{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T14:44:39Z","timestamp":1787237079274,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":47,"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":[{"DOI":"10.13039\/501100012659","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61571297"],"award-info":[{"award-number":["61571297"]}],"id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2017YFB1002401"],"award-info":[{"award-number":["2017YFB1002401"]}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["18DZ1112300"],"award-info":[{"award-number":["18DZ1112300"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3351024","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T12:32:26Z","timestamp":1571661146000},"page":"30-38","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Visual Relationship Detection with Relative Location Mining"],"prefix":"10.1145","author":[{"given":"Hao","family":"Zhou","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chongyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanping","family":"Hu","sequence":"additional","affiliation":[{"name":"Railway Police College, zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Paragraph Generation Network with Visual Relationship Detection. In 2018 ACM Multimedia Conference on Multimedia Conference. ACM","author":"Che Wenbin","year":"2018","unstructured":"Wenbin Che , Xiaopeng Fan , Ruiqin Xiong , and Debin Zhao . 2018 . Paragraph Generation Network with Visual Relationship Detection. In 2018 ACM Multimedia Conference on Multimedia Conference. ACM , New York, NY, USA, 1435--1443. Wenbin Che, Xiaopeng Fan, Ruiqin Xiong, and Debin Zhao. 2018. Paragraph Generation Network with Visual Relationship Detection. In 2018 ACM Multimedia Conference on Multimedia Conference. ACM, New York, NY, USA, 1435--1443."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00124"},{"key":"e_1_3_2_1_3_1","volume-title":"Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio.","author":"Cho Kyunghyun","year":"2014","unstructured":"Kyunghyun Cho , Bart Van Merri\u00ebnboer , Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014 . Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014). Kyunghyun Cho, Bart Van Merri\u00ebnboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)."},{"key":"e_1_3_2_1_4_1","volume-title":"Context-Dependent Diffusion Network for Visual Relationship Detection. In 2018 ACM Multimedia Conference on Multimedia Conference. ACM","author":"Cui Zhen","year":"2018","unstructured":"Zhen Cui , Chunyan Xu , Wenming Zheng , and Jian Yang . 2018 . Context-Dependent Diffusion Network for Visual Relationship Detection. In 2018 ACM Multimedia Conference on Multimedia Conference. ACM , New York, NY, USA, 1475--1482. Zhen Cui, Chunyan Xu, Wenming Zheng, and Jian Yang. 2018. Context-Dependent Diffusion Network for Visual Relationship Detection. In 2018 ACM Multimedia Conference on Multimedia Conference. ACM, New York, NY, USA, 1475--1482."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.352"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_12"},{"key":"e_1_3_2_1_7_1","volume-title":"Fast Parameter Adaptation for Few-shot Image Captioning and Visual Question Answering. In 2018 ACM Multimedia Conference on Multimedia Conference . ACM","author":"Dong Xuanyi","year":"2018","unstructured":"Xuanyi Dong , Linchao Zhu , De Zhang , Yi Yang , and Fei Wu . 2018 . Fast Parameter Adaptation for Few-shot Image Captioning and Visual Question Answering. In 2018 ACM Multimedia Conference on Multimedia Conference . ACM , New York, NY, USA, 54--62. Xuanyi Dong, Linchao Zhu, De Zhang, Yi Yang, and Fei Wu. 2018. Fast Parameter Adaptation for Few-shot Image Captioning and Visual Question Answering. In 2018 ACM Multimedia Conference on Multimedia Conference . ACM, New York, NY, USA, 54--62."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587799"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240687"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_2_1_12_1","volume-title":"Visual Spatial Attention Network for Relationship Detection. In 2018 ACM Multimedia Conference on Multimedia Conference. ACM","author":"Han Chaojun","year":"2018","unstructured":"Chaojun Han , Fumin Shen , Li Liu , Yang Yang , and Heng Tao Shen . 2018 . Visual Spatial Attention Network for Relationship Detection. In 2018 ACM Multimedia Conference on Multimedia Conference. ACM , New York, NY, USA, 510--518. Chaojun Han, Fumin Shen, Li Liu, Yang Yang, and Heng Tao Shen. 2018. Visual Spatial Attention Network for Relationship Detection. In 2018 ACM Multimedia Conference on Multimedia Conference. ACM, New York, NY, USA, 510--518."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_15_1","volume-title":"Shared Linear Encoder-based Gaussian Process Latent Variable Model for Visual Classification. In 2018 ACM Multimedia Conference on Multimedia Conference . ACM","author":"Li Jinxing","year":"2018","unstructured":"Jinxing Li , Bob Zhang , Guangming Lu , and David Zhang . 2018 b. Shared Linear Encoder-based Gaussian Process Latent Variable Model for Visual Classification. In 2018 ACM Multimedia Conference on Multimedia Conference . ACM , New York, NY, USA, 26--34. Jinxing Li, Bob Zhang, Guangming Lu, and David Zhang. 2018b. Shared Linear Encoder-based Gaussian Process Latent Variable Model for Visual Classification. In 2018 ACM Multimedia Conference on Multimedia Conference . ACM, New York, NY, USA, 26--34."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.766"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_21"},{"key":"e_1_3_2_1_18_1","volume-title":"Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493","author":"Li Yujia","year":"2015","unstructured":"Yujia Li , Daniel Tarlow , Marc Brockschmidt , and Richard Zemel . 2015. Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493 ( 2015 ). Yujia Li, Daniel Tarlow, Marc Brockschmidt, and Richard Zemel. 2015. Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493 (2015)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.469"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2014.7051577"},{"key":"e_1_3_2_1_25_1","unstructured":"Francisco Massa and Ross Girshick. 2018. maskrcnn-benchmark: Fast modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch . https:\/\/github.com\/facebookresearch\/maskrcnn-benchmark .  Francisco Massa and Ross Girshick. 2018. maskrcnn-benchmark: Fast modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch . https:\/\/github.com\/facebookresearch\/maskrcnn-benchmark ."},{"key":"e_1_3_2_1_26_1","volume-title":"Advances in neural information processing systems","author":"Mikolov Tomas","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 . MIT Press , 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. MIT Press, 3111--3119."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.554"},{"key":"e_1_3_2_1_28_1","volume-title":"Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi . 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 ( 2018 ). Joseph Redmon and Ali Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)."},{"key":"e_1_3_2_1_29_1","volume-title":"Advances in neural information processing systems","author":"Ren Shaoqing","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 . MIT Press , 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. MIT Press, 91--99."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995711"},{"key":"e_1_3_2_1_32_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 ( 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_33_1","volume-title":"Advances in Neural Information Processing Systems","author":"Woo Sanghyun","unstructured":"Sanghyun Woo , Dahun Kim , Donghyeon Cho , and In So Kweon . 2018. LinkNet: Relational Embedding for Scene Graph . In Advances in Neural Information Processing Systems . MIT Press , 558--568. Sanghyun Woo, Dahun Kim, Donghyeon Cho, and In So Kweon. 2018. LinkNet: Relational Embedding for Scene Graph. In Advances in Neural Information Processing Systems. MIT Press, 558--568."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123388"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 4622--4630","author":"Wu Qi","unstructured":"Qi Wu , Peng Wang , Chunhua Shen , Anthony Dick , and Anton van den Hengel. 2016. Ask me anything: Free-form visual question answering based on knowledge from external sources . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 4622--4630 . Qi Wu, Peng Wang, Chunhua Shen, Anthony Dick, and Anton van den Hengel. 2016. Ask me anything: Free-form visual question answering based on knowledge from external sources. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 4622--4630."},{"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","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_3"},{"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","volume-title":"CVPR","author":"Zhang Hanwang","unstructured":"Hanwang Zhang , Zawlin Kyaw , Shih-Fu Chang , and Tat-Seng Chua . 2017b. Visual translation embedding network for visual relation detection . In CVPR . IEEE , 5. Hanwang Zhang, Zawlin Kyaw, Shih-Fu Chang, and Tat-Seng Chua. 2017b. Visual translation embedding network for visual relation detection. In CVPR . IEEE, 5."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.454"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.555"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683464"},{"key":"e_1_3_2_1_46_1","volume-title":"Thirty-Second AAAI Conference on Artificial Intelligence. AAAI.","author":"Zhu Yaohui","year":"2018","unstructured":"Yaohui Zhu and Shuqiang Jiang . 2018 . Deep structured learning for visual relationship detection . In Thirty-Second AAAI Conference on Artificial Intelligence. AAAI. Yaohui Zhu and Shuqiang Jiang. 2018. Deep structured learning for visual relationship detection. In Thirty-Second AAAI Conference on Artificial Intelligence. AAAI."},{"key":"e_1_3_2_1_47_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\/3343031.3351024","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3351024","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:13:11Z","timestamp":1750187591000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351024"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":47,"alternative-id":["10.1145\/3343031.3351024","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3351024","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"}}]}}