Improved Dense Trajectory with Cross Streams

TL;DR

This paper introduces a novel local descriptor that combines appearance and motion streams through cross-network pooling, improving action recognition accuracy by emphasizing discriminative regions and reducing background noise.

Contribution

It proposes a new descriptor that pools convolutional layers from crossing two networks, enhancing the discriminative power for action recognition.

Findings

Achieved 92.3% accuracy on UCF101

Achieved 66.2% accuracy on HMDB51

Outperforms previous state-of-the-art methods

Abstract

Improved dense trajectories (iDT) have shown great performance in action recognition, and their combination with the two-stream approach has achieved state-of-the-art performance. It is, however, difficult for iDT to completely remove background trajectories from video with camera shaking. Trajectories in less discriminative regions should be given modest weights in order to create more discriminative local descriptors for action recognition. In addition, the two-stream approach, which learns appearance and motion information separately, cannot focus on motion in important regions when extracting features from spatial convolutional layers of the appearance network, and vice versa. In order to address the above mentioned problems, we propose a new local descriptor that pools a new convolutional layer obtained from crossing two networks along iDT. This new descriptor is calculated by applying discriminative weights learned from one network to a convolutional layer of the other network. Our method has achieved state-of-the-art performance on ordinal action recognition datasets, 92.3% on UCF101, and 66.2% on HMDB51.