{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T06:15:41Z","timestamp":1743142541501,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031198328"},{"type":"electronic","value":"9783031198335"}],"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_8","type":"book-chapter","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T00:40:30Z","timestamp":1667522430000},"page":"125-141","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Asymmetric Relation Consistency Reasoning for\u00a0Video Relation Grounding"],"prefix":"10.1007","author":[{"given":"Huan","family":"Li","sequence":"first","affiliation":[]},{"given":"Ping","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Jiapeng","family":"Li","sequence":"additional","affiliation":[]},{"given":"Zeyu","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Jiahui","family":"Shang","sequence":"additional","affiliation":[]},{"given":"Nanning","family":"Zheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,4]]},"reference":[{"key":"8_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"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Z., Ma, L., Luo, W., Wong, K.Y.K.: Weakly-supervised spatio-temporally grounding natural sentence in video. In: The Annual Meeting of the Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/P19-1183"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Da, C., Zhang, Y., Zheng, Y., Pan, P., Xu, Y., Pan, C.: Asynce: disentangling false-positives for weakly-supervised video grounding. In: ACM International Conference on Multimedia (2021)","DOI":"10.1145\/3474085.3481539"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Ding, X., et al.: Support-set based cross-supervision for video grounding. In: IEEE CVPR (2021)","DOI":"10.1109\/ICCV48922.2021.01137"},{"key":"8_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"8_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"696","DOI":"10.1007\/978-3-030-58610-2_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Gao","year":"2020","unstructured":"Gao, C., Xu, J., Zou, Y., Huang, J.-B.: DRG: dual relation graph for human-object interaction detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 696\u2013712. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_41"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Gao, K., Chen, L., Huang, Y., Xiao, J.: Video relation detection via tracklet based visual transformer. In: ACM International Conference on Multimedia (2021)","DOI":"10.1145\/3474085.3479231"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Kim, B., Lee, J., Kang, J., Kim, E.S., Kim, H.J.: Hotr: end-to-end human-object interaction detection with transformers. In: IEEE CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Krishna, R., Chami, I., Bernstein, M., Fei-Fei, L.: Referring relationships. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00718"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Li, J., Wei, P., Zhang, Y., Zheng, N.: A slow-i-fast-p architecture for compressed video action recognition. In: ACM International Conference on Multimedia (2020)","DOI":"10.1145\/3394171.3413641"},{"key":"8_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1007\/978-3-030-01234-2_34","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Q Li","year":"2018","unstructured":"Li, Q., Tao, Q., Joty, S., Cai, J., Luo, J.: VQA-E: explaining, elaborating, and enhancing your answers for visual questions. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 570\u2013586. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_34"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Li, Y., Yang, X., Shang, X., Chua, T.S.: Interventional video relation detection. In: ACM International Conference on Multimedia (2021)","DOI":"10.1145\/3474085.3475540"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Liao, Y., Liu, S., Wang, F., Chen, Y., Qian, C., Feng, J.: Ppdm: parallel point detection and matching for real-time human-object interaction detection. In: IEEE CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"8_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1007\/978-3-319-46448-0_51","volume-title":"Computer Vision \u2013 ECCV 2016","author":"C Lu","year":"2016","unstructured":"Lu, C., Krishna, R., Bernstein, M., Fei-Fei, L.: Visual relationship detection with language priors. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 852\u2013869. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_51"},{"key":"8_CR16","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 (2022)","DOI":"10.1109\/ICME52920.2022.9859803"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Mi, L., Chen, Z.: Hierarchical graph attention network for visual relationship detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01390"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Conference on Empirical Methods in Natural Language Processing (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Qian, X., Zhuang, Y., Li, Y., Xiao, S., Pu, S., Xiao, J.: Video relation detection with spatio-temporal graph. In: ACM International Conference on Multimedia (2019)","DOI":"10.1145\/3343031.3351058"},{"key":"8_CR20","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems (2015)"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Shang, X., Li, Y., Xiao, J., Ji, W., Chua, T.S.: Video visual relation detection via iterative inference. In: ACM International Conference on Multimedia (2021)","DOI":"10.1145\/3474085.3475263"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Shang, X., Ren, T., Guo, J., Zhang, H., Chua, T.S.: Video visual relation detection. In: ACM International Conference on Multimedia (2017)","DOI":"10.1145\/3123266.3123380"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Shi, J., Xu, J., Gong, B., Xu, C.: Not all frames are equal: Weakly-supervised video grounding with contextual similarity and visual clustering losses. In: IEEE CVPR (2019)","DOI":"10.1109\/CVPR.2019.01069"},{"key":"8_CR24","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: IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCVW54120.2021.00361"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Sun, X., Ren, T., Zi, Y., Wu, G.: Video visual relation detection via multi-modal feature fusion. In: ACM International Conference on Multimedia (2019)","DOI":"10.1145\/3343031.3356076"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Tamura, M., Ohashi, H., Yoshinaga, T.: Qpic: query-based pairwise human-object interaction detection with image-wide contextual information. In: IEEE CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H.H., Divvala, S., Morency, L.P., Salakhutdinov, R., Farhadi, A.: Video relationship reasoning using gated spatio-temporal energy graph. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.01067"},{"key":"8_CR28","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Rohrbach, M., Donahue, J., Mooney, R., Darrell, T., Saenko, K.: Sequence to sequence - video to text. In: IEEE International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.515"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Wang, T., Yang, T., Danelljan, M., Khan, F.S., Zhang, X., Sun, J.: Learning human-object interaction detection using interaction points. In: IEEE CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00417"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Wang, W., Gao, J., Xu, C.: Weakly-supervised video object grounding via stable context learning. In: ACM International Conference on Multimedia (2021)","DOI":"10.1145\/3474085.3475245"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhou, W., Li, H.: Fine-grained semantic alignment network for weakly supervised temporal language grounding. In: Findings of the Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.9"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Wei, P., Zhao, Y., Zheng, N., Zhu, S.C.: Modeling 4d human-object interactions for joint event segmentation, recognition, and object localization. In: IEEE Trans. Pattern Anal. Mach. Intell., 1165\u20131179 (2017)","DOI":"10.1109\/TPAMI.2016.2574712"},{"key":"8_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1007\/978-3-030-58539-6_27","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Xiao","year":"2020","unstructured":"Xiao, J., Shang, X., Yang, X., Tang, S., Chua, T.-S.: Visual relation grounding in videos. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 447\u2013464. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_27"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Yu, R., Li, A., Morariu, V.I., Davis, L.S.: Visual relationship detection with internal and external linguistic knowledge distillation. In: IEEE International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.121"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Zhan, Y., Yu, J., Yu, T., Tao, D.: On exploring undetermined relationships for visual relationship detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00527"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Zhao, Z., Zhang, Z., Lin, Z.: Cascaded prediction network via segment tree for temporal video grounding. In: IEEE CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00418"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: IEEE International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.244"}],"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_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T15:33:12Z","timestamp":1673278392000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19833-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198328","9783031198335"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19833-5_8","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":"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)"}}]}}