{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:27:26Z","timestamp":1750220846668,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,11,3]],"date-time":"2019-11-03T00:00:00Z","timestamp":1572739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,11,3]]},"DOI":"10.1145\/3357384.3357987","type":"proceedings-article","created":{"date-parts":[[2019,11,4]],"date-time":"2019-11-04T14:11:35Z","timestamp":1572876695000},"page":"189-198","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Inferring Context from Pixels for Multimodal Image Classification"],"prefix":"10.1145","author":[{"given":"Manan","family":"Shah","sequence":"first","affiliation":[{"name":"Stanford University & Google Research, Stanford, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Krishnamurthy","family":"Viswanathan","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun-Ta","family":"Lu","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ariel","family":"Fuxman","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Li","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aleksei","family":"Timofeev","sequence":"additional","affiliation":[{"name":"Waymo, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Jia","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Sun","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,11,3]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"volume-title":"Return of the devil in the details: Delving deep into convolutional nets. arXiv preprint arXiv:1405.3531","year":"2014","author":"Chatfield Ken","key":"e_1_3_2_1_2_1"},{"volume-title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. CoRR","year":"2018","author":"Chen Liang-Chieh","key":"e_1_3_2_1_3_1"},{"volume-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. arXiv preprint arXiv:1606.00915","year":"2016","author":"Chen Liang-Chieh","key":"e_1_3_2_1_4_1"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Xinlei Chen and Abhinav Gupta. 2015. Webly supervised learning of convolutional networks. In ICCV .  Xinlei Chen and Abhinav Gupta. 2015. Webly supervised learning of convolutional networks. In ICCV .","DOI":"10.1109\/ICCV.2015.168"},{"volume-title":"Neil: Extracting visual knowledge from web data. In ICCV .","year":"2013","author":"Chen Xinlei","key":"e_1_3_2_1_6_1"},{"volume-title":"Xception: Deep Learning with Depthwise Separable Convolutions. arXiv:1610.02357","year":"2016","author":"Chollet Francois","key":"e_1_3_2_1_7_1"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Santosh Divvala Ali Farhadi and Carlos Guestrin. 2014. Learning Everything about Anything: Webly-Supervised Visual Concept Learning. In CVPR .  Santosh Divvala Ali Farhadi and Carlos Guestrin. 2014. Learning Everything about Anything: Webly-Supervised Visual Concept Learning. In CVPR .","DOI":"10.1109\/CVPR.2014.412"},{"volume-title":"End-to-End Retrieval in Continuous Space. In preparation","year":"2018","author":"Gillick Daniel","key":"e_1_3_2_1_9_1"},{"volume-title":"Rich feature hierarchies for accurate object detection and semantic segmentation. arXiv:1311.2524","year":"2013","author":"Girshick Ross B.","key":"e_1_3_2_1_10_1"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540120"},{"key":"e_1_3_2_1_12_1","unstructured":"Ruiqi Guo Sanjiv Kumar Krzysztof Choromanski and David Simcha. 2016. Quantization based fast inner product search. In Artificial Intelligence and Statistics . 482--490.  Ruiqi Guo Sanjiv Kumar Krzysztof Choromanski and David Simcha. 2016. Quantization based fast inner product search. In Artificial Intelligence and Statistics . 482--490."},{"key":"e_1_3_2_1_13_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR .  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR ."},{"volume-title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv:1704.04861","year":"2017","author":"Howard Andrew G.","key":"e_1_3_2_1_14_1"},{"key":"e_1_3_2_1_15_1","unstructured":"Baotian Hu Zhengdong Lu Hang Li and Qingcai Chen. 2014. Convolutional neural network architectures for matching natural language sentences. In NIPS .  Baotian Hu Zhengdong Lu Hang Li and Qingcai Chen. 2014. Convolutional neural network architectures for matching natural language sentences. In NIPS ."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Jonathan Huang Vivek Rathod Chen Sun Menglong Zhu Anoop Korattikara Alireza Fathi Ian Fischer Zbigniew Wojna Yang Song Sergio Guadarrama and Kevin Murphy. 2017. Speed\/accuracy trade-offs for modern convolutional object detectors. In CVPR .  Jonathan Huang Vivek Rathod Chen Sun Menglong Zhu Anoop Korattikara Alireza Fathi Ian Fischer Zbigniew Wojna Yang Song Sergio Guadarrama and Kevin Murphy. 2017. Speed\/accuracy trade-offs for modern convolutional object detectors. In CVPR .","DOI":"10.1109\/CVPR.2017.351"},{"volume-title":"Proceedings of ACL-ICJNLP .","author":"Jean S.","key":"e_1_3_2_1_17_1"},{"volume-title":"International Conference on Machine Learning . 2309--2318","year":"2018","author":"Jiang Lu","key":"e_1_3_2_1_18_1"},{"volume-title":"Graph-RISE: Graph-Regularized Image Semantic Embedding. (2019). arxiv","year":"1902","author":"Juan Da-Cheng","key":"e_1_3_2_1_19_1"},{"volume-title":"International Conference on Learning Representations .","year":"2017","author":"Kim Jin-Hwa","key":"e_1_3_2_1_20_1"},{"volume-title":"Hinton","year":"2012","author":"Krizhevsky Alex","key":"e_1_3_2_1_21_1"},{"volume-title":"et almbox","year":"2018","author":"Kuznetsova Alina","key":"e_1_3_2_1_22_1"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.483"},{"volume-title":"WebVision Database: Visual Learning and Understanding from Web Data. arXiv:1708.02862","year":"2017","author":"Li Wen","key":"e_1_3_2_1_24_1"},{"key":"e_1_3_2_1_25_1","unstructured":"Chenxi Liu Barret Zoph Jonathon Shlens Wei Hua Li-Jia Li Li Fei-Fei Alan L. Yuille Jonathan Huang and Kevin Murphy. 2018. Progressive Neural Architecture Search. In ECCV .  Chenxi Liu Barret Zoph Jonathon Shlens Wei Hua Li-Jia Li Li Fei-Fei Alan L. Yuille Jonathan Huang and Kevin Murphy. 2018. Progressive Neural Architecture Search. In ECCV ."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186071"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018716"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Dhruv Mahajan Ross B. Girshick Vignesh Ramanathan Kaiming He Manohar Paluri Yixuan Li Ashwin Bharambe and Laurens van der Maaten. 2018. Exploring the Limits of Weakly Supervised Pretraining. In ECCV .  Dhruv Mahajan Ross B. Girshick Vignesh Ramanathan Kaiming He Manohar Paluri Yixuan Li Ashwin Bharambe and Laurens van der Maaten. 2018. Exploring the Limits of Weakly Supervised Pretraining. In ECCV .","DOI":"10.1007\/978-3-030-01216-8_12"},{"volume-title":"Computer Vision--ECCV 2012","author":"Mensink Thomas","key":"e_1_3_2_1_29_1"},{"key":"e_1_3_2_1_30_1","unstructured":"Mark Palatucci Dean Pomerleau Geoffrey E Hinton and Tom M Mitchell. 2009. Zero-shot learning with semantic output codes. In Advances in neural information processing systems. 1410--1418.  Mark Palatucci Dean Pomerleau Geoffrey E Hinton and Tom M Mitchell. 2009. Zero-shot learning with semantic output codes. In Advances in neural information processing systems. 1410--1418."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1244"},{"volume-title":"Efficient Neural Architecture Search via Parameter Sharing. arXiv:1802.03268","year":"2018","author":"Pham Hieu","key":"e_1_3_2_1_32_1"},{"volume-title":"Learning Deep Representations of Fine-Grained Visual Descriptions. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) .","year":"2016","author":"Reed Scott","key":"e_1_3_2_1_33_1"},{"key":"e_1_3_2_1_34_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 NIPS .  Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In NIPS ."},{"volume-title":"ImageNet Large Scale Visual Recognition Challenge. arXiv:1409.0575","year":"2014","author":"Russakovsky Olga","key":"e_1_3_2_1_35_1"},{"volume-title":"Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation. arXiv:1801.04381","year":"2018","author":"Sandler Mark","key":"e_1_3_2_1_36_1"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0160"},{"volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv:1409.1556","year":"2014","author":"Simonyan Karen","key":"e_1_3_2_1_38_1"},{"key":"e_1_3_2_1_39_1","unstructured":"Jake Snell Kevin Swersky and Richard Zemel. 2017. Prototypical networks for few-shot learning. In Advances in Neural Information Processing Systems. 4077--4087.  Jake Snell Kevin Swersky and Richard Zemel. 2017. Prototypical networks for few-shot learning. In Advances in Neural Information Processing Systems. 4077--4087."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Chen Sun Abhinav Shrivastava Saurabh Singh and Abhinav Gupta. 2017. Revisiting Unreasonable Effectiveness of Data in Deep Learning Era. In ICCV .  Chen Sun Abhinav Shrivastava Saurabh Singh and Abhinav Gupta. 2017. Revisiting Unreasonable Effectiveness of Data in Deep Learning Era. In ICCV .","DOI":"10.1109\/ICCV.2017.97"},{"volume-title":"Inception-ResNet and the Impact of Residual Connections on Learning. arXiv:1602.07261","year":"2016","author":"Szegedy Christian","key":"e_1_3_2_1_41_1"},{"volume-title":"CVPR","author":"Szegedy Christian","key":"e_1_3_2_1_42_1"},{"volume-title":"Rethinking the inception architecture for computer vision. arXiv:1512.00567","year":"2015","author":"Szegedy Christian","key":"e_1_3_2_1_43_1"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.5555\/2018936.2018965"},{"volume-title":"The New Data and New Challenges in Multimedia Research. arXiv:1503.01817","year":"2015","author":"Thomee Bart","key":"e_1_3_2_1_45_1"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4121"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206816"},{"volume-title":"Sanjiv Kumar, Daniel N Holtmann-Rice, David Simcha, and Felix Yu.","year":"2017","author":"Wu Xiang","key":"e_1_3_2_1_48_1"},{"volume-title":"Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly","year":"2018","author":"Xian Yongqin","key":"e_1_3_2_1_49_1"},{"volume-title":"attend and tell: Neural image caption generation with visual attention. arXiv preprint arXiv:1502.03044","year":"2015","author":"Xu Kelvin","key":"e_1_3_2_1_50_1"},{"volume-title":"Image Captioning With Semantic Attention. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) .","year":"2016","author":"You Quanzeng","key":"e_1_3_2_1_51_1"},{"volume-title":"Le","year":"2016","author":"Zoph Barret","key":"e_1_3_2_1_52_1"}],"event":{"name":"CIKM '19: The 28th ACM International Conference on Information and Knowledge Management","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Beijing China","acronym":"CIKM '19"},"container-title":["Proceedings of the 28th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3357384.3357987","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3357384.3357987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:23:05Z","timestamp":1750202585000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3357384.3357987"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,3]]},"references-count":52,"alternative-id":["10.1145\/3357384.3357987","10.1145\/3357384"],"URL":"https:\/\/doi.org\/10.1145\/3357384.3357987","relation":{},"subject":[],"published":{"date-parts":[[2019,11,3]]},"assertion":[{"value":"2019-11-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}