{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T12:36:23Z","timestamp":1780058183075,"version":"3.54.0"},"publisher-location":"New York, NY, USA","reference-count":43,"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":"Beijing Natural Science Foundation","award":["4192059"],"award-info":[{"award-number":["4192059"]}]},{"name":"National Natural Science Foundation of China","award":["61872366, 61472422"],"award-info":[{"award-number":["61872366, 61472422"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3350993","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"1175-1183","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Erasing-based Attention Learning for Visual Question Answering"],"prefix":"10.1145","author":[{"given":"Fei","family":"Liu","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richang","family":"Hong","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanqing","family":"Lu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Beijing, 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":"International Conference on Computer Vision and Pattern Recognition (CVPR) .","author":"Agrawal Aishwarya","year":"2018"},{"key":"e_1_3_2_1_2_1","volume-title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering. In International Conference on Computer Vision and Pattern Recognition (CVPR) .","author":"Anderson Peter","year":"2018"},{"key":"e_1_3_2_1_3_1","volume-title":"VQA: Visual Question Answering. In International Conference on Computer Vision (ICCV) .","author":"Antol Stanislaw","year":"2015"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_2"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Jane Bromley Isabelle Guyon Yann LeCun Eduard S\"ackinger and Roopak Shah. 1994. Signature verification using a \"siamese\" time delay neural network. In Advances in neural information processing systems. 737--744.  Jane Bromley Isabelle Guyon Yann LeCun Eduard S\"ackinger and Roopak Shah. 1994. Signature verification using a \"siamese\" time delay neural network. In Advances in neural information processing systems. 737--744.","DOI":"10.1142\/9789812797926_0003"},{"key":"e_1_3_2_1_7_1","volume-title":"Abc-cnn: An attention based convolutional neural network for visual question answering. arXiv preprint arXiv:1511.05960","author":"Chen Kan","year":"2015"},{"key":"e_1_3_2_1_8_1","volume-title":"Daylen Yang, Anna Rohrbach, Trevor Darrell, and Marcus Rohrbach.","author":"Fukui Akira","year":"2016"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_1_10_1","unstructured":"Qibin Hou PengTao Jiang Yunchao Wei and Ming-Ming Cheng. 2018. Self-erasing network for integral object attention. In Advances in Neural Information Processing Systems. 547--557.  Qibin Hou PengTao Jiang Yunchao Wei and Ming-Ming Cheng. 2018. Self-erasing network for integral object attention. In Advances in Neural Information Processing Systems. 547--557."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00535"},{"key":"e_1_3_2_1_12_1","unstructured":"Yu Jiang Vivek Natarajan Xinlei Chen M. Rohrbach D. Batra and D. Parikh. 2018. Pythia v0.1: the winning entry to the vqa challenge 2018. arXiv:1807.09956 (2018).  Yu Jiang Vivek Natarajan Xinlei Chen M. Rohrbach D. Batra and D. Parikh. 2018. Pythia v0.1: the winning entry to the vqa challenge 2018. arXiv:1807.09956 (2018)."},{"key":"e_1_3_2_1_13_1","volume-title":"An Analysis of Visual Question Answering Algorithms. In International Conference on Computer Vision (ICCV) .","author":"Kafle Kushal","year":"2017"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.06.005"},{"key":"e_1_3_2_1_15_1","volume-title":"International Conference on Neural Information Processing Systems (NeurIPS) .","author":"Kim Jin-Hwa","year":"2018"},{"key":"e_1_3_2_1_16_1","unstructured":"Jin-Hwa Kim Sang-Woo Lee Donghyun Kwak Min-Oh Heo Jeonghee Kim Jung-Woo Ha and Byoung-Tak Zhang. 2016. Multimodal residual learning for visual qa. In Advances in neural information processing systems. 361--369.  Jin-Hwa Kim Sang-Woo Lee Donghyun Kwak Min-Oh Heo Jeonghee Kim Jung-Woo Ha and Byoung-Tak Zhang. 2016. Multimodal residual learning for visual qa. In Advances in neural information processing systems. 361--369."},{"key":"e_1_3_2_1_17_1","volume-title":"International Conference on Learning Representations (ICLR) .","author":"Kim Jin-Hwa","year":"2017"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.381"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_21_1","unstructured":"Jiasen Lu Jianwei Yang Dhruv Batra and Devi Parikh. 2016. Hierarchical question-image co-attention for visual question answering. In Advances In Neural Information Processing Systems. 289--297.  Jiasen Lu Jianwei Yang Dhruv Batra and Devi Parikh. 2016. Hierarchical question-image co-attention for visual question answering. In Advances In Neural Information Processing Systems. 289--297."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_1"},{"key":"e_1_3_2_1_23_1","unstructured":"Mateusz Malinowski and Mario Fritz. 2014. A multi-world approach to question answering about real-world scenes based on uncertain input. In Advances in neural information processing systems. 1682--1690.  Mateusz Malinowski and Mario Fritz. 2014. A multi-world approach to question answering about real-world scenes based on uncertain input. In Advances in neural information processing systems. 1682--1690."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_26_1","unstructured":"Sainandan Ramakrishnan Aishwarya Agrawal and Stefan Lee. 2018. Overcoming language priors in visual question answering with adversarial regularization. In Advances in Neural Information Processing Systems. 1541--1551.  Sainandan Ramakrishnan Aishwarya Agrawal and Stefan Lee. 2018. Overcoming language priors in visual question answering with adversarial regularization. In Advances in Neural Information Processing Systems. 1541--1551."},{"key":"e_1_3_2_1_27_1","volume-title":"On the Convergence of Adam and Beyond. In International Conference on Learning Representations (ICLR) .","author":"Reddi Sashank J.","year":"2018"},{"key":"e_1_3_2_1_28_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 Advances in neural information processing systems. 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. 91--99."},{"key":"e_1_3_2_1_29_1","unstructured":"Ruslan Salakhutdinov and Geoff Hinton. 2007. Learning a nonlinear embedding by preserving class neighbourhood structure. In Artificial Intelligence and Statistics. 412--419.  Ruslan Salakhutdinov and Geoff Hinton. 2007. Learning a nonlinear embedding by preserving class neighbourhood structure. In Artificial Intelligence and Statistics. 412--419."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_1_31_1","volume-title":"Question Type Guided Attention in Visual Question Answering. In European Conference on Computer Vision (ECCV) .","author":"Shi Yang","year":"2018"},{"key":"e_1_3_2_1_32_1","unstructured":"Kihyuk Sohn. 2016. Improved deep metric learning with multi-class n-pair loss objective. In Advances in Neural Information Processing Systems. 1857--1865.  Kihyuk Sohn. 2016. Improved deep metric learning with multi-class n-pair loss objective. In Advances in Neural Information Processing Systems. 1857--1865."},{"key":"e_1_3_2_1_33_1","volume-title":"Learning Visual Knowledge Memory Networks for Visual Question Answering. In International Conference on Computer Vision and Pattern Recognition (CVPR) .","author":"Su Zhou","year":"2018"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.180"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.324"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.131"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.687"},{"key":"e_1_3_2_1_38_1","volume-title":"Chain of Reasoning for Visual Question Answering. In International Conference on Neural Information Processing Systems (NeurIPS) .","author":"Wu Chenfei","year":"2018"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"e_1_3_2_1_41_1","volume-title":"Beyond Bilinear: Generalized Multi-modal Factorized High-order Pooling for Visual Question Answering","author":"Yu Zhou","year":"2018"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00144"},{"key":"e_1_3_2_1_43_1","volume-title":"International Conference on Learning Representations (ICLR) .","author":"Zhang Yan","year":"2018"}],"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\/3343031.3350993","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3350993","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:18Z","timestamp":1750201998000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350993"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":43,"alternative-id":["10.1145\/3343031.3350993","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3350993","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"}}]}}