Z","timestamp":1695298165000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44195-0_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031441943","9783031441950"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44195-0_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"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)"}}]}}