{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:27:17Z","timestamp":1770917237753,"version":"3.50.1"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198328","type":"print"},{"value":"9783031198335","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19833-5_41","type":"book-chapter","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T00:40:30Z","timestamp":1667522430000},"page":"709-725","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["GEB+: A Benchmark for\u00a0Generic Event Boundary Captioning, Grounding and\u00a0Retrieval"],"prefix":"10.1007","author":[{"given":"Yuxuan","family":"Wang","sequence":"first","affiliation":[]},{"given":"Difei","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Licheng","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Weixian","family":"Lei","sequence":"additional","affiliation":[]},{"given":"Matt","family":"Feiszli","sequence":"additional","affiliation":[]},{"given":"Mike Zheng","family":"Shou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,4]]},"reference":[{"issue":"7","key":"41_CR1","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1007\/s10514-018-9734-5","volume":"42","author":"PF Alcantarilla","year":"2018","unstructured":"Alcantarilla, P.F., Stent, S., Ros, G., Arroyo, R., Gherardi, R.: Street-view change detection with deconvolutional networks. Auton. Robot. 42(7), 1301\u20131322 (2018). https:\/\/doi.org\/10.1007\/s10514-018-9734-5","journal-title":"Auton. Robot."},{"key":"41_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1007\/978-3-319-46454-1_24","volume-title":"Computer Vision \u2013 ECCV 2016","author":"P Anderson","year":"2016","unstructured":"Anderson, P., Fernando, B., Johnson, M., Gould, S.: SPICE: semantic propositional image caption evaluation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 382\u2013398. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_24"},{"key":"41_CR3","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: ICCV, pp. 1728\u20131738 (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"41_CR4","doi-asserted-by":"crossref","unstructured":"Bendale, A., Boult, T.: Towards open world recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1893\u20131902 (2015)","DOI":"10.1109\/CVPR.2015.7298799"},{"key":"41_CR5","doi-asserted-by":"crossref","unstructured":"Cao, M., Chen, L., Shou, M.Z., Zhang, C., Zou, Y.: On pursuit of designing multi-modal transformer for video grounding. In: EMNLP, pp. 9810\u20139823 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.773"},{"key":"41_CR6","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: CVPR, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"41_CR7","unstructured":"Chen, D., Dolan, W.: Collecting highly parallel data for paraphrase evaluation. In: ACL, pp. 190\u2013200, June 2011. www.aclanthology.org\/P11-1020"},{"key":"41_CR8","unstructured":"Cheng, X., Lin, H., Wu, X., Yang, F., Shen, D.: Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss. arXiv preprint arXiv:2109.04290 (2021)"},{"key":"41_CR9","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Yang, Z., Nevatia, R.: Tall: Temporal activity localization via language query. In: ICCV, pp. 5267\u20135275 (2017)","DOI":"10.1109\/ICCV.2017.563"},{"key":"41_CR10","doi-asserted-by":"crossref","unstructured":"Ge, R., Gao, J., Chen, K., Nevatia, R.: MAC: mining activity concepts for language-based temporal localization. In: WACV, pp. 245\u2013253. IEEE (2019)","DOI":"10.1109\/WACV.2019.00032"},{"key":"41_CR11","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":"41_CR12","doi-asserted-by":"crossref","unstructured":"Iashin, V., Rahtu, E.: Multi-modal dense video captioning. In: CVPR, pp. 958\u2013959 (2020)","DOI":"10.1109\/CVPRW50498.2020.00487"},{"key":"41_CR13","doi-asserted-by":"crossref","unstructured":"Jhamtani, H., Berg-Kirkpatrick, T.: Learning to describe differences between pairs of similar images. In: EMNLP (2018)","DOI":"10.18653\/v1\/D18-1436"},{"key":"41_CR14","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"41_CR15","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Carlos Niebles, J.: Dense-captioning events in videos. In: ICCV, pp. 706\u2013715 (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"41_CR16","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Bansal, M., Berg, T.L.: TVQA: localized, compositional video question answering. In: EMNLP (2018)","DOI":"10.18653\/v1\/D18-1167"},{"key":"41_CR17","doi-asserted-by":"crossref","unstructured":"Li, Y., Yao, T., Pan, Y., Chao, H., Mei, T.: Jointly localizing and describing events for dense video captioning. In: CVPR, pp. 7492\u20137500. IEEE Computer Society (2018)","DOI":"10.1109\/CVPR.2018.00782"},{"key":"41_CR18","unstructured":"Lin, C.Y.: Rouge: A package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"issue":"4","key":"41_CR19","doi-asserted-by":"publisher","first-page":"1822","DOI":"10.1109\/TIP.2017.2784560","volume":"27","author":"Z Liu","year":"2017","unstructured":"Liu, Z., Li, G., Mercier, G., He, Y., Pan, Q.: Change detection in heterogenous remote sensing images via homogeneous pixel transformation. IEEE Trans. Image Process. 27(4), 1822\u20131834 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"41_CR20","unstructured":"Luo, H., et al.: Univl: a unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353 (2020)"},{"key":"41_CR21","doi-asserted-by":"crossref","unstructured":"Mun, J., Cho, M., Han, B.: Local-global video-text interactions for temporal grounding. In: CVPR, pp. 10810\u201310819 (2020)","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"41_CR22","doi-asserted-by":"crossref","unstructured":"Park, D.H., Darrell, T., Rohrbach, A.: Robust change captioning. In: ICCV, pp. 4624\u20134633 (2019)","DOI":"10.1109\/ICCV.2019.00472"},{"key":"41_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-77004-4_1","volume-title":"Pattern Recognition","author":"JA Portillo-Quintero","year":"2021","unstructured":"Portillo-Quintero, J.A., Ortiz-Bayliss, J.C., Terashima-Mar\u00edn, H.: A straightforward framework for video retrieval using CLIP. In: Roman-Rangel, E., Kuri-Morales, \u00c1.F., Mart\u00ednez-Trinidad, J.F., Carrasco-Ochoa, J.A., Olvera-L\u00f3pez, J.A. (eds.) MCPR 2021. LNCS, vol. 12725, pp. 3\u201312. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-77004-4_1"},{"issue":"6","key":"41_CR24","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1002\/wcs.133","volume":"2","author":"GA Radvansky","year":"2011","unstructured":"Radvansky, G.A., Zacks, J.M.: Event perception. Wiley Interdisc. Rev. Cogn. Sci. 2(6), 608\u2013620 (2011)","journal-title":"Wiley Interdisc. Rev. Cogn. Sci."},{"key":"41_CR25","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1162\/tacl_a_00207","volume":"1","author":"M Regneri","year":"2013","unstructured":"Regneri, M., Rohrbach, M., Wetzel, D., Thater, S., Schiele, B., Pinkal, M.: Grounding action descriptions in videos. TACL 1, 25\u201336 (2013)","journal-title":"TACL"},{"key":"41_CR26","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, vol. 28 (2015)"},{"key":"41_CR27","doi-asserted-by":"crossref","unstructured":"Shou, M.Z., Lei, S.W., Wang, W., Ghadiyaram, D., Feiszli, M.: Generic event boundary detection: a benchmark for event segmentation. In: ICCV, pp. 8075\u20138084 (2021)","DOI":"10.1109\/ICCV48922.2021.00797"},{"issue":"1","key":"41_CR28","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1109\/TGRS.2013.2240692","volume":"52","author":"J Tian","year":"2013","unstructured":"Tian, J., Cui, S., Reinartz, P.: Building change detection based on satellite stereo imagery and digital surface models. IEEE Trans. Geosci. Remote Sens. 52(1), 406\u2013417 (2013)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"41_CR29","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: ICCV, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"41_CR30","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"issue":"11","key":"41_CR31","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang, L., et al.: Temporal segment networks for action recognition in videos. PAMI 41(11), 2740\u20132755 (2018)","journal-title":"PAMI"},{"key":"41_CR32","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhang, R., Lu, Z., Zheng, F., Cheng, R., Luo, P.: End-to-end dense video captioning with parallel decoding. In: ICCV, pp. 6847\u20136857 (2021)","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"41_CR33","doi-asserted-by":"crossref","unstructured":"Wang, X., Wu, J., Chen, J., Li, L., Wang, Y.F., Wang, W.Y.: Vatex: a large-scale, high-quality multilingual dataset for video-and-language research. In: ICCV, pp. 4581\u20134591 (2019)","DOI":"10.1109\/ICCV.2019.00468"},{"key":"41_CR34","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: Msr-vtt: A large video description dataset for bridging video and language. In: CVPR, pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"41_CR35","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Mei, T., Zhu, W.: To find where you talk: Temporal sentence localization in video with attention based location regression. In: AAAI, vol. 33, pp. 9159\u20139166 (2019)","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"41_CR36","doi-asserted-by":"crossref","unstructured":"Zeng, R., Xu, H., Huang, W., Chen, P., Tan, M., Gan, C.: Dense regression network for video grounding. In: CVPR, pp. 10287\u201310296 (2020)","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"41_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, S., Peng, H., Fu, J., Luo, J.: Learning 2d temporal adjacent networks formoment localization with natural language. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"41_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, L., Xu, C., Corso, J.J.: Towards automatic learning of procedures from web instructional videos. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"41_CR39","doi-asserted-by":"crossref","unstructured":"Zhu, L., Yang, Y.: Actbert: learning global-local video-text representations. In: CVPR, pp. 8746\u20138755 (2020)","DOI":"10.1109\/CVPR42600.2020.00877"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19833-5_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T15:48:57Z","timestamp":1673279337000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19833-5_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198328","9783031198335"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19833-5_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"4 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"0","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":"28% - 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":"3.21","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":"3.91","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"From the workshops, 367 reviewed full papers have been selected for publication","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)"}}]}}