Scholar
Reza Baharani
Google Scholar ID: LjWpX1AAAAAJ
School of Electrical and Computer Engineering, University of NC, Charlotte
Citations & Impact
Citations
481
H-index
9
i10-index
9
Publications
20
Co-authors
24
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Research Experience
- Scientific Researcher at TeCSAR Lab: Developing a self-supervised training framework tailored for transformer-based architectures in the realm of computer vision, with a focus on enhancing contextual understanding in 2/3-D pose estimation tasks; Developed a discrete Variational Auto-Encoder (dVAE) to accurately capture the dynamics of pose movement over time in a discrete latent space, enabling effective classification of pose movements; Training transformer-based models, including those based on ViT and BERT-like architectures, through generative and contrastive self-supervised approaches; Engaging in MLIR (Multi-Level Intermediate Representation) projects to lower machine learning models for custom hardware designed on FPGA as a potential target platform; Examining and evaluating open-source initiatives like CIRCT alongside pre-existing MLIR batteries, such as torch/tensorflow-mlir. Lead Edge/IoT Deep Learning Engineer at ForesightCares Inc: Led a smartphone software development team in leveraging AI and 3D pose estimation to assess and minimize fall risk and cognitive impairment in older adults, achieving performance up to 20 FPS on the device SoC; Large scale parallel training and validation of a novel human 3D pose estimation algorithms on datasets such as Human3.6M and NTU-RGB+D (2.3 TB); Developed Swift code to integrate TensorFlow TFLite and Apple MLPackage models with CoreML for NE(NPU)/CPU/GPU processing and utilized React Native to establish the connection between AI and user interface. MLOps Engineer at TeCSAR Lab: Designed and implemented an end-to-end scalable, intelligent advanced video surveillance vision pipeline, achieving a system performance of 23 frames per second (FPS) for eight concurrent cameras at Full HD resolution; Utilized four deep learning models for the purposes of detection, re-identification, body pose estimation, and segmentation; Trained a person re-ID model on large datasets, including DukeMTC, CUHK03, and Market1501, enhancing its accuracy for mixed-precision inference; Used PyTorch Multiprocessing Process and Queues to parallelize models inference; Leveraged the Flask module to construct a RESTful API that serves an ML model for re-identifying individuals across different camera clients.
Background
- With a fusion of skills in custom hardware design and deep learning, I bring unique expertise to the development of power-efficient solutions for edge devices. Proficient in High-Level Synthesis (HLS), Hardware Description Languages (HDL), and scalable modular architecture on FPGAs and ASIC, I also excel in real-time AI production, including complete development and verification cycles. As a Deep Learning Engineer, I specialize in crafting advanced neural network architectures such as convolutional, recurrent, and transformer structures for applications in computer vision, time series, and text. I've mastered handling large-scale datasets and parallel training on high-end GPU servers, applying cutting-edge techniques like AI HW/SW co-acceleration, quantization, knowledge distillation, and pruning. My commitment to continuous innovation and eagerness to explore new technologies fuels my dedication to staying at the forefront of AI and machine learning advancements, ensuring growth and excellence in all I pursue.
