arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1504.01561cs.CVcs.MM
收藏

混合深度学习框架中时空线索的建模

Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification

Fudan University(复旦大学)

Zuxuan Wu, Xi Wang, Yu-Gang Jiang, Hao Ye, Xiangyang Xue

摘要:

根据内容语义对视频进行分类是具有广泛应用的重要问题。在本文中,我们提出了一种用于视频分类的混合深度学习框架,该框架能够对视频中的静态空间信息、短期运动以及长期时间线索进行建模。具体而言,空间和短期运动特征分别提取两个卷积神经网络(CNN)。然后,这两种基于CNN的特征被组合在一个正则化的特征融合网络中进行分类,该网络能够学习和利用特征关系来提高性能。此外,长短期记忆(LSTM)网络被应用于这两个特征之上,以进一步对较长期的时间线索进行建模。这项工作的主要贡献是混合学习框架,可以模拟视频数据的几个重要方面。我们还表明,(1)在正则化融合网络中结合空间和短期运动特征优于使用具有softmax层的CNN的直接分类和融合,以及(2)基于序列的LSTM与传统的分类策略高度互补,而不考虑时间帧顺序。广泛的实验进行了两个流行的和具有挑战性的基准,UCF-101人的行动和哥伦比亚消费者视频(CCV)。在这两个基准测试中,我们的框架实现了迄今为止最好的报告性能:UCF-101上的$91.3\%$和CCV上的$83.5\%$。

英文摘要:

Classifying videos according to content semantics is an important problem with a wide range of applications. In this paper, we propose a hybrid deep learning framework for video classification, which is able to model static spatial information, short-term motion, as well as long-term temporal clues in the videos. Specifically, the spatial and the short-term motion features are extracted separately by two Convolutional Neural Networks (CNN). These two types of CNN-based features are then combined in a regularized feature fusion network for classification, which is able to learn and utilize feature relationships for improved performance. In addition, Long Short Term Memory (LSTM) networks are applied on top of the two features to further model longer-term temporal clues. The main contribution of this work is the hybrid learning framework that can model several important aspects of the video data. We also show that (1) combining the spatial and the short-term motion features in the regularized fusion network is better than direct classification and fusion using the CNN with a softmax layer, and (2) the sequence-based LSTM is highly complementary to the traditional classification strategy without considering the temporal frame orders. Extensive experiments are conducted on two popular and challenging benchmarks, the UCF-101 Human Actions and the Columbia Consumer Videos (CCV). On both benchmarks, our framework achieves to-date the best reported performance: $91.3\%$ on the UCF-101 and $83.5\%$ on the CCV.

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。

↑