all AI news
From Movements to Metrics: Evaluating Explainable AI Methods in Skeleton-Based Human Activity Recognition
Feb. 21, 2024, 5:42 a.m. | Kimji N. Pellano, Inga Str\"umke, Espen Alexander F. Ihlen
cs.LG updates on arXiv.org arxiv.org
Abstract: The advancement of deep learning in human activity recognition (HAR) using 3D skeleton data is critical for applications in healthcare, security, sports, and human-computer interaction. This paper tackles a well-known gap in the field, which is the lack of testing in the applicability and reliability of XAI evaluation metrics in the skeleton-based HAR domain. We have tested established XAI metrics namely faithfulness and stability on Class Activation Mapping (CAM) and Gradient-weighted Class Activation Mapping (Grad-CAM) …
abstract advancement applications arxiv computer cs.lg data deep learning explainable ai gap healthcare human human-computer interaction metrics movements paper recognition security sports testing type
More from arxiv.org / cs.LG updates on arXiv.org
The Perception-Robustness Tradeoff in Deterministic Image Restoration
2 days, 18 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne