This Wednesday, Dr. Sertan Şentürk (soon to join the R&D team in Kobalt music) is going to give a seminar titled “What is Music Information Retrieval? Applications and the State-of-the-Art” for Multimedia Informatics - Research Methods (MMI 700) course. You are all kindly invited.

Location: Conference Room (124), METU Informatics Institute
Time: December 20, 2017, 11:30-12:30

Abstract: What is Music Information Retrieval? Applications and the State-of-the-Art

Music, without a doubt, is one of the pinnacles of human creativity, communication and culture. With the digital media revolution and the rise of music streaming services, there has recently been a growing interest and a high demand to process large-scale musical material such as audio recordings, music scores and album reviews. In this talk, I will provide a gentle introduction to music information retrieval (MIR), an interdisciplinary field which “incorporates elements from signal processing, machine learning, psychology, musicology, and many more” to retrieve relevant information from music. From recommendation systems to automatic music generation, I will present a wide variety of examples involving MIR and discuss how such technologies are being used in academic and industrial settings, for example in music streaming, computational musicology and music education.

Bio
I am a data scientist, specializing in music information retrieval, soon to join the R&D team in Kobalt music. My research involves developing signal processing and machine learning based computational methodologies to automatically describe and discover music. Throughout the years, I have worked on creating robust and scalable solutions for a vast number of tasks such as audio-score alignment, automatic genre/mode classification, music structure analysis, and audio fingerprinting.

In February 2017, I obtained my Ph.D. degree in Information and Communication Technologies from the Music Technology Group in Universitat Pompeu Fabra, Spain. I received my MSc. degree in Music Technology from Georgia Institute of Technology, the USA in 2011, and my BSc. degree in Electrical and Electronics Engineering from Middle East Technical University, Turkey in 2009. I have also completed a four-year, part-time classical guitar program from Hacettepe University Ankara State Conservatory in 2009.

Asst. Prof. Hamdi Dibeklioglu (Bilkent University) is going to give a seminar titled “Exploring Temporal Dynamics of Facial Behavior” for Multimedia Informatics - Research Methods (MMI 700) course.

You are all kindly invited.

Location: Conference Room (124), METU Informatics Institute
Time: November 15, 2017, 11:30-12:30

Title: Exploring Temporal Dynamics of Facial Behavior

Abstract: While the majority of earlier studies in face analysis rely solely on static appearance, temporal analysis of expressions reveals interesting patterns. By exploiting temporal patterns, the current state of automatic face analysis goes far beyond recognizing basic expressions and identity. Our recent findings show that the use of temporal dynamics of expressions can benefit a large variety of tasks from assessing mental health to the estimation of taste appreciation and the verification of kin relations. In this talk, I will discuss how we can capture and model discriminative temporal characteristics of expressions, leading to a more reliable analysis of facial behavior.

Short bio: Hamdi Dibeklioglu is an Assistant Professor in the Computer Engineering Department of Bilkent University as well as being a Research Affiliate with the Pattern Recognition & Bioinformatics Group of Delft University of Technology and with the Computer Vision Group of the University of Amsterdam. He received the B.Sc. degree from Yeditepe University in 2006, the M.Sc. degree from Bogazici University in 2008, and the Ph.D. degree from the University of Amsterdam in 2014. Before joining Bilkent University, he was a Postdoctoral Researcher at Delft University of Technology, a Visiting Researcher at Carnegie Mellon University, University of Pittsburgh, and Massachusetts Institute of Technology. His research focuses on affective computing, computer vision, and pattern recognition. Dr. Dibeklioglu is a Program Committee Member for several top tier conferences in these areas. He was a Co-chair for the Netherlands Conference on Computer Vision 2015, and a Local Arrangements Co-chair for the European Conference on Computer Vision 2016. He served on the Local Organization Committee of the eNTERFACE Workshop on Multimodal Interfaces, in 2007 and 2010.

Abstract: Cognitive control is the ability to adjust behaviour to meet task demands under a changing context. Incoming information is suppressed or processed in light of the current goal and the environment. There is an ongoing debate on whether the adaptive control of behaviour is governed by a supervisory mechanism or by retrieval of past events. I will describe our studies and discuss implications to resolving this debate.

Speaker: Dr. Nart Bedin Atalay -- Department of Psychology, TOBB University of Economics and Technology

Date/Time: Friday 5 May 2017, 12:40

Place: METU Graduate School of Informatics,  S0

Abstract: Thanks to advances in computing technologies, availability of large amounts of data, and the discovery of new training techniques, deep learning has led to performance boost in many challenging problems across different domains. In this talk, I will make a very brief introduction to deep learning, focusing mainly on its properties, why it works and how it works.

Short bio: Sinan Kalkan received the M.Sc. degree in computer engineering from Middle East Technical University, Ankara, Turkey, in 2003, and the Ph.D. degree in informatics from the University of Göttingen, Göttingen, Germany, in 2008. He joined the Department of Computer Engineering at METU after his PhD. Sinan Kalkan’s research interests include computer vision, cognitive robotics and deep learning.

Location: Conference Room (124), METU Informatics Institute
Time: May 5, 2017, 12:40-13:30