This course aims to introduce the concepts, theories and state-of-the-art algorithms for visual learning and recognition.
The first half of the module is for formulations and theories of machine learning techniques, focused on discriminative classifier learning.
The latter half leads to the topics of visual recognition by the machine learning techniques learnt, including object detection, object categorisation, face recognition, and segmentation.
Python and Tensorflow Tutorial
The students will be able to earn knowledge and understanding about theories and concepts of visual recognition, contemporary machine learning techniques, applications of machine learning to computer vision, and skills of computer programming by coursework, and practical views of current and future application domains.
Part I.
- Object Categorisation, Bag of Words, K-means Clustering for Image Quantisation
- Randomised Decision Forests (for classification)
- Classification Forest (continued), Regression Forests, Pose Estimation
- Randomised Decision Forests (or Boosting for Face Detection)
Part II.
- Generative Adversarial Network
Part III.
- Recurrent Neural Network, LSTM, Activity Recognition