The Speakers
01
IR. Dr. Chuah Joon Huang
University of Malaya
Deep learning forms a hierarchical level of artificial neural networks to perform the mathematical process of machine learning. The artificial neural networks are created with an inspiration from the connections of neurons within human brain, where these neural nodes are linked up together like a web with certain connection strengths. While conventional computer programs carry out analysis with data in a linear way, the hierarchical function of deep learning systems enables machines to process data with a nonlinear approach. The learning process of the neural networks can be supervised, semi-supervised or unsupervised. Deep learning has been employed successfully in various fields such as computer vision, natural language processing, speech recognition, medical image processing, bioinformatics, etc. In this talk, recent advances of deep learning in a number of applications at the VIP Research Laboratory, University of Malaya will be discussed in detail.
Data Analyst
Dr. Lin, Chih-Yang
Yuan Ze University
PedJointNet: Joint Head-Shoulder and Full Body Deep Network for Pedestrian Detection
​
Pedestrian detection when occlusions exist represents a great challenge in real-world applications, including urban autonomous driving and surveillance systems. However, the head-shoulder feature of pedestrians, which is more stable and less likely to be occluded than other areas of the body, can be used as a complement to full body prediction to boost pedestrian detection accuracy. In this paper, we investigate the unique features of the head-shoulder and full body features belonging to pedestrians. Then, instead of using a popular general object detection framework like R-CNN series, SSD, or YOLO, we propose a novel pedestrian detection network, called PedJointNet, that simultaneously regresses two bounding boxes to localize the head-shoulder and full body regions based on a feasible object detection backbone. Moreover, unlike the traditional strategy of keeping the weights fixed for each attribute, we design an inbuilt mechanism to dynamically and adaptively adjust the relationships of the head-shoulder and full body predictions for more accurate pedestrian localization. We validate the effectiveness of the proposed method using the CUHK-SYSU, TownCentre and CityPersons datasets. Overall, our two-pronged prediction approach achieves excellent performance in detecting both non-occluded and occluded pedestrians, especially under circumstances involving occlusion, as compared to other state-of-the-art methods.
02
Cloud Architect
Agenda
08:30
Meet & Greet at N108
09:15
Keynote I by IR. Dr. Chuah
Keynote II by Dr. Lin, Chih-Yang
11.30
Lunch Time*
13.00
Postgraduates Presentations
17:00
Networking and Closing Ceremony
* Meal on your own
The Venue
N109, FYP Lab, Faculty of Information and Communication Technology, UTAR, Kampar
​
N108, Huawei Lab, Faculty of Information and Communication Technology, UTAR, Kampar
Presentation Schedule
