| 包希港,周春来,肖克晶,覃飙.视觉问答任务的研究综述.软件学报,0,(0):0 |
| 视觉问答任务的研究综述 |
| A survey of datasets and algorithms for Visual Question Answering |
| 投稿时间：2020-07-09 修订日期：2020-10-02 |
| DOI：10.13328/j.cnki.jos.006215 |
| 中文关键词: 视觉问答 交叉方向 语言偏见 数据集分布 算法鲁棒性 |
| 英文关键词:visual question answering interdisciplinary direction language bias distribution of datasets robustness |
| 基金项目:国家自然科学基金（61772534）；国家重点自然科学基金（61732006） |
|
| 摘要点击次数: 179 |
| 全文下载次数: 129 |
| 中文摘要: |
| 视觉问答是计算机视觉领域和自然语言处理领域的交叉方向，近几年受到广泛关注.在视觉问答任务中，算法需要回答基于特定图片（或视频）的问题.自2014年第一个视觉问答数据集发布以来，若干大规模数据集在近5年内被陆续发布，并有大量算法在此基础上被提出.已有综述性研究重点针对视觉问答任务的发展进行了总结，但近年来，有研究发现视觉问答模型强烈依赖语言偏见和数据集的分布，特别是自VQA-CP数据集发布以来，许多模型的效果大幅下降，目前尚未有综述研究对其总结.本文主要详细介绍近年来提出的算法以及发布的数据集，特别是讨论了算法在加强鲁棒性方面的研究.本文对视觉问答任务的算法进行了分类总结，介绍了其动机、细节以及局限性.最后讨论了视觉问答任务的挑战及展望. |
| 英文摘要: |
| Visual Question Answering (VQA) is an interdisciplinary direction in the field of computer vision and natural language processing. It has received extensive attention in recent years. In the Visual Question Answering, the algorithm is required to answer questions based on specific pictures(or videos). Since the first visual question answering dataset was released in 2014, several large-scale datasets have been released in the past five yeHars, and a large number of algorithms have been proposed based on them. Existing research has focused on the development of visual question answering, but in recent years, visual question answering has been found to rely heavily on language bias and the distribution of datasets, especially since the release of the VQA-CP dataset, the accuracy of many models has been greatly reduced, there is no review research to summarize it. We mainly introduce the proposed algorithms and the released datasets in recent years, especially discuss the research of algorithms on strengthening the robustness. We summarize the algorithms of visual question answering and introduce their motivation, details, and limitations. Finally, the challenge and prospect of visual question answering are discussed. |
|
HTML 下载PDF全文 查看/发表评论 下载PDF阅读器 |
