{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:32:09Z","timestamp":1750221129405,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,6,5]],"date-time":"2019-06-05T00:00:00Z","timestamp":1559692800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"by Shaanxi province key research and development program","award":["2018ZDXM-GY-036"],"award-info":[{"award-number":["2018ZDXM-GY-036"]}]},{"name":"Shanghai Science and Technology Committee","award":["17511104202"],"award-info":[{"award-number":["17511104202"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,6,5]]},"DOI":"10.1145\/3323873.3325025","type":"proceedings-article","created":{"date-parts":[[2019,6,10]],"date-time":"2019-06-10T12:10:58Z","timestamp":1560168658000},"page":"68-72","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Relationship Detection Based on Object Semantic Inference and Attention Mechanisms"],"prefix":"10.1145","author":[{"given":"Liang","family":"Zhang","sequence":"first","affiliation":[{"name":"Xidian University, Shanghai BNC, Xi'an, Shaanxi, China"}]},{"given":"Shuai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, Shaanxi, China"}]},{"given":"Peiyi","family":"Shen","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, Shaanxi, China"}]},{"given":"Guangming","family":"Zhu","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, Shaanxi, China"}]},{"given":"Syed","family":"Afaq Ali Shah","sequence":"additional","affiliation":[{"name":"Murdoch University, Perth, Australia"}]},{"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[{"name":"University of Western Australia, Perth, Australia"}]}],"member":"320","published-online":{"date-parts":[[2019,6,5]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33786-4_32"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.352"},{"key":"e_1_3_2_1_3_1","volume-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"00","author":"Johnson J.","unstructured":"J. Johnson , R. Krishna , M. Stark , L. Li , D. A. Shamma , M. S. Bernstein , and L. Fei-Fei . 2015. Image retrieval using scene graphs . In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , Vol. 00 . 3668--3678. J. Johnson, R. Krishna, M. Stark, L. Li, D. A. Shamma, M. S. Bernstein, and L. Fei-Fei. 2015. Image retrieval using scene graphs. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Vol. 00. 3668--3678."},{"key":"e_1_3_2_1_4_1","volume-title":"Deep Visual-Semantic Alignments for Generating Image Descriptions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Karpathy Andrej","year":"2015","unstructured":"Andrej Karpathy and Li Fei-Fei . 2015 . Deep Visual-Semantic Alignments for Generating Image Descriptions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015), 3128--3137. Andrej Karpathy and Li Fei-Fei. 2015. Deep Visual-Semantic Alignments for Generating Image Descriptions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015), 3128--3137."},{"key":"e_1_3_2_1_5_1","volume-title":"Detecting Visual Relationships Using Box Attention. CoRR","author":"Kolesnikov Alexander","year":"2018","unstructured":"Alexander Kolesnikov , Christoph H. Lampert , and Vittorio Ferrari . 2018. Detecting Visual Relationships Using Box Attention. CoRR , Vol. abs\/ 1807 .02136 ( 2018 ). Alexander Kolesnikov, Christoph H. Lampert, and Vittorio Ferrari. 2018. Detecting Visual Relationships Using Box Attention. CoRR, Vol. abs\/1807.02136 (2018)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.766"},{"key":"e_1_3_2_1_8_1","volume-title":"Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation. CoRR","author":"Li Yikang","year":"2018","unstructured":"Yikang Li , Wanli Ouyang , Bolei Zhou , Yawen Cui , Jianping Shi , and Xiaogang Wang . 2018 . Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation. CoRR , Vol. abs\/ 1806 .11538 (2018). arxiv: 1806.11538 http:\/\/arxiv.org\/abs\/1806.11538 Yikang Li, Wanli Ouyang, Bolei Zhou, Yawen Cui, Jianping Shi, and Xiaogang Wang. 2018. Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation. CoRR, Vol. abs\/1806.11538 (2018). arxiv: 1806.11538 http:\/\/arxiv.org\/abs\/1806.11538"},{"key":"e_1_3_2_1_9_1","volume-title":"Phrases and Region Captions. Proceedings of the IEEE International Conference on Computer Vision","volume":"1279","author":"Li Yikang","year":"2017","unstructured":"Yikang Li , Wanli Ouyang , Bolei Zhou , Kun Wang , and Xiaogang Wang . 2017 b. Scene Graph Generation from Objects , Phrases and Region Captions. Proceedings of the IEEE International Conference on Computer Vision , Vol. 2017-Octob (2017), 1270-- 1279 . arxiv: 1707.09700 Yikang Li, Wanli Ouyang, Bolei Zhou, Kun Wang, and Xiaogang Wang. 2017b. Scene Graph Generation from Objects, Phrases and Region Captions. Proceedings of the IEEE International Conference on Computer Vision, Vol. 2017-Octob (2017), 1270--1279. arxiv: 1707.09700"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","volume":"1","author":"Liang Xiaodan","year":"2017","unstructured":"Xiaodan Liang , Lisa Lee , and Eric P. Xing . 2017. Deep variation-structured reinforcement learning for visual relationship and attribute detection . Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 , Vol. 2017-Janua, 1 ( 2017 ), 4408--4417. arxiv: 1703.03054 Xiaodan Liang, Lisa Lee, and Eric P. Xing. 2017. Deep variation-structured reinforcement learning for visual relationship and attribute detection. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Vol. 2017-Janua, 1 (2017), 4408--4417. arxiv: 1703.03054"},{"key":"e_1_3_2_1_11_1","volume-title":"Natural Language Guided Visual Relationship Detection. CoRR","author":"Liao Wentong","year":"2017","unstructured":"Wentong Liao , Shuai Lin , Bodo Rosenhahn , and Michael Ying Yang . 2017. Natural Language Guided Visual Relationship Detection. CoRR , Vol. abs\/ 1711 .06032 ( 2017 ). Wentong Liao, Shuai Lin, Bodo Rosenhahn, and Michael Ying Yang. 2017. Natural Language Guided Visual Relationship Detection. CoRR, Vol. abs\/1711.06032 (2017)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.340"},{"key":"e_1_3_2_1_13_1","volume-title":"Visual Relationship Detection with Language Priors. CoRR","author":"Lu Cewu","year":"2016","unstructured":"Cewu Lu , Ranjay Krishna , Michael S. Bernstein , and Fei-Fei Li. 2016. Visual Relationship Detection with Language Priors. CoRR , Vol. abs\/ 1608 .00187 ( 2016 ), 852--869. arxiv: 1608.00187 http:\/\/arxiv.org\/abs\/1608.00187 Cewu Lu, Ranjay Krishna, Michael S. Bernstein, and Fei-Fei Li. 2016. Visual Relationship Detection with Language Priors. CoRR, Vol. abs\/1608.00187 (2016), 852--869. arxiv: 1608.00187 http:\/\/arxiv.org\/abs\/1608.00187"},{"key":"e_1_3_2_1_14_1","volume-title":"Efficient Estimation of Word Representations in Vector Space. CoRR","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov , Kai Chen , Greg Corrado , and Jeffrey Dean . 2013. Efficient Estimation of Word Representations in Vector Space. CoRR , Vol. abs\/ 1301 .3781 ( 2013 ). arxiv: 1301.3781 http:\/\/arxiv.org\/abs\/1301.3781 Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. CoRR, Vol. abs\/1301.3781 (2013). arxiv: 1301.3781 http:\/\/arxiv.org\/abs\/1301.3781"},{"key":"e_1_3_2_1_15_1","unstructured":"Alejandro Newell and Jia Deng. 2017. Pixels to graphs by associative embedding. In Advances in neural information processing systems. 2171--2180.  Alejandro Newell and Jia Deng. 2017. Pixels to graphs by associative embedding. In Advances in neural information processing systems. 2171--2180."},{"key":"e_1_3_2_1_16_1","volume-title":"Manning","author":"Pennington Jeffrey","year":"2014","unstructured":"Jeffrey Pennington , Richard Socher , and Christopher D . Manning . 2014 . GloVe: Global Vectors for Word Representation. In Empirical Methods in Natural Language Processing (EMNLP) . 1532--1543. http:\/\/www.aclweb.org\/anthology\/D14--1162 Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. GloVe: Global Vectors for Word Representation. In Empirical Methods in Natural Language Processing (EMNLP). 1532--1543. http:\/\/www.aclweb.org\/anthology\/D14--1162"},{"key":"e_1_3_2_1_17_1","volume-title":"Detecting rare visual relations using analogies. arXiv 2018","author":"Peyre Julia","year":"2018","unstructured":"Julia Peyre , Ivan Laptev , and Cordelia Schmid . 2018. Detecting rare visual relations using analogies. arXiv 2018 ( 2018 ). arxiv: arXiv:1812.05736v1 Julia Peyre, Ivan Laptev, and Cordelia Schmid. 2018. Detecting rare visual relations using analogies. arXiv 2018 (2018). arxiv: arXiv:1812.05736v1"},{"key":"e_1_3_2_1_18_1","volume-title":"Visual Relationship Detection Based on Guided Proposals and Semantic Knowledge Distillation. (2018). arxiv","author":"Plesse Francc","year":"1805","unstructured":"Francc ois Plesse , Alexandru Ginsca , Bertrand Delezoide , and Francc oise Pr\u00ea teux. 2018. Visual Relationship Detection Based on Guided Proposals and Semantic Knowledge Distillation. (2018). arxiv : 1805 .10802 http:\/\/arxiv.org\/abs\/1805.10802 Francc ois Plesse, Alexandru Ginsca, Bertrand Delezoide, and Francc oise Pr\u00ea teux. 2018. Visual Relationship Detection Based on Guided Proposals and Semantic Knowledge Distillation. (2018). arxiv: 1805.10802 http:\/\/arxiv.org\/abs\/1805.10802"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298713"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_1_21_1","volume-title":"Nips","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N. Gomez , Lukasz Kaiser , and Illia Polosukhin . 2017. Attention Is All You Need. Nips ( 2017 ). arxiv: 1706.03762 Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. Nips (2017). arxiv: 1706.03762"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"e_1_3_2_1_23_1","volume-title":"Exploring Visual Relationship for Image Captioning. CoRR","author":"Yao Ting","year":"2018","unstructured":"Ting Yao , Yingwei Pan , Yehao Li , and Tao Mei . 2018. Exploring Visual Relationship for Image Captioning. CoRR , Vol. abs\/ 1809 .07041 ( 2018 ). arxiv: 1809.07041 http:\/\/arxiv.org\/abs\/1809.07041 Ting Yao, Yingwei Pan, Yehao Li, and Tao Mei. 2018. Exploring Visual Relationship for Image Captioning. CoRR, Vol. abs\/1809.07041 (2018). arxiv: 1809.07041 http:\/\/arxiv.org\/abs\/1809.07041"},{"key":"e_1_3_2_1_24_1","volume-title":"Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition","author":"Yin Guojun","year":"2018","unstructured":"Guojun Yin , Lu Sheng , Bin Liu , Nenghai Yu , Xiaogang Wang , Jing Shao , and Chen Change Loy . 2018. Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition ., Vol. 1 ( 2018 ). arxiv: 1807.04979 http:\/\/arxiv.org\/abs\/1807.04979 Guojun Yin, Lu Sheng, Bin Liu, Nenghai Yu, Xiaogang Wang, Jing Shao, and Chen Change Loy. 2018. Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition., Vol. 1 (2018). arxiv: 1807.04979 http:\/\/arxiv.org\/abs\/1807.04979"},{"key":"e_1_3_2_1_25_1","volume-title":"Neural Motifs: Scene Graph Parsing with Global Context. CoRR","author":"Zellers Rowan","year":"2017","unstructured":"Rowan Zellers , Mark Yatskar , Sam Thomson , and Yejin Choi . 2017 . Neural Motifs: Scene Graph Parsing with Global Context. CoRR , Vol. abs\/ 1711 .06640 (2017). arxiv: 1711.06640 http:\/\/arxiv.org\/abs\/1711.06640 Rowan Zellers, Mark Yatskar, Sam Thomson, and Yejin Choi. 2017. Neural Motifs: Scene Graph Parsing with Global Context. CoRR, Vol. abs\/1711.06640 (2017). arxiv: 1711.06640 http:\/\/arxiv.org\/abs\/1711.06640"},{"key":"e_1_3_2_1_26_1","volume-title":"Visual Translation Embedding Network for Visual Relation Detection. CoRR","author":"Zhang Hanwang","year":"2017","unstructured":"Hanwang Zhang , Zawlin Kyaw , Shih-Fu Chang , and Tat-Seng Chua . 2017. Visual Translation Embedding Network for Visual Relation Detection. CoRR , Vol. abs\/ 1702 .08319 ( 2017 ). arxiv: 1702.08319 http:\/\/arxiv.org\/abs\/1702.08319 Hanwang Zhang, Zawlin Kyaw, Shih-Fu Chang, and Tat-Seng Chua. 2017. Visual Translation Embedding Network for Visual Relation Detection. CoRR, Vol. abs\/1702.08319 (2017). arxiv: 1702.08319 http:\/\/arxiv.org\/abs\/1702.08319"}],"event":{"name":"ICMR '19: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"ICMR '19"},"container-title":["Proceedings of the 2019 on International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3323873.3325025","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3323873.3325025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:02:22Z","timestamp":1750208542000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3323873.3325025"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,5]]},"references-count":26,"alternative-id":["10.1145\/3323873.3325025","10.1145\/3323873"],"URL":"https:\/\/doi.org\/10.1145\/3323873.3325025","relation":{},"subject":[],"published":{"date-parts":[[2019,6,5]]},"assertion":[{"value":"2019-06-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}