Youngjune Gwon, William Campbell, Kevin Brady, Douglas Sturim, Miriam Cha...
TL;DR本文介绍一种多模态稀疏编码的方法，用于学习多模态共享的特征表示，应用于多媒体事件检测，与其他特征学习方法进行比较，通过TRECVID MED 2014数据集的交叉验证分类准确性和平均精度来评估单模态和多模态设置下的特征学习。
Abstract
unsupervised feature learning methods have proven effective for classification tasks based on a single modality. We present multimodal sparse coding for learning feature representations shared across multiple mod