Fusing CNNs and attention-mechanisms to improve real-time indoor Human Activity Recognition for classifying home-based physical rehabilitation exercises

M Zaher, AS Ghoneim, L Abdelhamid, A Atia - Computers in Biology and …, 2025 - Elsevier
Physical rehabilitation plays a critical role in enhancing health outcomes globally. However,
the shortage of physiotherapists, particularly in develo** countries where the ratio is …

A late fusion framework with multiple optimization methods for media interestingness

M Shoukat, K Ahmad, N Said, N Ahmad… - arxiv preprint arxiv …, 2022 - arxiv.org
The recent advancement in Multimedia Analytical, Computer Vision (CV), and Artificial
Intelligence (AI) algorithms resulted in several interesting tools allowing an automatic …

[PDF][PDF] Media Interestingness Prediction in ImageCLEFfusion 2023 with Dense Architecture-based Ensemble & Scaled Gradient Boosting Regressor Model.

MIS Emon, MM Rahman - CLEF (Working Notes), 2023 - ceur-ws.org
The field of computer vision plays a key role in managing, processing, analyzing, and
interpreting multimedia data in diverse applications. Visual interestingness in multimedia …

[PDF][PDF] AIMultimediaLab at ImageCLEFfusion 2022: DeepFusion Methods for Ensembling in Diverse Scenarios.

MG Constantin, LD Stefan, M Dogariu… - CLEF (Working …, 2022 - researchgate.net
The ImageCLEFfusion task addresses the challenging task of creating ensembling schemes
and algorithms for fusing a large set of inducers in two particular scenarios: a regression …

[PDF][PDF] INDUCER SELECTION PRINCIPLES FOR DEEPFUSION SYSTEMS

MG CONSTANTIN, S Liviu-Daniel, BI TEFAN - gconstantin.aimultimedialab.ro
The current landscape of ensemble learning or late fusion approaches is dominated by
methods that employ a very low number of inducer systems, while using traditional …

[PDF][PDF] POLITEHNICA UNIVERSITY OF BUCHAREST

ELD STEFAN - docs.upb.ro
The era of big data presents an important challenge for data analysis, processing and
learning, as information become available in such a volume. In this context, images, video …