In the world of action recognition research, one primary focus has been on how to construct
and train networks to model the spatial-temporal volume of an input video. These methods …

Temporal modeling is key for action recognition in videos. It normally considers both short-
range motions and long-range aggregations. In this paper, we propose a Temporal …

We present a general and flexible video-level framework for learning action models in
videos. This method, called temporal segment network (TSN), aims to model long-range …

Recognizing actions in videos is not a trivial task because video is an information-intensive
media and includes multiple modalities. Moreover, on each modality, an action may only …

The state-of-the-arts in action recognition are suffering from three challenges:(1) How to
model spatial transformations of action since it is always geometric variation over time in …

Existing action recognition methods typically sample a few frames to represent each video to
avoid the enormous computation, which often limits the recognition performance. To tackle …

Recently, deep convolutional neural networks have demonstrated great effectiveness in
action recognition with both RGB and optical flow in the past decade. However, existing …

Efficient action recognition aims to classify a video clip into a specific action category with a
low computational cost. It is challenging since the integrated spatial-temporal calculation …

Temporal modelling is the key for efficient video action recognition. While understanding
temporal information can improve recognition accuracy for dynamic actions, removing …

Despite the success of deep learning for static image understanding, it remains unclear what
are the most effective network architectures for spatial-temporal modeling in videos. In this …