arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.08409cs.CLcs.CVcs.SDeess.AS
收藏

使用多模态基于注意力的视频特征的端到端视听场景感知对话

End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features

Mitsubishi Electric Research Laboratories (MERL)(三菱电机研究实验室(MERL));School of Interactive Computing, Georgia Tech(佐治亚理工学院交互计算学院)
Chiori Hori, Huda Alamri, Jue Wang, Gordon Wichern, Takaaki Hori, Anoop Cherian, Tim K. Marks, Vincent Cartillier, Raphael Gontijo Lopes, Abhishek Das, Irfan Es… 展开作者

Chiori Hori, Huda Alamri, Jue Wang, Gordon Wichern, Takaaki Hori, Anoop Cherian, Tim K. Marks, Vincent Cartillier, Raphael Gontijo Lopes, Abhishek Das, Irfan Essa, Dhruv Batra, Devi Parikh

摘要:

对话系统需要理解动态的视觉场景,以便与用户就周围的对象和事件进行对话。用于现实世界应用的场景感知对话系统可以通过集成来自多个研究领域的最新技术来开发,包括:端到端对话技术,其使用从对话数据训练的模型来生成系统响应;视觉问答(VQA)技术,其使用学习的图像特征来回答关于图像的问题;以及视频描述技术,其中使用多模态信息从视频生成描述/字幕。我们引入了一个新的关于人类行为视频的对话集。每个对话框都是一个类型化的对话,由两个Amazon Mechanical Turk(AMT)工作人员之间的10个问答(QA)对组成。总的来说,我们收集了大约9,000个视频的对话。使用这个用于视听场景感知对话(AVSD)的新数据集,我们训练了一个端到端会话模型,该模型在关于视频的对话中生成响应。我们的实验表明,使用多模态功能开发的多模态注意力为基础的视频描述,提高了质量的动态场景(视频)生成的对话。我们的数据集,模型代码和预训练模型将公开用于新的视频场景感知对话挑战。

英文摘要:

Dialog systems need to understand dynamic visual scenes in order to have conversations with users about the objects and events around them. Scene-aware dialog systems for real-world applications could be developed by integrating state-of-the-art technologies from multiple research areas, including: end-to-end dialog technologies, which generate system responses using models trained from dialog data; visual question answering (VQA) technologies, which answer questions about images using learned image features; and video description technologies, in which descriptions/captions are generated from videos using multimodal information. We introduce a new dataset of dialogs about videos of human behaviors. Each dialog is a typed conversation that consists of a sequence of 10 question-and-answer(QA) pairs between two Amazon Mechanical Turk (AMT) workers. In total, we collected dialogs on roughly 9,000 videos. Using this new dataset for Audio Visual Scene-aware dialog (AVSD), we trained an end-to-end conversation model that generates responses in a dialog about a video. Our experiments demonstrate that using multimodal features that were developed for multimodal attention-based video description enhances the quality of generated dialog about dynamic scenes (videos). Our dataset, model code and pretrained models will be publicly available for a new Video Scene-Aware Dialog challenge.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑