{"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/a-focused-dynamic-attention-model-for-visual","title":"A Focused Dynamic Attention Model for Visual Question Answering","arxiv_id":"1604.01485","date":"2016-04-06","proceeding":null,"authors":["Ilija Ilievski","Shuicheng Yan","Jiashi Feng"],"abstract":"Visual Question and Answering (VQA) problems are attracting increasing\ninterest from multiple research disciplines. Solving VQA problems requires\ntechniques from both computer vision for understanding the visual contents of a\npresented image or video, as well as the ones from natural language processing\nfor understanding semantics of the question and generating the answers.\nRegarding visual content modeling, most of existing VQA methods adopt the\nstrategy of extracting global features from the image or video, which\ninevitably fails in capturing fine-grained information such as spatial\nconfiguration of multiple objects. Extracting features from auto-generated\nregions -- as some region-based image recognition methods do -- cannot\nessentially address this problem and may introduce some overwhelming irrelevant\nfeatures with the question. In this work, we propose a novel Focused Dynamic\nAttention (FDA) model to provide better aligned image content representation\nwith proposed questions. Being aware of the key words in the question, FDA\nemploys off-the-shelf object detector to identify important regions and fuse\nthe information from the regions and global features via an LSTM unit. Such\nquestion-driven representations are then combined with question representation\nand fed into a reasoning unit for generating the answers. Extensive evaluation\non a large-scale benchmark dataset, VQA, clearly demonstrate the superior\nperformance of FDA over well-established baselines.","url_abs":"http://arxiv.org/abs/1604.01485v1","url_pdf":"http://arxiv.org/pdf/1604.01485v1.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":[],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"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":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-coco-visual-1","task":"Visual Question Answering (VQA)","dataset":"COCO Visual Question Answering (VQA) real images 1.0 multiple choice","model":"FDA","rank_in_archive_order":8,"of":10,"metrics":{"Percentage correct":"64.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-coco-visual-4","task":"Visual Question Answering (VQA)","dataset":"COCO Visual Question Answering (VQA) real images 1.0 open ended","model":"FDA","rank_in_archive_order":10,"of":14,"metrics":{"Percentage correct":"59.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1604.01485","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}