L2cs-net: Fine-grained gaze estimation in unconstrained environments

AA Abdelrahman, T Hempel, A Khalifa… - … on Frontiers of …, 2023 - ieeexplore.ieee.org
Human gaze is a crucial cue used in various applications such as human-robot interaction
and virtual reality. Recently, convolution neural network (CNN) approaches have made …

NITEC: Versatile Hand-Annotated Eye Contact Dataset for Ego-Vision Interaction

T Hempel, M Jung, AA Abdelrahman… - Proceedings of the …, 2024 - openaccess.thecvf.com
Eye contact is a crucial non-verbal interaction modality and plays an important role in our
everyday social life. While humans are very sensitive to eye contact, the capabilities of …

TCA-NET: Triplet Concatenated-Attentional Network For Multimodal Engagement Estimation

H He, D Wang, MR Hasan, T Gedeon… - … Conference on Image …, 2024 - ieeexplore.ieee.org
Human social interactions involve intricate social signals that artificial intelligence and
machine learning models aim to decipher, particularly in the context of artificial mediators …

Fine-grained gaze estimation based on the combination of regression and classification losses

AA Abdelrahman, T Hempel, A Khalifa, A Al-Hamadi - Applied Intelligence, 2024 - Springer
Human gaze is a crucial cue used in various applications such as human-robot interaction,
autonomous driving, and virtual reality. Recently, convolution neural network (CNN) …

Predicting Human Intent to Interact with a Public Robot: The People Approaching Robots Database (PAR-D)

S Thompson, A Lew, Y Li, E Stanish, A Huang… - Proceedings of the 26th …, 2024 - dl.acm.org
This work studies the problem of predicting human intent to interact with a robot in a public
environment. To facilitate research in this problem domain, we first contribute the People …

Novel Subject-Dependent Human-Posture Recognition Approach Using Tensor Regression

K Yan, G Liu, R **e, SH Fang, HC Wu… - IEEE Sensors …, 2024 - ieeexplore.ieee.org
A novel dynamic human-posture recognition approach using tensor regression is proposed
in this work. In our proposed approach, a new dynamic segmentation scheme based on …

[HTML][HTML] Multiuser design of an architecture for social robots in education: teachers, students, and researchers perspectives

DC Tozadore, RAF Romero - Frontiers in Robotics and AI, 2024 - pmc.ncbi.nlm.nih.gov
Research on social assistive robots in education faces many challenges that extend beyond
technical issues. On one hand, hardware and software limitations, such as algorithm …

Multi-Pose Human Action Recognition Using Deep Learning ConvLSTM

V Sharma, U Shandilya, D Mishra - 2024 12th European …, 2024 - ieeexplore.ieee.org
Multi-pose Human action recognition (HAR) is a pivotal task in computer vision with
applications spanning surveillance, human-robot interaction (HRI), behaviour analysis, etc …

A Multimodal Dataset for Enhancing Industrial Task Monitoring and Engagement Prediction

NK Mehta, H Kumar, A Banerjee, S Saurav… - arxiv preprint arxiv …, 2025 - arxiv.org
Detecting and interpreting operator actions, engagement, and object interactions in dynamic
industrial workflows remains a significant challenge in human-robot collaboration research …

Prediction Models of Collaborative Behaviors in Dyadic Interactions: An Application for Inclusive Teamwork Training in Virtual Environments

AZ Amat, A Plunk, D Adiani, DM Wilkes, N Sarkar - Signals, 2024 - mdpi.com
Collaborative virtual environment (CVE)-based teamwork training offers a promising avenue
for inclusive teamwork training. The incorporation of a feedback mechanism within virtual …