ACTION-Net: Multipath Excitation for Action Recognition

Spatial-temporal, channel-wise, and motion patterns are three complementary and crucial types of information for video action recognition. Conventional 2D CNNs are computationally cheap but cannot catch temporal relationships; 3D CNNs can achieve good performance but are computationally intensive. I...

Full description

Saved in:
Bibliographic Details
Main Authors: Wang, Zhengwei, She, Qi, Smolic, Aljosa
Format: Conference Proceeding
Language:English
Subjects:
Adaptation models
Codes
Computational modeling
Computer vision
Convolution
Target recognition
Three-dimensional displays
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!