{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T05:12:38Z","timestamp":1743138758934,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031189067"},{"type":"electronic","value":"9783031189074"}],"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\/978-3-031-18907-4_35","type":"book-chapter","created":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:03:53Z","timestamp":1666825433000},"page":"449-461","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-grained Cascade Interaction Network for\u00a0Temporal Activity Localization via\u00a0Language"],"prefix":"10.1007","author":[{"given":"Cong","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingli","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,27]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Anne Hendricks, L., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.: Localizing moments in video with natural language. In: ICCV, pp. 5803\u20135812 (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"35_CR2","doi-asserted-by":"crossref","unstructured":"Chen, J., Chen, X., Ma, L., Jie, Z., Chua, T.S.: Temporally grounding natural sentence in video. In: EMNLP, pp. 162\u2013171 (2018)","DOI":"10.18653\/v1\/D18-1015"},{"key":"35_CR3","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":"35_CR4","doi-asserted-by":"crossref","unstructured":"Ghosh, S., Agarwal, A., Parekh, Z., Hauptmann, A.G.: Excl: extractive clip localization using natural language descriptions. In: NAACL, pp. 1984\u20131990 (2019)","DOI":"10.18653\/v1\/N19-1198"},{"key":"35_CR5","unstructured":"Hahn, M., Kadav, A., Rehg, J.M., Graf, H.P.: Tripping through time: efficient localization of activities in videos. In: BMVC (2020)"},{"key":"35_CR6","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":"35_CR7","doi-asserted-by":"crossref","unstructured":"Liu, D., et al.: Context-aware biaffine localizing network for temporal sentence grounding. In: CVPR, pp. 11235\u201311244 (2021)","DOI":"10.1109\/CVPR46437.2021.01108"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Liu, D., Qu, X., Zhou, P.: Progressively guide to attend: an iterative alignment framework for temporal sentence grounding. In: EMNLP, pp. 9302\u20139311 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.733"},{"key":"35_CR9","doi-asserted-by":"crossref","unstructured":"Liu, M., Wang, X., Nie, L., He, X., Chen, B., Chua, T.S.: Attentive moment retrieval in videos. In: ACM SIGIR, pp. 15\u201324 (2018)","DOI":"10.1145\/3209978.3210003"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Lu, C., Chen, L., Tan, C., Li, X., Xiao, J.: Debug: a dense bottom-up grounding approach for natural language video localization. In: EMNLP-IJCNLP, pp. 5144\u20135153 (2019)","DOI":"10.18653\/v1\/D19-1518"},{"key":"35_CR12","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":"35_CR13","doi-asserted-by":"crossref","unstructured":"Nan, G., et al.: Interventional video grounding with dual contrastive learning. In: CVPR, pp. 2765\u20132775 (2021)","DOI":"10.1109\/CVPR46437.2021.00279"},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Qu, X., et al.: Fine-grained iterative attention network for temporal language localization in videos. In: ACM Multimedia, pp. 4280\u20134288 (2020)","DOI":"10.1145\/3394171.3414053"},{"key":"35_CR15","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. Trans. Assoc. Comput. Linguist. 1, 25\u201336 (2013)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"Soldan, M., Xu, M., Qu, S., Tegner, J., Ghanem, B.: VLG-net: video-language graph matching network for video grounding. In: ICCV Workshops, pp. 3224\u20133234 (2021)","DOI":"10.1109\/ICCVW54120.2021.00361"},{"key":"35_CR17","doi-asserted-by":"crossref","unstructured":"Wang, J., Ma, L., Jiang, W.: Temporally grounding language queries in videos by contextual boundary-aware prediction. In: AAAI, pp. 12168\u201312175 (2020)","DOI":"10.1609\/aaai.v34i07.6897"},{"key":"35_CR18","doi-asserted-by":"crossref","unstructured":"Wu, J., Li, G., Liu, S., Lin, L.: Tree-structured policy based progressive reinforcement learning for temporally language grounding in video. In: AAAI, pp. 12386\u201312393 (2020)","DOI":"10.1609\/aaai.v34i07.6924"},{"key":"35_CR19","doi-asserted-by":"crossref","unstructured":"Xu, H., He, K., Plummer, B.A., Sigal, L., Sclaroff, S., Saenko, K.: Multilevel language and vision integration for text-to-clip retrieval. In: AAAI, pp. 9062\u20139069 (2019)","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Ma, L., Wang, J., Liu, W., Zhu, W.: Semantic conditioned dynamic modulation for temporal sentence grounding in videos. In: NeurIPS, pp. 536\u2013546 (2019)","DOI":"10.1109\/TPAMI.2020.3038993"},{"key":"35_CR21","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. pp. 9159\u20139166 (2019)","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"35_CR22","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":"35_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, D., Dai, X., Wang, X., Wang, Y.F., Davis, L.S.: Man: moment alignment network for natural language moment retrieval via iterative graph adjustment. In: CVPR, pp. 1247\u20131257 (2019)","DOI":"10.1109\/CVPR.2019.00134"},{"key":"35_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, H., Sun, A., Jing, W., Zhou, J.T.: Span-based localizing network for natural language video localization. In: ACL, pp. 6543\u20136554 (2020)","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"35_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, S., Peng, H., Fu, J., Luo, J.: Learning 2d temporal adjacent networks for moment localization with natural language. In: AAAI, pp. 12870\u201312877 (2020)","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"35_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Lin, Z., Zhao, Z., Xiao, Z.: Cross-modal interaction networks for query-based moment retrieval in videos. In: ACM SIGIR, pp. 655\u2013664 (2019)","DOI":"10.1145\/3331184.3331235"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-18907-4_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T16:32:12Z","timestamp":1728232332000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-18907-4_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031189067","9783031189074"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-18907-4_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"27 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"14 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/en.prcv.cn\/","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":"microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"564","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":"233","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":"41% - 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":"3.03","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":"3.35","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)"}}]}}