Silhouette based View embeddings for Gait Recognition under Multiple Views
This work addresses gait recognition for computer vision applications, but it is incremental as it builds on existing convolutional neural network approaches.
The paper tackled the problem of gait recognition under multiple views by proposing a framework that embeds view information into existing architectures using a selective projection layer, achieving effective results on two large public datasets.
Gait recognition under multiple views is an important computer vision and pattern recognition task. In the emerging convolutional neural network based approaches, the information of view angle is ignored to some extent. Instead of direct view estimation and training view-specific recognition models, we propose a compatible framework that can embed view information into existing architectures of gait recognition. The embedding is simply achieved by a selective projection layer. Experimental results on two large public datasets show that the proposed framework is very effective.