I am an Artificial Intelligence (AI) researcher with a special focus on computer vision, audio-visual, and vision-language models ranging from images to videos.I completed my Ph.D. in EECS from York University under the supervision of Professor Richard P. Wildes. My dissertation, titled "A Unified Multiscale Encoder-Decoder Transformer For Video Segmentation," centers on innovating a unified multiscale video transformer for both video-only and multimodal audio-visual segmentation.My expertise spans various critical areas within the dynamic fields of Deep Learning, Computer Vision, and Large Language and Vision Models (LLVMs). My recent work includes video object segmentation, actor-action segmentation, semantic segmentation, object detection and tracking, video instance segmentation, text referring video segmentation, and sound source segmentation. Additionally, I have a strong grasp of neural network interpretability and explainable AI methodologies. Furthermore, I possess demonstrated experience in time series forecasting, particularly in financial forecast analysis, such as predicting stock and option prices, and in the exciting field of autonomous driving, specializing in precise vehicle trajectory prediction.With a rich academic research background of over seven years, I am deeply committed to exploring the frontiers of AI and translating these advancements into practical applications. I am passionate about innovating novel AI approaches to improve various facets of our everyday lives and actively contributing to the development of cutting-edge AI products for the benefit of society.I invite you to connect with me to explore potential collaborative opportunities and engage in insightful discussions on the latest advancements in AI and Computer Vision.#AI #DeepLearning #ComputerVision #LLM #Multimodal #Vision-Language #Innovation #Research #Technology #PhD