Seminar by Prof Jinchang Ren, Saliency Detection in Images and Videos: From Visual Perception to Deep Learning (08 Nov 2022)
08 Nov 2022
03.00 PM - 04.00 PM
Current Students, Industry/Academic Partners
You are cordially invited to the seminar jointly organized by
IEEE Signal Processing Singapore Chapter &
IEEE Circuits and Systems Singapore Chapter &
Centre for Information Sciences and Systems (CISS), School of EEE, NTU
Date and Time:
08 Nov 2022 | 3pm – 4pm, Tuesday
08 Nov 2022 | 3pm – 4pm, Tuesday
Venue:
NTU EEE Executive Seminar Room (S2.2-B2-53)
NTU EEE Executive Seminar Room (S2.2-B2-53)
Title:
Saliency Detection in Images and Videos: From Visual Perception to Deep Learning
Saliency Detection in Images and Videos: From Visual Perception to Deep Learning
Speaker:
Prof Jinchang Ren, Professor of Computing Sciences
Robert Gordon University, Aberdeen, U.K.
Abstract:
Visual attention is a kind of fundamental cognitive capability that allows human beings to focus on the region of interests (ROIs), i.e. the saliency parts, under complex natural environments. Saliency detection plays an important role in a wide range of computer vision tasks, especially for salient object detection. In this talk, conventional models for saliency detection is covered first, based on visual perception and gestalt laws in unsupervised saliency detection from images, where both bottom-up and top-down attention mechanisms are integrated for more effective detection.
Following the success in conventional models, we proposed deep learning - based saliency detection in videos. By taking several consecutive frames as input, both the spatial and temporal characteristics are considered when computing saliency maps through fusion of hybrid high-level features. In addition, applications of saliency detection in some interesting applications are also demonstrated.
Following the success in conventional models, we proposed deep learning - based saliency detection in videos. By taking several consecutive frames as input, both the spatial and temporal characteristics are considered when computing saliency maps through fusion of hybrid high-level features. In addition, applications of saliency detection in some interesting applications are also demonstrated.
Biography:
Jinchang Ren received his B. Eng. degree in computer software, M.Eng. in image processing, and D. Eng. in computer vision, all from Northwestern Polytechnical University, Xi’an, China. He was also awarded a Ph.D. degree in Electronic Imaging and Media Communication from the University of Bradford, Bradford, U.K.
Currently he is a full Professor of Computing Sciences, Transparent Ocean Lead, and Director of the Hyperspectral Imaging Lab at the National Subsea Centre (NSC), also Director of NSC International PGR Academy, Robert Gordon University, Aberdeen, U.K.
Dr. Ren is a Senior Member of IEEE, and Lifetime Achievement Fellow of Marquis Who’s Who. His research interests focus mainly on hyperspectral imaging, image processing, computer vision, big data analytics and machine learning, with a research portfolio over £3.5 million. He has published 300+ peer reviewed journal/conferences articles, and acts as an Associate Editor for several international journals including IEEE TGRS and J. of the Franklin Institute et al. He has also chaired and co-chaired a number of conferences and workshops. His students have received many awards, including the Best PhD thesis from IET Image and Vision Section and various conferences/workshops.