March

March 28th

15:30

Room 55.309

Invited Research Seminar

Towards perceptually realistic visual experience
Speaker: Rafal Mantiuk

Hosted by: Marelo Bertalmío

Abstract>>

Today's computer graphics techniques make it possible to create imagery that is hardly distinguishable from photographs. However, a photograph is clearly no match to an actual real-world scene. I argue that the next big challenge is to achieve perceptual realism by creating artificial imagery that would be hard to distinguish from reality. This requires profound changes in the entire imaging pipeline, from acquisition and rendering to display, with the strong focus on visual perception.
 
The technical limitations of display technologies make it very hard to deliver perceptually realistic images. However, we can get much closer to that goal by a technique that involves optimization of perceptual match between real-world visual content and the rendition of that content on a display. Given the limitations of a display and a model of visual system, we can render images which are the closest match to the real-world experience. I will demonstrate such an approach on an example modeling night vision, in which we can simulate night vision or compensate for its limitations. The method can be used in games, driving simulators, or as a compensation for displays used under varying ambient light levels.
 

Short Bio >>

Rafal K. Mantiuk is a senior lecturer at the Computer Laboratory, University of Cambridge (UK). He received PhD from the Max-Planck-Institute for Computer Science (Germany). His recent interests focus on designing imaging algorithms that adapt to human visual performance and viewing conditions in order to deliver the best images given limited resources, such as computation time, bandwidth or dynamic range. He contributed to early work on high dynamic range imaging, including quality metrics (HDR-VDP), video compression and tone-mapping. More on his research can be found at: http://www.cl.cam.ac.uk/~rkm38/.

March 29th

11:00

Room 55.410

Invited Research Seminar

Style aware tone retargeting
Speaker: Rèmi Cozot 

Hosted by: Marelo Bertalmío

Abstract>>

The last trend in displays and TV is High Dynamic Range technologies, which provide high range of contrast. On the one hand, the vast majority of video content existing today is in Standard Dynamic Range (SDR) format and there is a strong interest in upscaling this content for High Dynamic Range (HDR) displays. This retargeting processing is called Tone Expansion (or Inverse Tone Mapping). On the other hand, HDR content must be downscaled to SDR format in order to be displayed on SDR displays. This processing is called Tone Mapping.  After a short introduction that presents the key elements related to lighting styles or aesthetics, we show that current Tone Expansion and Tone Mapping operators do not perform as well when dealing with content of various lighting styles/aesthetics. Then we propose a Tone Expansion method that adapts to the style of the video and ensure the lighting style fidelity.  Concerning Tone Mapping operators, many solutions have been designed for still images over the last decade; only few of them can cope with video sequences. Indeed, these operators tone map each frame of a video sequence separately, which results in the lost of the lighting style of the HDR content. We propose a method that aims at preserving lighting style (more especially temporal brightness coherency) when tone mapping video sequences.
 

Short Bio >>

Rémi Cozot (born 1968, France) is associate professor at the University of Rennes 1 and member of the IRISA Laboratory. He received his Ph.D and Habilitation to conduct researches respectively in 1996 and 2014. His main research topic concerns the preservation of a user’s intent when editing real or computer generated contents. This topic involves many scientific skills such as visual human perception, image and video analysis, computer graphics. He has been involved in HDR imagery since 2007 and participated in many French and European projects on HDR imaging. He is co-author of the chapter “video tone mapping” of the book entitled “High Dynamic Range Video - From Acquisition, to Display and Applications”.

March 30th

12:30

Auditorium

Integrative  Research Seminar

Technology-enhanced music learning, health and well-being
Speaker: Rafael Ramirez
 

Abstract>>

Learning to play a musical instrument has been showed to provide several benefits for acquiring non-musical skills. However, there is a lack of generalised access to music education, and musical instrument learning is mostly based on the master-apprentice model in which the student’s interaction and socialization is often restricted to short and punctual contact with the teacher followed by long periods of self-study resulting in high abandonment rates. In such scenario, modern technologies are rarely employed and almost never go beyond audio and video recording. Our research aims to study how we learn musical instruments from a pedagogical and scientific perspective in order to create new interactive, assistive, self-learning, augmented-feedback, and social-aware systems complementary to traditional teaching. The aim is to allow more people to have access to music education, including people with motor disabilities, and reduce abandonment rates among music students. In this seminar, I will take the opportunity to present some of the research carried out in our research lab on areas such as technology-enhanced music learning, expressive performance modelling, accessible music interfaces, as well as some applications to health and well-being.

Short Bio >>

Dr. Rafael Ramirez is a Tenured Associate Professor and Leader of the Music and Machine Learning Lab at the Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona. He obtained his BSc in Mathematics form the National Autonomous University of Mexico, and his MSc in Artificial Intelligence and PhD in Computer Science from the University of Bristol, UK. For five years, Rafael was a Lecturer in the Department of Computer Science at the School of Computing of the National University of Singapore. He is currently principal investigator in the H2020 Research and Innovation TELMI (Technology-Enhanced Learning of Music Instruments) project. His research interests include music technology, machine learning, data mining, and their application to cognition, creative processes, accessible and brain-computer Interfaces, and health and well-being. He has published more than 100 research articles in peer-reviewed international Journals and Conferences, and acted as guest-editor of several special issues focused on machine learning and music. He currently acts as chair and program committee member for several machine learning and music technology conferences.

March 30th

15:30

Room 54.003

 

PhD Research Seminar

Mendeley reference manager and research network
Speaker: Gemma Álvarez
Hosted by: Aurelio Ruiz

Abstract>>

During the presentation we will talk about:

Mendeley as a reference manager:

​- How to import your documents and references into your ​own library

​- How to generate citations and bibliographies with MS Word and LibreOffice Plug-ins

Mendeley as a research network: 

- Connect and collaborate with researchers

- Your professional researcher profile

IMPORTANT: Previous tasks to do before the session (we recommend you to bring your on laptop. Please fill this form if you plan to attend):

1. Create your Mendeley account.

2. Access the upgraded Mendeley Institutional Edition (MIE) as a UPF's member to get the advantages.

3. Download the Mendeley Desktop version into your device.

Short Bio >>

UPF Library

April

April 20th

15:30

Room 52.s29

Invited Research Seminar

Considerations about space in acousmatic music. Expanding ideas into multichannel formats
Speaker: Daniel Schachter
Hosted by: Andres Lewin

Abstract>>

The relation between sound and space has always been a central concern for composers of acousmatic music and spatial distribution is undoubtedly a part of the conception of musical works. In this way, composers have at their disposal the possibility of defining which will be the final concert format for each of their compositions.  On the other hand technological advances allow the listener to access and choose more than one way of listening to music and in recent years the installation of multichannel audio home systems has become more and more usual, while the concert venues have incorporated multichannel options as a standard for the concert.

However, stereo remains as the most widely used format for CD distribution as well as for radio broadcasting.  This situation is undoubtedly decisive for the composer’s perspective. In fact, composers in some cases think their music in stereo and afterwards need to extended their thought into 6 or 8 channels for the concert, or on the contrary they may originally think their sound discourse in multiple channels with the concert in mind, and after that are forced to think on a stereo reduction for recording and broadcasting.  This talk will propose some compositional strategies, considering that the multichannel expansion of an original stereo can have similar textural characteristics that the orchestration in traditional instrumental music, and that the stereo reduction of a multichannel original may also be compared with the piano reduction of orchestral pieces.  This approach does not rule out the use of computer applications, but takes more into account the textural characteristics of musical works in order to face expansion and/or reduction. 

Short Bio >>

Composer and researcher, born in Buenos Aires in 1953. Professor at the National University of Lanús (UNLa, Argentina) where he is also director of the UNLa’s Research Centre for Sonic and Audiovisual Arts (CEPSA). He taught electroacoustic composition at the Julian Aguirre Conservatory in Buenos Aires for almost 20 years and established the conservatory’s Electroacoustic Studio. He is a founder and Board Member of the RedASLA (Network for Latinamerican Sonic Arts) created in Santiago, Chile (2005). 

 

Research Seminars Archives >>

If you are interested in giving a Research Seminar or you would like to invite a speaker please fill in the following form RSDetails Form >>