Spatiotemporal Residual Networks for Video Action Recognition

Abstract

Two-stream Convolutional Networks (ConvNets) have shown strong performance for human action recognition in videos. Recently, Residual Networks (ResNets) have arisen as a new technique to train extremely deep architectures. In this paper, we introduce spatiotemporal ResNets as a combination of these two approaches. Our novel architecture generalizes ResNets for the spatiotemporal domain by introducing residual connections in two ways. First, we inject residual connections between the appearance and motion pathways of a two-stream architecture to allow spatiotemporal interaction between the two streams. Second, we transform pretrained image ConvNets into spatiotemporal networks by equipping these with learnable convolutional filters that are initialized as temporal residual connections and operate on adjacent feature maps in time. This approach slowly increases the spatiotemporal receptive field as the depth of the model increases and naturally integrates image ConvNet design principles. The whole model is trained end-to-end to allow hierarchical learning of complex spatiotemporal features. We evaluate our novel spatiotemporal ResNet using two widely used action recognition benchmarks where it exceeds the previous state-of-the-art.

NIPS 2016

Cited by in corpus (8)

• Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
• Asymmetric Residual Neural Network for Accurate Human Activity Recognition
• Collaborative Spatio-temporal Feature Learning for Video Action Recognition
• Spatio-Temporal Fusion Networks for Action Recognition
• Hierarchical Feature Aggregation Networks for Video Action Recognition
• Human Action Recognition with Deep Temporal Pyramids
• Design Light-weight 3D Convolutional Networks for Video Recognition Temporal Residual, Fully Separable Block, and Fast Algorithm
• UniDual: A Unified Model for Image and Video Understanding