Distilling Knowledge from CNN-Transformer Models for Enhanced Human Action Recognition

This paper presents a study on improving human action recognition through the utilization of knowledge distillation, and the combination of CNN and ViT models. The research aims to enhance the performance and efficiency of smaller student models by transferring knowledge from larger teacher models....

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Ahmadabadi, Hamid, Manzari, Omid Nejati, Ayatollahi, Ahmad
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!