用于视频问答的模块化混合注意力网络
Modular Blended Attention Network for Video Question Answering
AI总结：
本文提出一种可重用且可组合的神经单元，通过串联或并联连接并共享参数，简化多模态机器学习任务的网络构建，在视频问答任务中显著降低空间复杂度并取得优异性能。
摘要：
在多模态机器学习任务中，正是由于任务的复杂性，网络结构在大多数情况下是以复杂的方式组装的。根据模块设计所要实现的各自目标，整体架构可以划分为几个逻辑部分。随着信息表示模态数量的增加，构建处理不同模态数据的专用子网络，同时协调不同信息类型的融合，已成为一个繁琐且昂贵的问题。在本文中，我们提出了一种利用可重用和可组合神经单元来促进问题处理的方法；通过串联或并联连接这些单元，多模态机器学习任务中艰巨的网络构建将以更直接的方式完成。此外，通过单元间的参数共享（权重复制），空间复杂度将显著降低。我们在三个常用数据集上进行了实验；与几个视频QA基线相比，我们的方法取得了令人印象深刻的性能。
英文摘要：
In multimodal machine learning tasks, it is due to the complexity of the assignments that the network structure, in most cases, is assembled in a sophisticated way. The holistic architecture can be separated into several logical parts according to the respective ends that the modules are devised to achieve. As the number of modalities of information representation increases, constructing ad hoc subnetworks for processing the data from divergent modalities while mediating the fusion of different information types has become a cumbersome and expensive problem. In this paper, we present an approach to facilitate the question with a reusable and composable neural unit; by connecting the units in series or parallel, the arduous network constructing of multimodal machine learning tasks will be accomplished in a much straightforward way. Additionally, through parameter sharing (weights replication) among the units, the space complexity will be significantly reduced. We have conducted experiments on three commonly used datasets; our method achieves impressive performance compared to several video QA baselines.
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。
