|
|||||
|
|
| 基于Yes/No反馈的视觉问答方法 | |
| 引用本文： | 邓硙,汪剑鸣,金光浩.基于Yes/No反馈的视觉问答方法[J].模式识别与人工智能,2020,33(11):1043-1053. |
| 作者姓名： | 邓硙 汪剑鸣 金光浩 |
| 作者单位： | 1.天津工业大学 电子与信息工程学院 天津 300387; 2.天津工业大学 计算机科学与技术学院 天津 300387 |
| 基金项目： | 国家自然科学基金;中央高校基本科研业务费专项 |
| 摘 要： | 针对视觉问答任务中问题语句可能存在的歧义,文中提出基于Yes/No反馈的视觉问答方法,通过Yes/No的反馈机制判断模型第一次得出答案的正误.当用户给出的反馈信息为No时,重新解析该问题,生成多种消歧后的问题,产生不同的候选答案,输出最高置信度的答案作为最终结果.在CLEVR、CLEVR-CoGenT基准数据集上的实验表明文中方法精度较高. |
| 关 键 词： | 视觉问答 计算机视觉 自然语言处理 句法消歧 反馈 |
| 收稿时间： | 2020-03-18 |
Visual Question Answering Method Based on Yes/No Feedback |
|
| DENG Wei,WANG Jianming,JIN Guanghao.Visual Question Answering Method Based on Yes/No Feedback[J].Pattern Recognition and Artificial Intelligence,2020,33(11):1043-1053. | |
| Authors: | DENG Wei WANG Jianming JIN Guanghao |
| Affiliation: | 1. School of Electronics and Information Engineering,Tiangong University,Tianjin 300387; 2. School of Computer Science and Technology,Tiangong University,Tianjin 300387 |
| Abstract: | Aiming at the ambiguous question sentence in the visual question answering task,a visual question answering method based on Yes/No feedback is proposed.The Yes/No feedback mechanism is employed to determine whether or not the answer is correct for the first time.When the feedback given by the user is no,the question is re-analyzed,new questions are generated after disambiguation and different candidate answers are generated.The answer with the highest confidence is output as the final result.The experimental results on ClEVR,CLEVR-CoGen benchmark datasets show the proposed method achieves higher accuracy than the existing methods. |
| Keywords: | Visual Question Answering Computer Vision Natural Language Processing Syntactic Disambiguation Feedback |
| 本文献已被 万方数据 等数据库收录！ | |
| 点击此处可从《模式识别与人工智能》浏览原始摘要信息 | |
| 点击此处可从《模式识别与人工智能》下载全文 | |
