3 citations · 21 across the 26 of their papers we have counts for
8 papers · 1 filter
PIM: Physics-Informed Multi-task Pre-training for Improving Inertial Sensor-Based Human Activity Recognition
Dominique Nshimyimana, Vitor Fortes Rey, Sungho Suh +2
Human activity recognition (HAR) with deep learning models relies on large amounts of labeled data, often challenging to obtain due to associated cost, time, and labor. Self-superv…
OV-HHIR: Open Vocabulary Human Interaction Recognition Using Cross-modal Integration of Large Language Models
Lala Shakti Swarup Ray, Bo Zhou, Sungho Suh +1
Understanding human-to-human interactions, especially in contexts like public security surveillance, is critical for monitoring and maintaining safety. Traditional activity recogni…
A Novel Local-Global Feature Fusion Framework for Body-weight Exercise Recognition with Pressure Mapping Sensors
Davinder Pal Singh, Lala Shakti Swarup Ray, Bo Zhou +2
We present a novel local-global feature fusion framework for body-weight exercise recognition with floor-based dynamic pressure maps. One step further from the existing studies usi…
PressureTransferNet: Human Attribute Guided Dynamic Ground Pressure Profile Transfer using 3D simulated Pressure Maps
Lala Shakti Swarup Ray, Vitor Fortes Rey, Bo Zhou +2
We propose PressureTransferNet, a novel method for Human Activity Recognition (HAR) using ground pressure information. Our approach generates body-specific dynamic ground pressure…
Selecting the motion ground truth for loose-fitting wearables: benchmarking optical MoCap methods
Lala Shakti Swarup Ray, Bo Zhou, Sungho Suh +1
To help smart wearable researchers choose the optimal ground truth methods for motion capturing (MoCap) for all types of loose garments, we present a benchmark, DrapeMoCapBench (DM…
A Synthetic Benchmarking Pipeline to Compare Camera Calibration Algorithms
Lala Shakti Swarup Ray, Bo Zhou, Lars Krupp +2
Accurate camera calibration is crucial for various computer vision applications. However, measuring calibration accuracy in the real world is challenging due to the lack of dataset…