July–December 2026. Representation learning, alignment and fusion across text, vision and audio; vision–language pre-training and multimodal generation.
Project briefs on deep-learning based recognition systems.
Foundations of deep neural networks and their applications.
Image classification, detection and recognition pipelines.
Core image and video processing techniques.
Lossless and lossy compression, coding and transforms.
Lab assignments, tutorials and class lectures.
Lectures, tutorials and lab assignments.