This course introduces algorithms and techniques for integration of computer vision and natural language processing for innovative applications, such as robot dialog system, image/video captioning, cross-media multimedia search and question-answering. The course will discuss the latest technologies in bridging the gap between vision and language, with topics ranging from machine translation, feature extraction and learning, to design of deep neural network architecture.

For a student to pass the course, at least 30% of the maximum mark for the examination must be obtained.