{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dual-attention-networks-for-multimodal","title":"Dual Attention Networks for Multimodal Reasoning and Matching","arxiv_id":"1611.00471","date":"2016-11-02","proceeding":"CVPR 2017 7","authors":["Hyeonseob Nam","Jung-Woo Ha","Jeonghee Kim"],"abstract":"We propose Dual Attention Networks (DANs) which jointly leverage visual and\ntextual attention mechanisms to capture fine-grained interplay between vision\nand language. DANs attend to specific regions in images and words in text\nthrough multiple steps and gather essential information from both modalities.\nBased on this framework, we introduce two types of DANs for multimodal\nreasoning and matching, respectively. The reasoning model allows visual and\ntextual attentions to steer each other during collaborative inference, which is\nuseful for tasks such as Visual Question Answering (VQA). In addition, the\nmatching model exploits the two attention mechanisms to estimate the similarity\nbetween images and sentences by focusing on their shared semantics. Our\nextensive experiments validate the effectiveness of DANs in combining vision\nand language, achieving the state-of-the-art performance on public benchmarks\nfor VQA and image-text matching.","url_abs":"http://arxiv.org/abs/1611.00471v2","url_pdf":"http://arxiv.org/pdf/1611.00471v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dual-attention-networks-for-multimodal","repo_url":"https://github.com/iammrhelo/pytorch-vqa-dan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"dual-attention-networks-for-multimodal","repo_url":"https://github.com/JunweiLiang/DualAttentionNetwork","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"collaborative-inference","task_name":"Collaborative Inference"},{"task_slug":"image-text-matching","task_name":"Image-text matching"},{"task_slug":"multimodal-reasoning","task_name":"Multimodal Reasoning"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"text-matching","task_name":"Text Matching"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-flickr30k-1k-test","task":"Image Retrieval","dataset":"Flickr30K 1K test","model":"DAN","rank_in_archive_order":12,"of":18,"metrics":{"R@1":"39.4","R@10":"79.1","R@5":"69.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v1-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v1 test-dev","model":"DAN (ResNet)","rank_in_archive_order":2,"of":7,"metrics":{"Accuracy":"64.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.00471","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}