1 code implementation • 4 May 2023 • Zikang Leng, Hyeokhyen Kwon, Thomas Plötz
We benchmarked our approach on three HAR datasets (RealWorld, PAMAP2, and USC-HAD) and demonstrate that the use of virtual IMU training data generated using our new approach leads to significantly improved HAR model performance compared to only using real IMU data.
1 code implementation • 1 Feb 2024 • Zikang Leng, Amitrajit Bhattacharjee, Hrudhai Rajasekhar, Lizhe Zhang, Elizabeth Bruda, Hyeokhyen Kwon, Thomas Plötz
With the emergence of generative AI models such as large language models (LLMs) and text-driven motion synthesis models, language has become a promising source data modality as well as shown in proof of concepts such as IMUGPT.
no code implementations • 25 Dec 2013 • Sourav Bhattacharya, Petteri Nurmi, Nils Hammerla, Thomas Plötz
We propose a sparse-coding framework for activity recognition in ubiquitous and mobile computing that alleviates two fundamental problems of current supervised learning approaches.
no code implementations • 22 Feb 2022 • Harish Haresamudram, Irfan Essa, Thomas Plötz
As such, self-supervision, i. e., the paradigm of 'pretrain-then-finetune' has the potential to become a strong alternative to the predominant end-to-end training approaches, let alone hand-crafted features for the classic activity recognition chain.
no code implementations • 2 Nov 2022 • Zikang Leng, Yash Jain, Hyeokhyen Kwon, Thomas Plötz
In this work we first introduce a measure to quantitatively assess the subtlety of human movements that are underlying activities of interest--the motion subtlety index (MSI)--which captures local pixel movements and pose changes in the vicinity of target virtual sensor locations, and correlate it to the eventual activity recognition accuracy.
no code implementations • 18 Oct 2023 • Zikang Leng, Hyeokhyen Kwon, Thomas Plötz
In human activity recognition (HAR), the limited availability of annotated data presents a significant challenge.
no code implementations • 16 Nov 2023 • Srivatsa P, Thomas Plötz
To overcome this limitation, we propose a novel graph-guided neural network approach that performs activity recognition by learning explicit co-firing relationships between sensors.