Benchmarking Federated Few-Shot Learning for Video-Based Action Recognition

Few-shot action recognition aims to train a model to classify actions in videos using only a few examples, known as “shots,” per action class. This learning approach is particularly useful but challenging due to the limited availability of labeled video data in practice. Although signi...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Nguyen Anh Tu, Nartay Aikyn, Nursultan Makhanov, Assanali Abu, Kok-Seng Wong, Min-Ho Lee
Formato:	Artigo
Idioma:	Inglês
Publicado em:	IEEE 2024-01-01
Colecção:	IEEE Access
Assuntos:	Human action recognition few-shot learning federated learning representation learning few-shot action recognition
Acesso em linha:	https://ieeexplore.ieee.org/document/10804801/
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!