The goal of this work is to understand the way actions are performed in
...
Humans excel at acquiring knowledge through observation. For example, we...
Precisely naming the action depicted in a video can be a challenging and...
Understanding the steps required to perform a task is an important skill...
We address the problem of data augmentation for video action recognition...
We address the problem of capturing temporal information for video
class...
Zero-shot action recognition is the task of classifying action categorie...
Prototype learning is extensively used for few-shot segmentation. Typica...
Zero-shot action recognition is the task of recognizing action classes
w...
Action recognition is computationally expensive. In this paper, we addre...
We consider the challenging problem of zero-shot video object segmentati...
This is the proceedings of the Computer Vision for Agriculture (CV4A)
Wo...
Understanding temporal information and how the visual world changes over...
Video classification methods often divide the video into short clips, do...
Motion has shown to be useful for video understanding, where motion is
t...
Most of the top performing action recognition methods use optical flow a...
The optical flow of natural scenes is a combination of the motion of the...
Existing optical flow methods make generic, spatially homogeneous,
assum...