Electrical Engineering & Computer Vision Researcher
Federal University of Rio de Janeiro (UFRJ), Brazil
About Me
I am Emre Can Aslan, a Turkish-born PhD researcher in Electrical Engineering at the Federal University of Rio de Janeiro (UFRJ), one of Latin America's most prestigious research universities. My academic journey brought me from Turkey to the vibrant city of Rio de Janeiro, Brazil, where I pursue cutting-edge research at the intersection of computer vision and human motion analysis.
My doctoral research focuses on Human Pose Estimation — developing deep learning systems that can accurately detect and track human body keypoints from images and video. This work has broad applications in healthcare, sports science, robotics, and human-computer interaction.
I have had the privilege of conducting research at Rowan University (New Jersey, USA), where I collaborated with international teams on advanced computer vision challenges. Living and working in two continents has shaped my perspective as both a researcher and a global citizen.
Beyond the lab, I enjoy futevôlei — the iconic Brazilian beach sport that blends football and volleyball — and embrace the rich culture of Rio de Janeiro that surrounds my academic life every day.
Academic Work
Developing state-of-the-art deep learning models to detect and track human body keypoints in 2D and 3D space from monocular images and video sequences. Research spans single-person and multi-person estimation across diverse real-world scenarios.
Applying convolutional neural networks, transformer architectures, and attention mechanisms to solve complex visual understanding tasks. Research includes image classification, object detection, and semantic segmentation in challenging environments.
Building intelligent systems for motion capture, activity recognition, and biomechanical analysis using artificial intelligence. Applications include rehabilitation technology, sports performance optimization, and autonomous systems.
Designing and deploying scalable AI workloads on cloud infrastructure, leveraging distributed computing to accelerate deep learning training and inference pipelines. Research covers resource optimization, containerization, and cloud-native architectures for compute-intensive vision tasks.
Researching training strategies inspired by human pedagogy, where models learn from easy examples first and progressively tackle harder ones. Applied to pose estimation and vision tasks, curriculum learning improves convergence, generalization, and robustness in challenging low-data and noisy-label scenarios.
Building intelligent conversational agents powered by Retrieval-Augmented Generation (RAG), combining large language models with dynamic knowledge bases for accurate, context-aware responses. Research focuses on domain-specific RAG pipelines, vector search, and real-time document retrieval for academic and industrial applications.
Moments
Get In Touch
I am always open to research collaborations, academic discussions, and opportunities in computer vision and deep learning. Whether you're a fellow researcher, an industry partner, or just curious about my work — feel free to reach out.