New framework uses ontology and personalized memory for human activity recognition

Researchers have developed OntoAR-HAR, a novel framework for human activity recognition (HAR) that leverages ontology-guided agentic retrieval-augmented generation (RAG) and personalized memory. This approach decomposes classification into local decisions within a tree-structured activity ontology, combining static population knowledge with user-specific motion patterns. Experiments demonstrate that this hierarchical retrieval and personalized memory system achieves state-of-the-art performance across various LLM backbones and sensing modalities. AI

IMPACT This framework could improve the accuracy and personalization of AI systems that interpret human actions from sensor data.

RANK_REASON The cluster contains a research paper detailing a new framework for human activity recognition. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• CatalyzeX
• DagsHub
• Gotit.pub
• Hugging Face
• human activity recognition
• Influence Flower
• LLMs
• OntoAR-HAR
• retrieval-augmented generation
• ScienceCast

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →