Related papers: STH: Spatio-Temporal Hybrid Convolution for Effici…

The modeling, computational cost, and accuracy of traditional Spatio-temporal networks are the three most concentrated research topics in video action recognition. The traditional 2D convolution has a low computational cost, but it cannot…

Spatiotemporal and motion features are two complementary and crucial information for video action recognition. Recent state-of-the-art methods adopt a 3D CNN stream to learn spatiotemporal features and another flow stream to learn motion…

Despite the success of deep learning for static image understanding, it remains unclear what are the most effective network architectures for the spatial-temporal modeling in videos. In this paper, in contrast to the existing CNN+RNN or…

The video based CNN works have focused on effective ways to fuse appearance and motion networks, but they typically lack utilizing temporal information over video frames. In this work, we present a novel spatio-temporal fusion network…

The work in this paper is driven by the question if spatio-temporal correlations are enough for 3D convolutional neural networks (CNN)? Most of the traditional 3D networks use local spatio-temporal features. We introduce a new block that…

Effective processing of video input is essential for the recognition of temporally varying events such as human actions. Motivated by the often distinctive temporal characteristics of actions in either horizontal or vertical direction, we…

Spatio-temporal prediction is a pivotal task with broad applications in traffic management, climate monitoring, energy scheduling, etc. However, existing methodologies often struggle to balance model expressiveness and computational…

This paper studies how to introduce viewpoint-invariant feature representations that can help action recognition and detection. Although we have witnessed great progress of action recognition in the past decade, it remains challenging yet…

Skeleton-based action recognition relies on the extraction of spatial-temporal topological information. Hypergraphs can establish prior unnatural dependencies for the skeleton. However, the existing methods only focus on the construction of…

Skeleton-based Human Activity Recognition has achieved great interest in recent years as skeleton data has demonstrated being robust to illumination changes, body scales, dynamic camera views, and complex background. In particular,…

Spatio-temporal feature learning is of central importance for action recognition in videos. Existing deep neural network models either learn spatial and temporal features independently (C2D) or jointly with unconstrained parameters (C3D).…

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…

Spiking Neural Networks (SNNs), as one of the algorithmic models in neuromorphic computing, have gained a great deal of research attention owing to temporal information processing capability, low power consumption, and high biological…

3D CNN shows its strong ability in learning spatiotemporal representation in recent video recognition tasks. However, inflating 2D convolution to 3D inevitably introduces additional computational costs, making it cumbersome in practical…

This paper studies introducing viewpoint invariant feature representations in existing action recognition architecture. Despite significant progress in action recognition, efficiently handling geometric variations in large-scale datasets…

Image pre-training, the current de-facto paradigm for a wide range of visual tasks, is generally less favored in the field of video recognition. By contrast, a common strategy is to directly train with spatiotemporal convolutional neural…

Skeleton-based human action recognition has achieved a great interest in recent years, as skeleton data has been demonstrated to be robust to illumination changes, body scales, dynamic camera views, and complex background. Nevertheless, an…

Dynamics of human body skeletons convey significant information for human action recognition. Conventional approaches for modeling skeletons usually rely on hand-crafted parts or traversal rules, thus resulting in limited expressive power…

Temporal reasoning is an important aspect of video analysis. 3D CNN shows good performance by exploring spatial-temporal features jointly in an unconstrained way, but it also increases the computational cost a lot. Previous works try to…

With the rapid development of digital multimedia, video understanding has become an important field. For action recognition, temporal dimension plays an important role, and this is quite different from image recognition. In order to learn…