Instructors/Speakers Prof. Daniel P. K. LUN Department of Electronic and Information Engineering Hong Kong Polytechnic University Abstract In 3D computer graphics, the depth map of a scene is a dataset that provides information about the distance of the surfaces of scene objects from a viewpoint. Nowadays, we can effectively estimate the depth map of a scene using different hardware or software techniques. It is particularly the case with the recent high-end mobile devices which are all equipped with multiple cameras. The depth map can be estimated using different triangulation methods based on the multiple images captured by the cameras. Once the depth map is obtained, the next question is what we can do with such additional information of the scene. ...

Instructors/Speakers Prof. Kin-Man LAM The Hong Kong Polytechnic University Abstract Facial aging variation is a major problem for face recognition systems, due to large intra-personal variations caused by age progression. A major challenge is to develop an efficient, discriminative feature representation and matching framework, which is robust to facial aging variations. In this talk, we will present a robust deep-feature encoding-based discriminative model for age-invariant face recognition. Our method learns high-level deep features using a pretrained deep-CNN model. These features are then encoded by learning a codebook with S codewords or atoms, which converts each of the features into a discriminant S-dimensional codeword for image representation. By incorporating the locality information in the whole learning process, a closed-form solution is ...

Instructors/Speakers Prof. Wenbo HE McMaster University Canada Abstract Nowadays, billions of videos are captured, hosted and shared in the cloud, and the world has stepped into a multimedia big data era. As an active and interdisciplinary research field, multimedia big data presents great challenges and opportunities for multimedia big data computing. A vast amount of research work has been done in image processing, targeting different aspects of big data analytics, such as the capture, storage, indexing, mining, and retrieval. However, when shifting the attention from images to videos, we are facing several challenges (e.g. it is more challenging to generate video features with temporal correlation; it is more challenging to get correctly labeled video samples for machine learning algorithms; etc.). ...