Faizan Siddiqui

action segmentation · 3d scene encoding · 3d world modeling · representation learning · human motion generation · human motion classification · world models · foundation models · semantic segmentation · instance segmentation · image segmentation · multi-modal language models · large language models · vision language models · diffusion models · scene understanding · image captioning · video captioning · keypoint detection · keypoint estimation · simulations · carla · unreal engine · computer vision · deep learning · autonomous driving · vision encoders · image encoders · video encoders · image detection · image classification · tracking · 3d tracking