{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T03:17:43Z","timestamp":1792034263384,"version":"4.4.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,10,15]],"date-time":"2018-10-15T00:00:00Z","timestamp":1539561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Engineering Research Center of Information Networks of MOE, China"},{"name":"NSFC","award":["61273365"],"award-info":[{"award-number":["61273365"]}]},{"name":"111 Project","award":["B08004"],"award-info":[{"award-number":["B08004"]}]},{"name":"NSSFC","award":["2016ZDA055"],"award-info":[{"award-number":["2016ZDA055"]}]},{"name":"Beijing Advanced Innovation Center for Imag- ing Technology"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,10,15]]},"DOI":"10.1145\/3240508.3240513","type":"proceedings-article","created":{"date-parts":[[2018,10,18]],"date-time":"2018-10-18T17:52:08Z","timestamp":1539885128000},"page":"519-527","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":50,"title":["Object-Difference Attention"],"prefix":"10.1145","author":[{"given":"Chenfei","family":"Wu","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinlai","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojie","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuan","family":"Dong","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2018,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Peter Anderson Xiaodong He Chris Buehler Damien Teney Mark Johnson Stephen Gould and Lei Zhang. 2017. Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering. arXiv preprint arXiv:1707.07998 (2017). arXiv:1707.07998.  Peter Anderson Xiaodong He Chris Buehler Damien Teney Mark Johnson Stephen Gould and Lei Zhang. 2017. Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering. arXiv preprint arXiv:1707.07998 (2017). arXiv:1707.07998."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Jacob Andreas Marcus Rohrbach Trevor Darrell and Dan Klein. 2016. Learning to Compose Neural Networks for Question Answering NAACL. 1545--1554.  Jacob Andreas Marcus Rohrbach Trevor Darrell and Dan Klein. 2016. Learning to Compose Neural Networks for Question Answering NAACL. 1545--1554.","DOI":"10.18653\/v1\/N16-1181"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Jacob Andreas Marcus Rohrbach Trevor Darrell and Dan Klein. 2016. Neural Module Networks. In CVPR. 39--48.  Jacob Andreas Marcus Rohrbach Trevor Darrell and Dan Klein. 2016. Neural Module Networks. In CVPR. 39--48.","DOI":"10.1109\/CVPR.2016.12"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_5_1","volume-title":"MUTAN: Multimodal Tucker Fusion for Visual Question Answering ICCV. 2631--2639.","author":"Hedi","year":"2017"},{"key":"e_1_3_2_1_6_1","unstructured":"Kan Chen Jiang Wang Liang-Chieh Chen Haoyuan Gao Wei Xu and Ram Nevatia. 2015. ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering. arXiv preprint arXiv:1511.05960 (2015).  Kan Chen Jiang Wang Liang-Chieh Chen Haoyuan Gao Wei Xu and Ram Nevatia. 2015. ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering. arXiv preprint arXiv:1511.05960 (2015)."},{"key":"e_1_3_2_1_7_1","unstructured":"Kyunghyun Cho Bart van Merrienboer Dzmitry Bahdanau and Yoshua Bengio. 2014. On the Properties of Neural Machine Translation: Encoder-Decoder Approaches. arXiv preprint arXiv:1409.1259 (2014). {arxiv:1409.1259  Kyunghyun Cho Bart van Merrienboer Dzmitry Bahdanau and Yoshua Bengio. 2014. On the Properties of Neural Machine Translation: Encoder-Decoder Approaches. arXiv preprint arXiv:1409.1259 (2014). {arxiv:1409.1259"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Akira Fukui Dong Huk Park Daylen Yang Anna Rohrbach Trevor Darrell and Marcus Rohrbach. 2016. Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding EMNLP. 457--468.  Akira Fukui Dong Huk Park Daylen Yang Anna Rohrbach Trevor Darrell and Marcus Rohrbach. 2016. Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding EMNLP. 457--468.","DOI":"10.18653\/v1\/D16-1044"},{"key":"e_1_3_2_1_9_1","unstructured":"Michael S. Gazzaniga Richard B. Ivry and George R. Mangun. 2013. Cognitive Neuroscience: The Biology of the Mind 4th Edition (bibinfoedition4th edition ed.). W. W. Norton & Company New York N.Y.  Michael S. Gazzaniga Richard B. Ivry and George R. Mangun. 2013. Cognitive Neuroscience: The Biology of the Mind 4th Edition (bibinfoedition4th edition ed.). W. W. Norton & Company New York N.Y."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_1_11_1","unstructured":"Ronghang Hu Jacob Andreas Marcus Rohrbach Trevor Darrell and Kate Saenko. 2017. Learning to Reason: End-to-End Module Networks for Visual Question Answering. arXiv preprint arXiv:1704.05526 (2017).  Ronghang Hu Jacob Andreas Marcus Rohrbach Trevor Darrell and Kate Saenko. 2017. Learning to Reason: End-to-End Module Networks for Visual Question Answering. arXiv preprint arXiv:1704.05526 (2017)."},{"key":"e_1_3_2_1_12_1","unstructured":"Ilija Ilievski and Jiashi Feng. 2017. Multimodal Learning and Reasoning for Visual Question Answering NIPS. 551--562.  Ilija Ilievski and Jiashi Feng. 2017. Multimodal Learning and Reasoning for Visual Question Answering NIPS. 551--562."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Kushal Kafle and Christopher Kanan. 2016. Answer-Type Prediction for Visual Question Answering CVPR. 4976--4984.  Kushal Kafle and Christopher Kanan. 2016. Answer-Type Prediction for Visual Question Answering CVPR. 4976--4984.","DOI":"10.1109\/CVPR.2016.538"},{"key":"e_1_3_2_1_14_1","unstructured":"Jin-Hwa Kim Kyoung-Woon On Jeonghee Kim Jung-Woo Ha and Byoung-Tak Zhang. 2017. Hadamard Product for Low-Rank Bilinear Pooling. In ICLR.  Jin-Hwa Kim Kyoung-Woon On Jeonghee Kim Jung-Woo Ha and Byoung-Tak Zhang. 2017. Hadamard Product for Low-Rank Bilinear Pooling. In ICLR."},{"key":"e_1_3_2_1_15_1","volume-title":"Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik","year":"2014"},{"key":"e_1_3_2_1_16_1","unstructured":"Ryan Kiros Yukun Zhu Ruslan R. Salakhutdinov Richard Zemel Raquel Urtasun Antonio Torralba and Sanja Fidler. 2015. Skip-Thought Vectors NIPS. 3294--3302.   Ryan Kiros Yukun Zhu Ruslan R. Salakhutdinov Richard Zemel Raquel Urtasun Antonio Torralba and Sanja Fidler. 2015. Skip-Thought Vectors NIPS. 3294--3302."},{"key":"e_1_3_2_1_17_1","unstructured":"Ruiyu Li and Jiaya Jia. 2016. Visual Question Answering with Question Representation Update (Qru) NIPS. 4655--4663.   Ruiyu Li and Jiaya Jia. 2016. Visual Question Answering with Question Representation Update (Qru) NIPS. 4655--4663."},{"key":"e_1_3_2_1_18_1","volume-title":"Microsoft Coco: Common Objects in Context. In ECCV. 740--755.","author":"Lin Tsung-Yi","year":"2014"},{"key":"e_1_3_2_1_19_1","volume-title":"Deepfashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations CVPR. 1096--1104.","author":"Liu Ziwei","year":"2016"},{"key":"e_1_3_2_1_20_1","unstructured":"Jiasen Lu Jianwei Yang Dhruv Batra and Devi Parikh. 2016. Hierarchical Question-Image Co-Attention for Visual Question Answering. In NIPS.   Jiasen Lu Jianwei Yang Dhruv Batra and Devi Parikh. 2016. Hierarchical Question-Image Co-Attention for Visual Question Answering. In NIPS."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Pan Lu Hongsheng Li Wei Zhang Jianyong Wang and Xiaogang Wang. 2018. Co-Attending Free-Form Regions and Detections with Multi-Modal Multiplicative Feature Embedding for Visual Question Answering AAAI. arxiv:1711.06794  Pan Lu Hongsheng Li Wei Zhang Jianyong Wang and Xiaogang Wang. 2018. Co-Attending Free-Form Regions and Detections with Multi-Modal Multiplicative Feature Embedding for Visual Question Answering AAAI. arxiv:1711.06794","DOI":"10.1609\/aaai.v32i1.12240"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Lin Ma Zhengdong Lu and Hang Li. 2016. Learning to Answer Questions from Image Using Convolutional Neural Network. AAAI (2016).   Lin Ma Zhengdong Lu and Hang Li. 2016. Learning to Answer Questions from Image Using Convolutional Neural Network. AAAI (2016).","DOI":"10.1609\/aaai.v30i1.10442"},{"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 NIPS. 1682--1690.   Mateusz Malinowski and Mario Fritz. 2014. A Multi-World Approach to Question Answering about Real-World Scenes Based on Uncertain Input NIPS. 1682--1690."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"e_1_3_2_1_25_1","unstructured":"Hyeonseob Nam Jung-Woo Ha and Jeonghee Kim. 2017. Dual Attention Networks for Multimodal Reasoning and Matching. CVPR (2017).  Hyeonseob Nam Jung-Woo Ha and Jeonghee Kim. 2017. Dual Attention Networks for Multimodal Reasoning and Matching. CVPR (2017)."},{"key":"e_1_3_2_1_26_1","unstructured":"Hyeonwoo Noh Paul Hongsuck Seo and Bohyung Han. 2016. Image Question Answering Using Convolutional Neural Network with Dynamic Parameter Prediction. CVPR (2016).  Hyeonwoo Noh Paul Hongsuck Seo and Bohyung Han. 2016. Image Question Answering Using Convolutional Neural Network with Dynamic Parameter Prediction. CVPR (2016)."},{"key":"e_1_3_2_1_27_1","unstructured":"Mengye Ren Ryan Kiros and Richard Zemel. 2015. Exploring Models and Data for Image Question Answering. In NIPS. 2953--2961.   Mengye Ren Ryan Kiros and Richard Zemel. 2015. Exploring Models and Data for Image Question Answering. In NIPS. 2953--2961."},{"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 NIPS. 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 NIPS. 91--99."},{"key":"e_1_3_2_1_29_1","unstructured":"Adam Santoro David Raposo David G. T. Barrett Mateusz Malinowski Razvan Pascanu Peter Battaglia and Timothy Lillicrap. 2017. A Simple Neural Network Module for Relational Reasoning. NIPS (2017).  Adam Santoro David Raposo David G. T. Barrett Mateusz Malinowski Razvan Pascanu Peter Battaglia and Timothy Lillicrap. 2017. A Simple Neural Network Module for Relational Reasoning. NIPS (2017)."},{"key":"e_1_3_2_1_30_1","unstructured":"Idan Schwartz Alexander G. Schwing and Tamir Hazan. 2017. High-Order Attention Models for Visual Question Answering. In NIPS. arXiv:1711.04323  Idan Schwartz Alexander G. Schwing and Tamir Hazan. 2017. High-Order Attention Models for Visual Question Answering. In NIPS. arXiv:1711.04323"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Kevin J. Shih Saurabh Singh and Derek Hoiem. 2016. Where to Look: Focus Regions for Visual Question Answering. CVPR (2016).  Kevin J. Shih Saurabh Singh and Derek Hoiem. 2016. Where to Look: Focus Regions for Visual Question Answering. CVPR (2016).","DOI":"10.1109\/CVPR.2016.499"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_1_33_1","unstructured":"Damien Teney Peter Anderson Xiaodong He and Anton van den Hengel. 2017. Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge. arXiv:1708.02711 {cs} (Aug. 2017). arXiv:cs\/1708.02711  Damien Teney Peter Anderson Xiaodong He and Anton van den Hengel. 2017. Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge. arXiv:1708.02711 {cs} (Aug. 2017). arXiv:cs\/1708.02711"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Huijuan Xu and Kate Saenko. 2016. Ask Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering. In ECCV. 451--466.  Huijuan Xu and Kate Saenko. 2016. Ask Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering. In ECCV. 451--466.","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Zichao Yang Xiaodong He Jianfeng Gao Li Deng and Alex Smola. 2016. Stacked Attention Networks for Image Question Answering CVPR.  Zichao Yang Xiaodong He Jianfeng Gao Li Deng and Alex Smola. 2016. Stacked Attention Networks for Image Question Answering CVPR.","DOI":"10.1109\/CVPR.2016.10"},{"key":"e_1_3_2_1_36_1","volume-title":"Multi-Modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering. ICCV 2017 (Aug.","author":"Yu Zhou","year":"2017"},{"key":"e_1_3_2_1_37_1","unstructured":"Yan Zhang Jonathon Hare and Adam Pr\u00fcgel-Bennett. 2018. Learning to Count Objects in Natural Images for Visual Question Answering. In arXiv:1802.05766 {Cs}. arXiv:cs\/1802.05766  Yan Zhang Jonathon Hare and Adam Pr\u00fcgel-Bennett. 2018. Learning to Count Objects in Natural Images for Visual Question Answering. In arXiv:1802.05766 {Cs}. arXiv:cs\/1802.05766"},{"key":"e_1_3_2_1_38_1","volume-title":"Structured Attentions for Visual Question Answering. ICCV 2017 (Aug. 2017","author":"Zhu Chen","year":"2017"}],"event":{"name":"MM '18: ACM Multimedia Conference","location":"Seoul Republic of Korea","acronym":"MM '18","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 26th ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3240508.3240513","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3240508.3240513","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:44:00Z","timestamp":1750207440000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3240508.3240513"}},"subtitle":["A Simple Relational Attention for Visual Question Answering"],"short-title":[],"issued":{"date-parts":[[2018,10,15]]},"references-count":38,"alternative-id":["10.1145\/3240508.3240513","10.1145\/3240508"],"URL":"https:\/\/doi.org\/10.1145\/3240508.3240513","relation":{},"subject":[],"published":{"date-parts":[[2018,10,15]]},"assertion":[{"value":"2018-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}