2026
PAD-Hand: Physics-Aware Diffusion for Hand Motion Recovery
Elkhan Ismayilzada, Yufei Zhang, Zijun Cui
Computer Vision and Pattern Recognition (CVPR) 2026 Highlight
We propose a novel physics-aware conditional diffusion framework that refines noisy pose sequences into physically plausible hand motion while estimating the physics variance in motion estimates. .
PAD-Hand: Physics-Aware Diffusion for Hand Motion Recovery
Elkhan Ismayilzada, Yufei Zhang, Zijun Cui
Computer Vision and Pattern Recognition (CVPR) 2026 Highlight
We propose a novel physics-aware conditional diffusion framework that refines noisy pose sequences into physically plausible hand motion while estimating the physics variance in motion estimates. .
2025
QORT-Former: Query-optimized Real-time Transformer for Understanding Two Hands Manipulating Objects
Elkhan Ismayilzada*, MD Khalequzzaman Chowdhury Sayem*, Yihalem Yimolal Tiruneh, Mubarrat Tajoar Chowdhury, Muhammadjon Boboev, Seungryul Baek (* equal contribution)
Association for the Advancement of Artificial Intelligence (AAAI) 2025
We present a query-optimized real-time Transformer (QORT-Former), the first Transformer-based real-time framework for 3D pose estimation of two hands and an object.
QORT-Former: Query-optimized Real-time Transformer for Understanding Two Hands Manipulating Objects
Elkhan Ismayilzada*, MD Khalequzzaman Chowdhury Sayem*, Yihalem Yimolal Tiruneh, Mubarrat Tajoar Chowdhury, Muhammadjon Boboev, Seungryul Baek (* equal contribution)
Association for the Advancement of Artificial Intelligence (AAAI) 2025
We present a query-optimized real-time Transformer (QORT-Former), the first Transformer-based real-time framework for 3D pose estimation of two hands and an object.
2023
Poracle: Testing Patches Under Preservation Conditions to Combat the Overfitting Problem of Program Repair
Elkhan Ismayilzada, Md Mazba Ur Rahman, Dongsun Kim, Jooyong Yi
ACM Transactions on Software Engineering and Methodology (TOSEM) 2023
We propose Poracle, a testing approach that evaluates patches under preservation conditions to address the overfitting problem prevalent in automated program repair tools.
Poracle: Testing Patches Under Preservation Conditions to Combat the Overfitting Problem of Program Repair
Elkhan Ismayilzada, Md Mazba Ur Rahman, Dongsun Kim, Jooyong Yi
ACM Transactions on Software Engineering and Methodology (TOSEM) 2023
We propose Poracle, a testing approach that evaluates patches under preservation conditions to address the overfitting problem prevalent in automated program repair tools.
Transformer-based Unified Recognition of Two Hands Manipulating Objects
Hoseong Cho, Chanwoo Kim, Jihyeon Kim, Seongyeong Lee, Elkhan Ismayilzada, Seungryul Baek
Computer Vision and Pattern Recognition (CVPR) 2023
We present a transformer-based unified framework for simultaneous recognition of two hands manipulating objects, enabling joint understanding of hand poses and object interactions.
Transformer-based Unified Recognition of Two Hands Manipulating Objects
Hoseong Cho, Chanwoo Kim, Jihyeon Kim, Seongyeong Lee, Elkhan Ismayilzada, Seungryul Baek
Computer Vision and Pattern Recognition (CVPR) 2023
We present a transformer-based unified framework for simultaneous recognition of two hands manipulating objects, enabling joint understanding of hand poses and object interactions.
2022
Secure human action recognition by encrypted neural network inference
Miran Kim, Xiaoqian Jiang, Kristin Lauter, Elkhan Ismayilzada, Shayan Shams
Nature Communications 2022
We propose a privacy-preserving framework for human action recognition using homomorphic encryption, enabling secure inference without revealing private data.
Secure human action recognition by encrypted neural network inference
Miran Kim, Xiaoqian Jiang, Kristin Lauter, Elkhan Ismayilzada, Shayan Shams
Nature Communications 2022
We propose a privacy-preserving framework for human action recognition using homomorphic encryption, enabling secure inference without revealing private data.
Speeding up Constraint-Based Program Repair Using a Search-Based Technique
Jooyong Yi, Elkhan Ismayilzada
Information and Software Technology 2022
We present a search-based technique to accelerate constraint-based automated program repair, significantly reducing the search space and improving repair efficiency.
Speeding up Constraint-Based Program Repair Using a Search-Based Technique
Jooyong Yi, Elkhan Ismayilzada
Information and Software Technology 2022
We present a search-based technique to accelerate constraint-based automated program repair, significantly reducing the search space and improving repair efficiency.