EE论坛（第328期）：Quantum Mechanics Meets Spectral Graph Theory: Salient Object Detection by Quantum CUTS
讲座题目：Quantum Mechanics Meets Spectral Graph Theory: Salient Object Detection by Quantum CUTS
主讲人： Prof. Moncef Gabbouj, Tampere University of Technology, Tampere, Finland，IEEE Fellow, Member of the Academia Europaea
报告简介：This talk focuses on the key problem of salient object using principles from Quantum Mechanics. The talk is organized in three parts. Part 1 is a direct application of ideas originally proposed for describing the wave nature of particles in Quantum Mechanics and expressed through the Schrödinger’s Equation, to salient object detection in images. This is the first study that proposes a realizable quantum mechanical system for salient object proposals yielding an instantaneous speed in a possible physical implementation in the quantum scale.
The second part of the talk focuses on spectral graph based salient object detection method, namely Quantum-Cuts. Despite the success of spectral graph based methods in many Computer Vision tasks, traditional approaches on applications of spectral graph partitioning methods offer little for the salient object detection problem which can be mapped as a foreground segmentation problem using graphs. Thus, Quantum-Cuts adopts a novel approach to spectral graph partitioning by integrating quantum mechanical concepts to Spectral Graph Theory. In particular, the probabilistic interpretation of quantum mechanical wave-functions and the unary potential fields in Quantum Mechanics when combined with the pairwise graph affinities that are widely used in Spectral Graph Theory, results into a unique optimization problem that formulates salient object detection. The optimal solution of a relaxed version of this problem is obtained via Quantum-Cuts and is proven to efficiently represent salient object regions in images.
The third part of the talk covers improvements of Quantum-Cuts obtained by analyzing the main factors that affect its performance in salient object detection. Particularly, both unsupervised and supervised approaches are adopted in improving the exploited graph representation. The extensions on Quantum-Cuts led to computationally efficient algorithms that outperform the state-of-the-art in salient object detection.
主讲人简介：MONCEF GABBOUJ received his BS degree in electrical engineering in 1985 from Oklahoma State University, Stillwater, and his MS and PhD degrees in electrical engineering from Purdue University, West Lafayette, Indiana, in 1986 and 1989, respectively.
Dr. Gabbouj is a Professor of Signal Processing at the Department of Signal Processing, Tampere University of Technology, Tampere, Finland. He was Academy of Finland Professor during 2011-2015. He held several visiting professorships at different universities. Dr. Gabbouj is currently the TUT-Site Director of the NSF I/UCRC funded Center for Visual and Decision Informatics. His research interests include multimedia content-based analysis, indexing and retrieval, machine learning, nonlinear signal and image processing and analysis, voice conversion, and video processing and coding.
Dr. Gabbouj is a Fellow of the IEEE and member of the Academia Europaea and the Finnish Academy of Science and Letters. He is the past Chairman of the IEEE CAS TC on DSP and committee member of the IEEE Fourier Award for Signal Processing. He served as Distinguished Lecturer for the IEEE CASS. He served as associate editor and guest editor of many IEEE, and international journals.
Dr. Gabbouj was the recipient of the 2017 Finnish Cultural Foundation for Art and Science Award, the recipient of the 2015 TUT Foundation Grand Award, the 2012 Nokia Foundation Visiting Professor Award, the 2005 Nokia Foundation Recognition Award, and several Best Paper Awards. He published over 700 publications and supervised 45 doctoral and 58 Master theses.