ActAR: Actor-Driven Pose Embeddings for Video Action Recognition

by   Soufiane Lamghari, et al.

Human action recognition (HAR) in videos is one of the core tasks of video understanding. Based on video sequences, the goal is to recognize actions performed by humans. While HAR has received much attention in the visible spectrum, action recognition in infrared videos is little studied. Accurate recognition of human actions in the infrared domain is a highly challenging task because of the redundant and indistinguishable texture features present in the sequence. Furthermore, in some cases, challenges arise from the irrelevant information induced by the presence of multiple active persons not contributing to the actual action of interest. Therefore, most existing methods consider a standard paradigm that does not take into account these challenges, which is in some part due to the ambiguous definition of the recognition task in some cases. In this paper, we propose a new method that simultaneously learns to recognize efficiently human actions in the infrared spectrum, while automatically identifying the key-actors performing the action without using any prior knowledge or explicit annotations. Our method is composed of three stages. In the first stage, optical flow-based key-actor identification is performed. Then for each key-actor, we estimate key-poses that will guide the frame selection process. A scale-invariant encoding process along with embedded pose filtering are performed in order to enhance the quality of action representations. Experimental results on InfAR dataset show that our proposed model achieves promising recognition performance and learns useful action representations.


page 1

page 5


A Grid-based Representation for Human Action Recognition

Human action recognition (HAR) in videos is a fundamental research topic...

Pose from Action: Unsupervised Learning of Pose Features based on Motion

Human actions are comprised of a sequence of poses. This makes videos of...

Mimetics: Towards Understanding Human Actions Out of Context

Recent methods for video action recognition have reached outstanding per...

IndGIC: Supervised Action Recognition under Low Illumination

Technologies of human action recognition in the dark are gaining more an...

Prompt Learning for Action Recognition

We present a new general learning approach for action recognition, Promp...

Hand-Object Interaction and Precise Localization in Transitive Action Recognition

Action recognition in still images has seen major improvement in recent ...

Identifying Visible Actions in Lifestyle Vlogs

We consider the task of identifying human actions visible in online vide...

Please sign up or login with your details

Forgot password? Click here to reset