{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T05:01:02Z","timestamp":1764997262814,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":44,"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":["6197020369, 61572431"],"award-info":[{"award-number":["6197020369, 61572431"]}]},{"name":"Zhejiang Natural Science Foundation","award":["LR19F020002, LZ17F020001"],"award-info":[{"award-number":["LR19F020002, LZ17F020001"]}]},{"name":"National Key Research and Development Program of China","award":["SQ2018AAA010010"],"award-info":[{"award-number":["SQ2018AAA010010"]}]},{"name":"the Fundamental Research Funds for the Central Universities and Chinese Knowledge Center for Engineering Sciences and Technology"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3351058","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"84-93","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":66,"title":["Video Relation Detection with Spatio-Temporal Graph"],"prefix":"10.1145","author":[{"given":"Xufeng","family":"Qian","sequence":"first","affiliation":[{"name":"Zhejiang University, Zhejiang Hangzhou, China"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang Hangzhou, China"}]},{"given":"Yimeng","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang Hangzhou, China"}]},{"given":"Shaoning","family":"Xiao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang Hangzhou, China"}]},{"given":"Shiliang","family":"Pu","sequence":"additional","affiliation":[{"name":"Hikvision Research Institute, Zhejiang Hangzhou, China"}]},{"given":"Jun","family":"Xiao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang Hangzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"volume-title":"Deep Compositional Question Answering with Neural Module Networks. CoRR","year":"2015","author":"Andreas Jacob","key":"e_1_3_2_1_1_1"},{"volume-title":"Hinton","year":"2016","author":"Ba Lei Jimmy","key":"e_1_3_2_1_2_1"},{"volume-title":"Fully-Convolutional Siamese Networks for Object Tracking. In Computer Vision - ECCV 2016 Workshops - Amsterdam, The Netherlands, October 8--10 and 15--16, 2016, Proceedings, Part II. 850--865","author":"Bertinetto Luca","key":"e_1_3_2_1_3_1"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539960"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Long Chen Hanwang Zhang Jun Xiao Xiangnan He Shiliang Pu and Shih-Fu Chang. 2019. Counterfactual Critic Multi-Agent Training for Scene Graph Generation. In ICCV .  Long Chen Hanwang Zhang Jun Xiao Xiangnan He Shiliang Pu and Shih-Fu Chang. 2019. Counterfactual Critic Multi-Agent Training for Scene Graph Generation. In ICCV .","DOI":"10.1109\/ICCV.2019.00471"},{"volume-title":"High-Order Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting. CoRR","year":"2018","author":"Cui Zhiyong","key":"e_1_3_2_1_7_1"},{"volume-title":"Accurate Scale Estimation for Robust Visual Tracking. In British Machine Vision Conference, BMVC 2014","year":"2014","author":"Danelljan Martin","key":"e_1_3_2_1_8_1"},{"volume-title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016","year":"2016","author":"Defferrard Micha\u00eb","key":"e_1_3_2_1_9_1"},{"volume-title":"ActionVLAD: Learning Spatio-Temporal Aggregation for Action Classification. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","year":"2017","author":"Girdhar Rohit","key":"e_1_3_2_1_10_1"},{"volume-title":"Inductive Representation Learning on Large Graphs. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","year":"2017","author":"Hamilton William L.","key":"e_1_3_2_1_11_1"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00508"},{"volume-title":"Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016","year":"2016","author":"He Kaiming","key":"e_1_3_2_1_13_1"},{"volume-title":"Deep Convolutional Networks on Graph-Structured Data. CoRR","year":"2015","author":"Henaff Mikael","key":"e_1_3_2_1_14_1"},{"volume-title":"Kipf and Max Welling","year":"2017","author":"Thomas","key":"e_1_3_2_1_15_1"},{"volume-title":"Phrases and Region Captions. In IEEE International Conference on Computer Vision, ICCV 2017","year":"2017","author":"Li Yikang","key":"e_1_3_2_1_16_1"},{"volume-title":"Proceedings, Part I. 852--869","year":"2016","author":"Lu Cewu","key":"e_1_3_2_1_17_1"},{"volume-title":"The More You Know: Using Knowledge Graphs for Image Classification. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","year":"2017","author":"Marino Kenneth","key":"e_1_3_2_1_18_1"},{"volume-title":"Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","year":"2017","author":"Monti Federico","key":"e_1_3_2_1_19_1"},{"volume-title":"Weakly-Supervised Learning of Visual Relations. In IEEE International Conference on Computer Vision, ICCV 2017","year":"2017","author":"Peyre Julia","key":"e_1_3_2_1_20_1"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1187"},{"volume-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015","year":"2015","author":"Ren Shaoqing","key":"e_1_3_2_1_22_1"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995711"},{"volume-title":"Few-Shot Learning with Graph Neural Networks. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings .","year":"2018","author":"Satorras Victor Garcia","key":"e_1_3_2_1_25_1"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123380"},{"volume-title":"Training Region-Based Object Detectors with Online Hard Example Mining. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016","year":"2016","author":"Shrivastava Abhinav","key":"e_1_3_2_1_27_1"},{"volume-title":"Graph-Structured Representations for Visual Question Answering. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","year":"2017","author":"Teney Damien","key":"e_1_3_2_1_28_1"},{"volume-title":"End-to-End Representation Learning for Correlation Filter Based Tracking. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","year":"2017","author":"Valmadre Jack","key":"e_1_3_2_1_29_1"},{"volume-title":"Graph Convolutional Matrix Completion. CoRR","year":"2017","author":"van den Berg Rianne","key":"e_1_3_2_1_30_1"},{"volume-title":"Action Recognition with Improved Trajectories. In IEEE International Conference on Computer Vision, ICCV 2013","year":"2013","author":"Wang Heng","key":"e_1_3_2_1_31_1"},{"volume-title":"Non-Local Neural Networks. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018","year":"2018","author":"Wang Xiaolong","key":"e_1_3_2_1_32_1"},{"volume-title":"Proceedings, Part V. 413--431","year":"2018","author":"Wang Xiaolong","key":"e_1_3_2_1_33_1"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"volume-title":"Dual-stream recurrent neural network for video captioning","year":"2018","author":"Xu Ning","key":"e_1_3_2_1_36_1"},{"volume-title":"Proceedings, Part I. 690--706","year":"2018","author":"Yang Jianwei","key":"e_1_3_2_1_37_1"},{"volume-title":"Proceedings, Part III. 330--347","year":"2018","author":"Yin Guojun","key":"e_1_3_2_1_38_1"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"volume-title":"Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation. In IEEE International Conference on Computer Vision, ICCV 2017","year":"2017","author":"Yu Ruichi","key":"e_1_3_2_1_40_1"},{"volume-title":"Neural Motifs: Scene Graph Parsing With Global Context. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018","year":"2018","author":"Zellers Rowan","key":"e_1_3_2_1_41_1"},{"volume-title":"Visual Translation Embedding Network for Visual Relation Detection. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","year":"2017","author":"Zhang Hanwang","key":"e_1_3_2_1_42_1"},{"volume-title":"Proceedings, Part I. 831--846","year":"2018","author":"Zhou Bolei","key":"e_1_3_2_1_43_1"},{"volume-title":"Towards Context-Aware Interaction Recognition for Visual Relationship Detection. In IEEE International Conference on Computer Vision, ICCV 2017","year":"2017","author":"Zhuang Bohan","key":"e_1_3_2_1_44_1"}],"event":{"name":"MM '19: The 27th ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Nice France","acronym":"MM '19"},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351058","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3351058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:12Z","timestamp":1750201992000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351058"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":44,"alternative-id":["10.1145\/3343031.3351058","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3351058","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"}}]}}