Knowledge Commons of Institute of Automation,CAS
Dual Hierarchical Temporal Convolutional Network with QA-Aware Dynamic Normalization for Video Story Question Answering | |
Liu, Fei1,2; Liu, Jing1,2; Zhu, Xinxin1; Hong, Richang3; Lu, Hanqing1,2 | |
2020-10 | |
会议名称 | Proceedings of the 28th ACM International Conference on Multimedia |
会议日期 | 2020-10 |
会议地点 | 线上 |
出版者 | ACM |
摘要 | Video story question answering (video story QA) is a challenging problem, as it requires a joint understanding of diverse data sources (i.e., video, subtitle, question, and answer choices). Existing approaches for video story QA have several common defects: (1) single temporal scale; (2) static and rough multimodal interaction; and (3) insufficient (or shallow) exploitation of both question and answer choices. In this paper, we propose a novel framework named Dual Hierarchical Temporal Convolutional Network (DHTCN) to address the aforementioned defects together. The proposed DHTCN explores multiple temporal scales by building hierarchical temporal convolutional network. In each temporal convolutional layer, two key components, namely AttLSTM and QA-Aware Dynamic Normalization, are introduced to capture the temporal dependency and the multimodal interaction in a dynamic and fine-grained manner. To enable sufficient exploitation of both question and answer choices, we increase the depth of QA pairs with a stack of nonlinear layers, and exploit QA pairs in each layer of the network. Extensive experiments are conducted on two widely used datasets: TVQA and MovieQA, demonstrating the effectiveness of DHTCN. Our model obtains state-of-the-art results on the both datasets. |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48671 |
专题 | 紫东太初大模型研究中心_图像与视频分析 |
通讯作者 | Liu, Jing |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.School of Computer and Information, Hefei University of Technology |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Liu, Fei,Liu, Jing,Zhu, Xinxin,et al. Dual Hierarchical Temporal Convolutional Network with QA-Aware Dynamic Normalization for Video Story Question Answering[C]:ACM,2020. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
3394171.3413649.pdf(2797KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论