{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T14:30:39Z","timestamp":1790001039889,"version":"4.0.1"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T00:00:00Z","timestamp":1571097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China award number(s):","award":["61772535"],"award-info":[{"award-number":["61772535"]}]},{"name":"Beijing Natural Science Foundation award number(s):","award":["4192028"],"award-info":[{"award-number":["4192028"]}]},{"name":"National Key Research and Development Plan award number(s)","award":["2016YFB1001202"],"award-info":[{"award-number":["2016YFB1001202"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3350962","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"121-129","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["Visual Relation Detection with Multi-Level Attention"],"prefix":"10.1145","author":[{"given":"Sipeng","family":"Zheng","sequence":"first","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shizhe","family":"Chen","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qin","family":"Jin","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_3_1","volume-title":"Learning to generalize to new compositions in image understanding. arXiv preprint arXiv:1608.07639","author":"Atzmon Yuval","year":"2016"},{"key":"e_1_3_2_1_4_1","volume-title":"Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473","author":"Bahdanau Dzmitry","year":"2014"},{"key":"e_1_3_2_1_5_1","unstructured":"Antoine Bordes Nicolas Usunier Alberto Garcia-Duran Jason Weston and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi-relational data. In Advances in neural information processing systems. 2787--2795.  Antoine Bordes Nicolas Usunier Alberto Garcia-Duran Jason Weston and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi-relational data. In Advances in neural information processing systems. 2787--2795."},{"key":"e_1_3_2_1_6_1","volume-title":"Sca-cnn: Spatial and channel-wise attention in convolutional networks for image captioning. In roceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5659--5667.","author":"Chen Long","year":"2017"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206067"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.352"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.412"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_4"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2004.824875"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00872"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88682-2_3"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"e_1_3_2_1_20_1","volume-title":"International Conference on Machine Learning. 1378--1387","author":"Kumar Ankit","year":"2016"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540072"},{"key":"e_1_3_2_1_22_1","volume-title":"A hierarchical neural autoencoder for paragraphs and documents. arXiv preprint arXiv:1506.01057","author":"Li Jiwei","year":"2015"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.766"},{"key":"e_1_3_2_1_24_1","volume-title":"Thirty-Second AAAI Conference on Artificial Intelligence.","author":"Liang Kongming","year":"2018"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"e_1_3_2_1_27_1","volume-title":"Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025","author":"Luong Minh-Thang","year":"2015"},{"key":"e_1_3_2_1_28_1","unstructured":"Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems. 3111--3119.  Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems. 3111--3119."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298713"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_32_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. 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. 91--99."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995711"},{"key":"e_1_3_2_1_34_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014"},{"key":"e_1_3_2_1_35_1","volume-title":"International conference on machine learning. 2397--2406","author":"Xiong Caiming","year":"2016"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"e_1_3_2_1_37_1","volume-title":"International conference on machine learning. 2048--2057","author":"Xu Kelvin","year":"2015"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_20"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.121"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.331"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.454"},{"key":"e_1_3_2_1_44_1","volume-title":"Large-scale visual relationship understanding. arXiv preprint arXiv:1804.10660","author":"Zhang Ji","year":"2018"},{"key":"e_1_3_2_1_45_1","volume-title":"Modality Attention for End-to-End Audio-visual Speech Recognition. arXiv preprint arXiv:1811.05250","author":"Zhou Pan","year":"2018"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.71"}],"event":{"name":"MM '19: The 27th ACM International Conference on Multimedia","location":"Nice France","acronym":"MM '19","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350962","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3350962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:18Z","timestamp":1750201998000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350962"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":46,"alternative-id":["10.1145\/3343031.3350962","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3350962","relation":{},"subject":[],"published":{"date-parts":[[2019,10,15]]},"assertion":[{"value":"2019-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}