{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:26:11Z","timestamp":1781587571713,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3414026","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T12:26:53Z","timestamp":1602505613000},"page":"4070-4078","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":88,"title":["Jointly Cross- and Self-Modal Graph Attention Network for Query-Based Moment Localization"],"prefix":"10.1145","author":[{"given":"Daizong","family":"Liu","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoye","family":"Qu","sequence":"additional","affiliation":[{"name":"Huawei Cloud, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Columbia University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfeng","family":"Dong","sequence":"additional","affiliation":[{"name":"Zhejiang Gongshang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zichuan","family":"Xu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"e_1_3_2_2_2_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Ballas Nicolas","year":"2015","unstructured":"Nicolas Ballas , Li Yao , Chris Pal , and Aaron Courville . 2015 . Delving deeper into convolutional networks for learning video representations . In Proceedings of the International Conference on Learning Representations (ICLR). Nicolas Ballas, Li Yao, Chris Pal, and Aaron Courville. 2015. Delving deeper into convolutional networks for learning video representations. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3078976"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.95"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6627"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018199"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_2_9_1","unstructured":"Junyoung Chung Caglar Gulcehre KyungHyun Cho and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. In Advances in Neural Information Processing Systems (NIPS).  Junyoung Chung Caglar Gulcehre KyungHyun Cho and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. In Advances in Neural Information Processing Systems (NIPS)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00808"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2832602"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Ko Endo Masaki Aono Eric Nichols and Kotaro Funakoshi. 2017. An Attention-based Regression Model for Grounding Textual Phrases in Images.. In IJCAI. 3995--4001.  Ko Endo Masaki Aono Eric Nichols and Kotaro Funakoshi. 2017. An Attention-based Regression Model for Grounding Textual Phrases in Images.. In IJCAI. 3995--4001.","DOI":"10.24963\/ijcai.2017\/558"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00138"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_4"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00032"},{"key":"e_1_3_2_2_19_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning (ICML). 1263--1272","author":"Gilmer Justin","year":"2017","unstructured":"Justin Gilmer , Samuel S Schoenholz , Patrick F Riley , Oriol Vinyals , and George E Dahl . 2017 . Neural message passing for quantum chemistry . In Proceedings of the 34th International Conference on Machine Learning (ICML). 1263--1272 . Justin Gilmer, Samuel S Schoenholz, Patrick F Riley, Oriol Vinyals, and George E Dahl. 2017. Neural message passing for quantum chemistry. In Proceedings of the 34th International Conference on Machine Learning (ICML). 1263--1272."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"e_1_3_2_2_21_1","volume-title":"Heterogeneous Graph Transformer. arXiv preprint arXiv:2003.01332","author":"Hu Ziniu","year":"2020","unstructured":"Ziniu Hu , Yuxiao Dong , Kuansan Wang , and Yizhou Sun . 2020. Heterogeneous Graph Transformer. arXiv preprint arXiv:2003.01332 ( 2020 ). Ziniu Hu, Yuxiao Dong, Kuansan Wang, and Yizhou Sun. 2020. Heterogeneous Graph Transformer. arXiv preprint arXiv:2003.01332 (2020)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01186"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"e_1_3_2_2_30_1","unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in Neural Information Processing Systems (NIPS). 91--99.  Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in Neural Information Processing Systems (NIPS). 91--99."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_2_34_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems (NIPS). 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems (NIPS). 5998--6008."},{"key":"e_1_3_2_2_35_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Petar Velivc","year":"2017","unstructured":"Petar Velivc kovi\u0107, Guillem Cucurull , Arantxa Casanova , Adriana Romero , Pietro Lio , and Yoshua Bengio . 2017 . Graph attention networks . In Proceedings of the International Conference on Learning Representations (ICLR). Petar Velivc kovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6897"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_42"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.337"},{"key":"e_1_3_2_2_42_1","unstructured":"Yitian Yuan Lin Ma Jingwen Wang Wei Liu and Wenwu Zhu. 2019 a. Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos. In Advances in Neural Information Processing Systems (NIPS). 534--544.  Yitian Yuan Lin Ma Jingwen Wang Wei Liu and Wenwu Zhu. 2019 a. Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos. In Advances in Neural Information Processing Systems (NIPS). 534--544."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350879"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331235"}],"event":{"name":"MM '20: The 28th ACM International Conference on Multimedia","location":"Seattle WA USA","acronym":"MM '20","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3414026","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3414026","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:23Z","timestamp":1750197683000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3414026"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":48,"alternative-id":["10.1145\/3394171.3414026","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3414026","relation":{},"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}