Enhanced Spatial Stream of Two-Stream Network Using Optical Flow for Human Action Recognition

Encoding Multi-resolution Two-Stream CNNs for Action Recognition

Two-Stream Convolutional Networks for Action Recognition in Videos

We investigate architectures of discriminatively trained deep Convolutional Networks (ConvNets) for action recognition in video. The challenge is to capture the complementary information on appearance from still frames and motion between frames. We also aim to generalise the best performing hand-crafted features within a data-driven learning framework. Our contribution is three-fold. First, we ...

Hidden Two-Stream Convolutional Networks for Action Recognition

Analyzing videos of human actions involves understanding the temporal relationships among video frames. CNNs are the current state-of-the-art methods for action recognition in videos. However, the CNN architectures currently being used have difficulty in capturing these relationships. State-of-the-art action recognition approaches rely on traditional local optical flow estimation methods to pre...

Two-Stream SR-CNNs for Action Recognition in Videos

Human action is a high-level concept in computer vision research and understanding it may benefit from different semantics, such as human pose, interacting objects, and scene context. In this paper, we explicitly exploit semantic cues with aid of existing human/object detectors for action recognition in videos, and thoroughly study their effect on the recognition performance for different types...

Two-Stream convolutional nets for action recognition in untrimmed video

We extend the two-stream convolutional net architecture developed by Simonyan for action recognition in untrimmed video clips. The main challenges of this project are first replicating the results of Simonyan et al, and then extending the pipeline to apply it to much longer video clips in which no actions of interest are taking place most of the time. We explore aspects of the performance of th...