{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T22:02:43Z","timestamp":1770069763124,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,10,19]],"date-time":"2017-10-19T00:00:00Z","timestamp":1508371200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Beijing Natural Science Foundation","award":["4152053"],"award-info":[{"award-number":["4152053"]}]},{"name":"National Natural Science Foundation of China","award":["61572503"],"award-info":[{"award-number":["61572503"]}]},{"name":"National Natural Science Foundation of China","award":["61572029"],"award-info":[{"award-number":["61572029"]}]},{"name":"National Natural Science Foundation of China","award":["61620106003"],"award-info":[{"award-number":["61620106003"]}]},{"name":"National Natural Science Foundation of China","award":["61432019"],"award-info":[{"award-number":["61432019"]}]},{"name":"Key Research Program of Frontier Sciences-CAS","award":["QYZDJ-SSW-JSC039"],"award-info":[{"award-number":["QYZDJ-SSW-JSC039"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,10,19]]},"DOI":"10.1145\/3123266.3123443","type":"proceedings-article","created":{"date-parts":[[2017,10,20]],"date-time":"2017-10-20T13:04:26Z","timestamp":1508504666000},"page":"411-419","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Multi-Modal Knowledge Representation Learning via Webly-Supervised Relationships Mining"],"prefix":"10.1145","author":[{"given":"Fudong","family":"Nian","sequence":"first","affiliation":[{"name":"Anhui University & Chinese Academy of Sciences, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing-Kun","family":"Bao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Teng","family":"Li","sequence":"additional","affiliation":[{"name":"Anhui University, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2017,10,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Melvin Johnson Premkumar, and Christopher D Manning","author":"Angeli Gabor","year":"2015","unstructured":"Gabor Angeli , Melvin Johnson Premkumar, and Christopher D Manning . 2015 . Leveraging linguistic structure for open domain information extraction Annual Meeting of the Association for Computational Linguistics . Gabor Angeli, Melvin Johnson Premkumar, and Christopher D Manning. 2015. Leveraging linguistic structure for open domain information extraction Annual Meeting of the Association for Computational Linguistics."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_38"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.3115\/1225403.1225421"},{"key":"e_1_3_2_1_4_1","unstructured":"Antoine Bordes Nicolas Usunier Alberto Garcia-Duran Jason Weston and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi-relational data 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 Advances in Neural Information Processing Systems. 2787--2795."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"e_1_3_2_1_6_1","volume-title":"Learning to Detect Human-Object Interactions. arXiv preprint arXiv:1702.05448","author":"Chao Yu-Wei","year":"2017","unstructured":"Yu-Wei Chao , Yunfan Liu , Xieyang Liu , Huayi Zeng , and Jia Deng . 2017. Learning to Detect Human-Object Interactions. arXiv preprint arXiv:1702.05448 ( 2017 ). Yu-Wei Chao, Yunfan Liu, Xieyang Liu, Huayi Zeng, and Jia Deng. 2017. Learning to Detect Human-Object Interactions. arXiv preprint arXiv:1702.05448 (2017)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.178"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Yongming Chen Liang Wang Wei Wang and Zhang Zhang. 2012. Continuum regression for cross-modal multimedia retrieval IEEE International Conference on Image Processing. 1949--1952.  Yongming Chen Liang Wang Wei Wang and Zhang Zhang. 2012. Continuum regression for cross-modal multimedia retrieval IEEE International Conference on Image Processing. 1949--1952.","DOI":"10.1109\/ICIP.2012.6467268"},{"key":"e_1_3_2_1_9_1","unstructured":"Douze. 2003. GIST descriptors. http:\/\/people.csail.mit.edu\/torralba\/code\/spatialenvelope\/. (2003).  Douze. 2003. GIST descriptors. http:\/\/people.csail.mit.edu\/torralba\/code\/spatialenvelope\/. (2003)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2527602"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Carolina Galleguillos Andrew Rabinovich and Serge Belongie. 2008. Object categorization using co-occurrence location and appearance IEEE Conference on Computer Vision and Pattern Recognition. 1--8.  Carolina Galleguillos Andrew Rabinovich and Serge Belongie. 2008. Object categorization using co-occurrence location and appearance IEEE Conference on Computer Vision and Pattern Recognition. 1--8.","DOI":"10.1109\/CVPR.2008.4587799"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-008-0140-x"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_16_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks Advances in neural information processing systems. 1097--1105.   Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks Advances in neural information processing systems. 1097--1105."},{"key":"e_1_3_2_1_17_1","volume-title":"ViP-CNN: A Visual Phrase Reasoning Convolutional Neural Network for Visual Relationship Detection. arXiv preprint arXiv:1702.07191","author":"Li Yikang","year":"2017","unstructured":"Yikang Li , Wanli Ouyang , and Xiaogang Wang . 2017. ViP-CNN: A Visual Phrase Reasoning Convolutional Neural Network for Visual Relationship Detection. arXiv preprint arXiv:1702.07191 ( 2017 ). Yikang Li, Wanli Ouyang, and Xiaogang Wang. 2017. ViP-CNN: A Visual Phrase Reasoning Convolutional Neural Network for Visual Relationship Detection. arXiv preprint arXiv:1702.07191 (2017)."},{"key":"e_1_3_2_1_18_1","unstructured":"Yankai Lin Zhiyuan Liu Maosong Sun Yang Liu and Xuan Zhu. 2015. Learning Entity and Relation Embeddings for Knowledge Graph Completion Association for the Advancement of Artificial Intelligence. 2181--2187.   Yankai Lin Zhiyuan Liu Maosong Sun Yang Liu and Xuan Zhu. 2015. Learning Entity and Relation Embeddings for Knowledge Graph Completion Association for the Advancement of Artificial Intelligence. 2181--2187."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Cewu Lu Ranjay Krishna Michael Bernstein and Li Fei-Fei. 2016. Visual relationship detection with language priors European Conference on Computer Vision. 852--869.  Cewu Lu Ranjay Krishna Michael Bernstein and Li Fei-Fei. 2016. Visual relationship detection with language priors European Conference on Computer Vision. 852--869.","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"e_1_3_2_1_21_1","volume-title":"Wordnet: An electronic lexical database.","author":"Miller George","year":"1998","unstructured":"George Miller and Christiane Fellbaum . 1998 . Wordnet: An electronic lexical database. (1998). George Miller and Christiane Fellbaum. 1998. Wordnet: An electronic lexical database. (1998)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2483592"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2049621"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Vignesh Ramanathan Congcong Li Jia Deng Wei Han Zhen Li Kunlong Gu Yang Song Samy Bengio Chuck Rossenberg and Li Fei-Fei. 2015. Learning semantic relationships for better action retrieval in images IEEE Conference on Computer Vision and Pattern Recognition. 1100--1109.  Vignesh Ramanathan Congcong Li Jia Deng Wei Han Zhen Li Kunlong Gu Yang Song Samy Bengio Chuck Rossenberg and Li Fei-Fei. 2015. Learning semantic relationships for better action retrieval in images IEEE Conference on Computer Vision and Pattern Recognition. 1100--1109.","DOI":"10.1109\/CVPR.2015.7298713"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.318"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995711"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Abhishek Sharma Abhishek Kumar Hal Daume and David W Jacobs. 2012. Generalized multiview analysis: A discriminative latent space IEEE Conference on Computer Vision and Pattern Recognition. 2160--2167.   Abhishek Sharma Abhishek Kumar Hal Daume and David W Jacobs. 2012. Generalized multiview analysis: A discriminative latent space IEEE Conference on Computer Vision and Pattern Recognition. 2160--2167.","DOI":"10.1109\/CVPR.2012.6247923"},{"key":"e_1_3_2_1_29_1","unstructured":"Nitish Srivastava and Ruslan R Salakhutdinov. 2012. Multimodal learning with deep boltzmann machines. Advances in neural information processing systems. 1967--2006.   Nitish Srivastava and Ruslan R Salakhutdinov. 2012. Multimodal learning with deep boltzmann machines. Advances in neural information processing systems. 1967--2006."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874029"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872427.2883041"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015349"},{"key":"e_1_3_2_1_33_1","volume-title":"Relations between two sets of variates: The bits of information provided by each variate in each set. Statistics & probability letters","author":"Theil Henri","year":"1988","unstructured":"Henri Theil and Ching-Fan Chung . 1988. Relations between two sets of variates: The bits of information provided by each variate in each set. Statistics & probability letters Vol. 6 , 3 ( 1988 ), 137--139. Henri Theil and Ching-Fan Chung. 1988. Relations between two sets of variates: The bits of information provided by each variate in each set. Statistics & probability letters Vol. 6, 3 (1988), 137--139."},{"key":"e_1_3_2_1_34_1","unstructured":"Zhen Wang Jianwen Zhang Jianlin Feng and Zheng Chen. 2014. Knowledge Graph Embedding by Translating on Hyperplanes Association for the Advancement of Artificial Intelligence. 1112--1119.   Zhen Wang Jianwen Zhang Jianlin Feng and Zheng Chen. 2014. Knowledge Graph Embedding by Translating on Hyperplanes Association for the Advancement of Artificial Intelligence. 1112--1119."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2519449"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502113"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2807418"},{"key":"e_1_3_2_1_38_1","unstructured":"Danfei Xu Yuke Zhu Christopher B Choy and Li Fei-Fei. 2017. Scene Graph Generation by Iterative Message Passing IEEE Conference on Computer Vision and Pattern Recognition.  Danfei Xu Yuke Zhu Christopher B Choy and Li Fei-Fei. 2017. Scene Graph Generation by Iterative Message Passing IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_39_1","volume-title":"Embedding entities and relations for learning and inference in knowledge bases. arXiv preprint arXiv:1412.6575","author":"Yang Bishan","year":"2014","unstructured":"Bishan Yang , Wen-tau Yih, Xiaodong He , Jianfeng Gao , and Li Deng . 2014. Embedding entities and relations for learning and inference in knowledge bases. arXiv preprint arXiv:1412.6575 ( 2014 ). Bishan Yang, Wen-tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. 2014. Embedding entities and relations for learning and inference in knowledge bases. arXiv preprint arXiv:1412.6575 (2014)."},{"key":"e_1_3_2_1_40_1","unstructured":"Daojian Zeng Kang Liu Siwei Lai Guangyou Zhou Jun Zhao and others. 2014. Relation Classification via Convolutional Deep Neural Network International Conference on Computational Linguistics. 2335--2344.  Daojian Zeng Kang Liu Siwei Lai Guangyou Zhou Jun Zhao and others. 2014. Relation Classification via Convolutional Deep Neural Network International Conference on Computational Linguistics. 2335--2344."},{"key":"e_1_3_2_1_41_1","volume-title":"Relation Classification via Recurrent Neural Network. Computer Science","author":"Zhang Dongxu","year":"2015","unstructured":"Dongxu Zhang and Dong Wang . 2015. Relation Classification via Recurrent Neural Network. Computer Science ( 2015 ). Dongxu Zhang and Dong Wang. 2015. Relation Classification via Recurrent Neural Network. Computer Science (2015)."},{"key":"e_1_3_2_1_42_1","volume-title":"Visual Translation Embedding Network for Visual Relation Detection IEEE Conference on Computer Vision and Pattern Recognition.","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 IEEE Conference on Computer Vision and Pattern Recognition. Hanwang Zhang, Zawlin Kyaw, Shih-Fu Chang, and Tat-Seng Chua. 2017. Visual Translation Embedding Network for Visual Relation Detection IEEE Conference on Computer Vision and Pattern Recognition."}],"event":{"name":"MM '17: ACM Multimedia Conference","location":"Mountain View California USA","acronym":"MM '17","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 25th ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3123266.3123443","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3123266.3123443","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:14:04Z","timestamp":1750212844000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3123266.3123443"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10,19]]},"references-count":42,"alternative-id":["10.1145\/3123266.3123443","10.1145\/3123266"],"URL":"https:\/\/doi.org\/10.1145\/3123266.3123443","relation":{},"subject":[],"published":{"date-parts":[[2017,10,19]]},"assertion":[{"value":"2017-10-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}