RAG-HAR: Retrieval Augmented Generation-based Human Activity Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sivaroopan, Nirhoshan, Karunarathna, Hansi, Madarasingha, Chamara, Jayasumana, Anura, Thilakarathna, Kanchana
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914546935922688
author Sivaroopan, Nirhoshan
Karunarathna, Hansi
Madarasingha, Chamara
Jayasumana, Anura
Thilakarathna, Kanchana
author_facet Sivaroopan, Nirhoshan
Karunarathna, Hansi
Madarasingha, Chamara
Jayasumana, Anura
Thilakarathna, Kanchana
contents Human Activity Recognition (HAR) underpins applications in healthcare, rehabilitation, fitness tracking, and smart environments, yet existing deep learning approaches demand dataset-specific training, large labeled corpora, and significant computational resources.We introduce RAG-HAR, a training-free retrieval-augmented framework that leverages large language models (LLMs) for HAR. RAG-HAR computes lightweight statistical descriptors, retrieves semantically similar samples from a vector database, and uses this contextual evidence to make LLM-based activity identification. We further enhance RAG-HAR by first applying prompt optimization and introducing an LLM-based activity descriptor that generates context-enriched vector databases for delivering accurate and highly relevant contextual information. Along with these mechanisms, RAG-HAR achieves state-of-the-art performance across six diverse HAR benchmarks. Most importantly, RAG-HAR attains these improvements without requiring model training or fine-tuning, emphasizing its robustness and practical applicability. RAG-HAR moves beyond known behaviors, enabling the recognition and meaningful labelling of multiple unseen human activities.
format Preprint
id arxiv_https___arxiv_org_abs_2512_08984
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RAG-HAR: Retrieval Augmented Generation-based Human Activity Recognition
Sivaroopan, Nirhoshan
Karunarathna, Hansi
Madarasingha, Chamara
Jayasumana, Anura
Thilakarathna, Kanchana
Computer Vision and Pattern Recognition
Artificial Intelligence
Human Activity Recognition (HAR) underpins applications in healthcare, rehabilitation, fitness tracking, and smart environments, yet existing deep learning approaches demand dataset-specific training, large labeled corpora, and significant computational resources.We introduce RAG-HAR, a training-free retrieval-augmented framework that leverages large language models (LLMs) for HAR. RAG-HAR computes lightweight statistical descriptors, retrieves semantically similar samples from a vector database, and uses this contextual evidence to make LLM-based activity identification. We further enhance RAG-HAR by first applying prompt optimization and introducing an LLM-based activity descriptor that generates context-enriched vector databases for delivering accurate and highly relevant contextual information. Along with these mechanisms, RAG-HAR achieves state-of-the-art performance across six diverse HAR benchmarks. Most importantly, RAG-HAR attains these improvements without requiring model training or fine-tuning, emphasizing its robustness and practical applicability. RAG-HAR moves beyond known behaviors, enabling the recognition and meaningful labelling of multiple unseen human activities.
title RAG-HAR: Retrieval Augmented Generation-based Human Activity Recognition
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2512.08984