Computer vision is the field of artificial intelligence that trains computers to interpret and understand the visual world. Once the computer has learned to accurately identify objects and infer actions using digital images and deep learning models from cameras and video, it can react to what it "watches." Similarly, we humans predict and judge various behaviors with this visual information.Our laboratory is researching deep learning and machine learning in the field of computer vision, such as inferring poses of people and hands, algorithms that recognize actions and motions, semantic segmentation, and object recognition. As it is a technology that can be used in various fields such as autonomous driving, AR, and VR, accurate algorithms and data are essential.Website: http://vision.unist.ac.kr/index.html

Assist teacher in organizing the learning environment, preparing materials, maintaining resources, and grading tests and homework.

- Developed small to medium-sized autonomous robot vehicles.- Collected and annotated 3D data from LiDAR sensors for object detection.- Trained models to detect pedestrians and vehicles using LiDAR data.

- Conducted code testing and quality improvements in Python, and migrated existing code from TensorFlow to PyTorch.- Participated in daily morning and evening meetings to share progress, plan tasks, and provide feedback on team activities.- Contributed to AI-driven drug discovery by integrating AI technologies, such as NLP, with biological and chemical data, enhancing the drug discovery process.

- Researched, implemented, and developed state-of-the-art (SOTA) deep learning models, theories, and technologies.- Trained generative models on custom datasets and presented findings from relevant research papers.- Collaborated with hardware and software engineers to accelerate AI algorithms for enhanced performance and low power consumption using Mobilint's NPU solutions.

Implement a user-level library that uses ELEMENT: a latency diagnosis framework, to minimize delays.