Data-efficient Alignment of Multimodal Sequences by Aligning Gradient Updates and Internal Feature Distributions
2021 IEEE Winter Conference on Applications of Computer Vision (WACV)(2021)
摘要
The task of video and text sequence alignment is a pre-requisite step toward joint understanding of movie videos and screenplays. However, supervised methods face the obstacle of limited realistic training data. With this pa-per, we attempt to enhance data efficiency of the end-to-end alignment network NeuMATCH [15]. Recent research [56] suggests that network components dealing with different moda...
更多查看译文
关键词
Training,Computer vision,Adaptive systems,Conferences,Training data,Motion pictures,Reservoirs
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要