Accurate analysis of human movement is critical for tasks such as understanding body loading, identifying techniques for enhancing performance, and analysing activities. Computer vision based systems allow for non-invasive, unencumbered human movement analysis, and combined with advances in hardware capability enable the tracking and monitoring of people in the field, outside the strict confines of a laboratory. Athletes, patients and workers can be observed in their natural environment, leading to a more realistic understanding of their movements. Application domains vary from sports, health (walking gait) and well-being (injury detection) to entertainment (dancing analysis) and broadcasting (automatic annotation).
Dependable detection and tracking of human body parts, accurate body posture estimation, and analysis of changing facial expressions and hand gestures are examples of demanding tasks. The goal of this workshop is to provide a forum for researchers and professionals to share recent advances in employing computer vision technology for human movement analysis, and identify future directions.
We invite high-quality research papers and reports on best practices in the field of computer vision that address the following (and related) issues:
The Human Body & Face
Action and Gesture Recognition
Facial Expression and Emotion Recognition
Anthropometric Measurements Estimation
Gait Analysis
3D Body Reconstruction
2D/3D Human Pose Estimation
Head Pose Estimation
Facial Landmarks Tracking
Human Behavior Understanding
Data
Human-focussed datasets (human motion, human detection in various scenarios etc)
Human Analysis Fairness and Biases Privacy Preservation and Data Anonymization
First Person Vision for Human Behavior Understanding
Multi-modal Data Fusion for Human Analysis
Computational Issues in Human Analysis Architectures
Applications in Sports , Health and Other Scenarios
Physical rehabilitation and monitoring
Automated assessment of movements of infants and adults
Tools for remote physiological measurements
Visual Analysis of injuries and performance assessment
Activity recognition and event detection
Estimation of position and motion of cameras and participants
Spectator monitoring
Alternative sensing (Hyperspectral, Infrared, etc.)
Tactics analysis
Automatic narration and captioning
Augmented/virtual reality
Ethics and algorithms
Gait Analysis systems
Detection, Prediction of future injuries
Systems, Tools, and Hardware
Hardware design for computer vision methods for Human Motion Analysis, and
Systems and software tools for computer vision methods
Workshop Paper Submissions Deadline: 30th March 2023
Workshop Paper Author Notification: 20th Apr 2023
Camera Ready Paper Submission: 1st May 2023
The deadline for all submissions will close at 11:59PM Pacific Standard Time.
IEEE International Conference on Multimedia and Expo is coming to Brisbane, Australia from July 10 to 14, 2023
Submissions should be made through the following LINK.
(https://cmt3.research.microsoft.com/ICMEW2023)
The papers will have the following commonalities:
Length: Papers must be no longer than 6 pages, including all text, figures, and references.
Format: Workshop papers have the same format as regular papers. See the example paper under the General Information section below. However, they need not be double-blind.
Review: Reviews will be handled directly by the Workshop organizers.
Submission site: Papers must be submitted under the track for the appropriate Workshop. Submissions may be accompanied by up to 20 MB of supplemental material following the same guidelines as regular and special session papers.
Presentation guarantee: As with accepted Regular and Special Session papers, accepted Workshop papers must be registered by the author deadline and presented at the conference; otherwise they will not be included in IEEE Xplore.
A workshop paper is covered by a full-conference registration only.
For detailed instructions, please see the "General Information" section HERE.
Dr. Amit Gupta
CTO-VueMotion
Dr. Vinay Kaushik
AI R&D - VueMotion
Dr. Jeroen Vendrig
CTO- ProofTec
Dr Amit Gupta: Dr Amit Gupta is an experienced AI and Computer Vision Research Leader actively working on creating cutting edge computer vision algorithms and real-world AI products. His main work experience has been in Research and Management related to Artificial Intelligence (Machine Learning methods such as Deep Learning, Probabilistic Models) for computer vision applications. The algorithms he has developed cover a broad spectrum of topics such as sports and surveillance video data analytics, image & video compression, watermarking and data embedding in images. He is an inventor (or co-inventor) on more than 18 Aus/US patent applications. He is the co-founder of VueMotion - a human movement analysis company and founder DVIEW AI - a computer vision/intelligent data pipeline company. He has been on the advisory board for School of EE - UNSW and Vantage Circle and many other companies/organisations.
Dr Vinay Kaushik: Dr. Vinay Kaushik received his Ph.D. degree from the Indian Institute of Technology Delhi (IITD), India, in 2021. His doctorate entailed learning scene depth and camera ego-motion estimation for autonomous driving scenarios. His interests include computer vision, 3D reconstruction, computer graphics, human pose understanding, and machine learning. He has published and reviewed papers in IEEE journals and conferences on computer vision and recently organized a workshop at ICIP. At present, he is a Research Scientist in VueMotion/ DVIEW AI and has been working on developing algorithms for Computer Vision applications for human understanding and analysis for the past 2 years.
Dr Jeroen Vendrig: Dr Jeroen Vendrig has been working in vision AI for over 25 years, and received a PhD in video understanding from the Universiteit van Amsterdam. In 2003, he joined Canon's Sydney research lab (CiSRA) where he has been leading R&D in machine learning to enable AI applications for automatic surveillance and sports analysis, including the technology driving Canon's smart cameras. He's also led collaboration projects with several Australian universities. Currently, Jeroen is using vision AI for tracking anomalies in high value assets at ProofTec. Jeroen holds over 20 patents worldwide, and has published several academic papers on image/video understanding.
Dr. Amit Gupta
Dr. Jeroen Vendrig
hmaworkshop2023@dview.ai