Skip to search formSkip to main contentSkip to account menu

SUGAR: Learning Skeleton Representation with Visual-Motion Knowledge for Action Recognition

This paper introduces a novel paradigm named learning Skeleton representation with visUal-motion knowledGe for Action Recognition (SUGAR), and proposes to supervise skeleton learning through this prior knowledge to yield discrete representations.
arXiv (opens in a new tab)

YOLOX-B: A Better Yolox Model for Real-Time Driver Behavior Detection

A new model YOLOX-B is proposed, which introduces a serialized atrous spatial pyramid pooling structure (S-ASPP), obtains different sizes of receptive field information through serialized Atrous Convolution, solves the problem of information loss in max-pooling, and maximizes the efficiency of atrous convolution.
IEEE (opens in a new tab)

IFF-Net: I-Frame Fusion Network for Compressed Video Action Recognition

This work proposes a Time Domain Fusion (TDF) Module that can extract both low-frequency and high-frequency components from the video and integrate them seamlessly, resulting in the effective integration of abundant motion information into a single frame.
IEEE (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)