Computer Vision and Machine Learning at Adelaide

报告嘉宾:沈春华(澳大利亚阿德莱德大学  University of Adelaide)
报告题目:Computer Vision and Machine Learning at Adelaide [PPT & Video]
报告简介:The computer vision centre at the University of Adelaide is the leading research centre for computer vision in Australia. Here I’d like to present an overview of some work done by my research group, which form part of the vision centre at Adelaide. My group have been working on statistical machine learning with a focus on computer vision applications.  Not long ago we started working on deep learning, and achieved some good results on pixel labelling, image captioning, and depth estimation. In this talk, I will show some very recent results on these topics, along with a brief review of some old work on boosting, pedestrian detection, hashing, and semidefinite programming.
报告人简介:Chunhua Shen is a Professor at School of Computer Science, The University of Adelaide. He is a Project Leader and Chief Investigator at the Australian Research Council Centre of Excellence for Robotic Vision (ACRV), for which he leads the project of ‘machine learning for robotic vision’.  He is also involved in the Data to Decisions CRC Centre (D2DCRC), in particular on the projects of large scale image classification and text analysis. Before he moved to Adelaide in 2011, he was with the computer vision program at NICTA (National ICT Australia), Canberra Research Laboratory for about six years, working with Professor Richard Hartley.  His research interests are in the  intersection of computer vision and statistical machine learning. Recent work has been on real-time object detection, large-scale image retrieval and classification, and scalable nonlinear optimisation. He studied at Nanjing University (BSc and MSc), at Australian National University (MPhil), and received his PhD degree from the University of Adelaide. From 2012 to 2016, he holds an Australian Research Council Future Fellowship. He is serving as Associate Editor of IEEE Transactions on Neural Networks and Learning Systems.


(Visited 568 times, 1 visits today)