Guoying Zhao

Yingyue Xu (Doctoral Dissertation): Computational modeling for visual attention analysis. Jun. 2020

Visual attention, is a biologically inspired and psychologically driven mechanism that works by selecting visually relevant information and filtering out the redundant contents. This thesis is a thorough summary around computational modeling for visual attention analysis, consisting of published papers corresponding to doctoral research progress.

Xin Liu (Doctoral Dissertation): Human Motion Detection and Gesture Recognition Using Computer Vision Methods. Mar. 2019

Gestures are present in most daily human activities. This thesis contributes to the research on gesture analysis from two aspects, 1) Detection: human motion segmentation from video sequences, and 2) Understanding: gesture cues extraction and recognition.

Xiaobai Li (Doctoral Dissertation): Reading subtle information from human faces. Sep. 2017

The face plays an important role in our social interactions as it conveys rich sources of
information. The thesis concerns using computer vision methodologies to analyse two kinds of subtle facial information that can hardly be perceived by naked eyes: the micro-expression (ME), and the heart rate (HR).

Xiaohua Huang (Doctoral Dissertation): Methods for facial expression recognition with applications in challenging situations. Dec. 2014

In recent years, facial expression recognition has become a useful scheme for computers
to affectively understand the emotional state of human beings. This thesis contributes to the research and development of facial expression recognition systems from the above two aspects.

Yimo Guo (Doctoral Dissertation): Image and video analysis by local descriptors and deformable image registration. Jun. 2013

In the first part of this work, two image description methods are presented to provide discriminative representations for image classification. In the second part, based on static image description and deformable image registration, video analysis is studied for the applications of dynamic texture description, synthesis and recognition.

Tuomas Varanka: Master thesis (2020): Facial Micro-Expression Recognition with Noisy Labels.

In this thesis, we explore new methods taking noisy labels into special account in an attempt to solve the problem. We propose a simple, yet efficient label refurbishing method and a data cleaning method for handling noisy labels. We show through both quantitative and qualitative analysis the effectiveness of the methods for detecting noisy samples.

Hao Ban: Master thesis (2020): Raw Image Burst Based Super-Resolution Algorithm for Handheld Cameras.

With the development of photography technology, how to achieve high-quality imaging through convenient handheld devices has attracted more attention. The raw image based super-resolution problem is combined with the demosaicing problem to provide better color performance and image details.

Bofan Lin: Master thesis (2019): Face Liveness Detection by rPPG Features and Contextual Patch- Based CNN.

Face anti-spoofing plays a vital role in security systems including face payment systems and face recognition systems. We propose a generalized method exploiting both rPPG and texture features for face antispoofing task.

Radouane Kaddari: Master thesis (2019): Action detection and recognition using deep neural networks.

Action detection and recognition in videos has become an attractive topic in computer vision area. In this thesis, we discuss different approaches to detect and recognize actions inside videos using
deep neural networks.

Hamza Zair: Master thesis (2019): Collision warning design in automotive head-up display.

In this thesis work, we introduce three different Forward Collision Warning (FCW) designs: static,
animated and 3D animated warnings.

Jiawei Zhang: Master thesis (2018): An Expandable System for Collection, Detection and Recognition of Human Body Gesture.

We setup a data collecting system with Kinect camera to append five more gesture categories with complementary samples in the same format to ChaLearn Looking at People dataset. A deep learning approach is developped to detect and classify the samples with Deep Belief Network (DBN) and the Viterbi algorithm with only the skeleton data as input.

Haoyu Chen: Master thesis (2017): A Preliminary Study of Micro-Gesture: Dataset Collection and Analysis with Multi-Modal Dynamic Networks.

A preliminary exploration of Micro-Gesture is made in this thesis. By collecting recorded sequences of body gestures in a spontaneous state during games, a micro-gesture dataset is built through Kinect V2. Implementations of two sets of neural network architectures are achieved for micro-gestures segmentation and recognition task.

Niloufar Zebarjadi: Master thesis (2016): Static and Dynamic Approaches for Pain Detection and Pain Intensity Estimating Using Facial Expressions.

In this thesis, a new dataset of facial expressions of patients with lower back pains is collected and annotated. Both static features: well-known LBP, and Dense SIFT, and dynamic features: LBP-TOP and 3D-SIFT, are extracted. Experiments of pain detection and pain intensity estimation are carried out and the results are compared and analyzed.

Yingyue Xu: Master thesis (2015): A Task-driven Eye Tracking Dataset For Visual Attention Analysis

In this thesis, we design and establish a new task-driven eye tracking dataset of 47 subjects. Moreover, we provide baseline results by evaluating popular saliency models. Furthermore, we hold discussions about the influence of tasks and image semantics on human visual behavior and provide suggestions for the scanpath estimation research in future.

Tuomas Varanka: Bachelor thesis (2015): Facial Micro-Expression Recognition.

In this thesis we look at why micro-expressions are important, datasets that contain micro-expressions for training of automatic systems, and how we can utilize modern computational methods for automatically recognizing micro-expressions. Lastly, we experiment with several representative methods in the literature and compare their performance.