Mats SjöbergPostdoctoral Researcher, D.Sc. (Tech.)
CoSCo / INTENT research group
Helsinki Institute for Information Technology HIIT
Room A341, 3rd floor of the Exactum building,
Gustaf Hällströmin katu 2b,
Kumpula campus area,
- Postal Address:
Department of Computer Science,
P.O. 68, FI-00014,
University of Helsinki,
- +358 2941 51293 / +358 50 4480128
- email@example.com (GPG: 99E8E6D3)
My research focuses on machine learning applications, especially programming computers to learn to recognise patterns in different kinds of data. I have previously worked with huge image and video datasets, in particular detecting affective and emotional content, and general concept detection. Currently my focus is on personal data, in particular creating machine learning tools for individuals to manage and understand their digital footprint.
- Developing Digital Me (DiMe) in the context of the Re:Know project and the HIIT-wide Augmented research focus area. DiMe is a machine learning-based tool for collecting, managing and controlling your digital footprint.
- I was lead organiser for the Violent Scenes Detection Task 2014 and Affective Impact of Movies Task 2015 in the MediaEval benchmark.
- I worked in the Content-Based Image and Information Retrieval research group at Aalto University during the years 2002-2014.
- The CBIR group has taken part in the TRECVID video retrieval evaluations since 2005.
- In the CBIR group we developed the PicSOM content-based image retrieval system.
- I was assisting with the seminar course Machine Learning in Computer Vision and teaching its companion course Project in Machine Vision in 2015-2016.
- Lecturer (Swedish) for CSE-A1110 Programming 1 in 2013 and assistant in ICS-A1120 Programming 2 in 2014 at Aalto University.
- Assistant for T-61.5100 Digital Image Processing (2006-2012), T-61.5070 Computer Vision (2007-2010), and T-61.6030 Multimedia Retrieval (special course) (2008) at Aalto University.
The idea of the Digital Me (DiMe) server is to collect your personal data from various loggers into a central place that you control. Our focus is on tracking knowledge work and developing applications that can help the knowledge worker manage their working life better.
[Source code] - the source code is freely licensed (MIT).
[QE2017 slides PDF] - my slides from the Quantified Employee 2017 event explaining DiMe and time tracking.
[MyData 2016 slides PDF] - my slides from the MyData 2016 conference explaining Re:Know and Digital Me.
[Pre-print PDF] - Digital Me position paper presented at the Symbiotic 2016 workshop.
Digital Me: Controlling and Making Sense of My Digital Footprint
Mats Sjöberg, Hung-Han Chen, Patrik Floréen, Markus Koskela, Kai Kuikkaniemi, Tuukka Lehtiniemi, and Jaakko Peltonen. In Proceedings of the 5th International Workshop on Symbiotic Interaction, Symbiotic 2016. Padova, Italy.
The MediaEval 2015 Affective Impact of Movies Task
Mats Sjöberg, Yoann Baveye, Hanli Wang, Vu Lam Quang, Emmanuel Dellandréa, Markus Schedl, Claire-Hélène Demarty, and Liming Chen. In Proceedings of the MediaEval 2015 Multimedia Benchmark Workshop, Wurzen, Germany, September 14-15, 2015.
[PDF] [Slides PDF]
VSD2014: A Dataset for Violent Scenes Detection in Hollywood Movies and Web Videos
Markus Schedl, Mats Sjöberg, Ionut Mironica, Bogdan Ionescu, Vu Lam Quang, Yu-Gang Jiang, Claire-Hélène Demarty. In Proceedings of the 13th International Workshop on Content-Based Multimedia Indexing (CBMI) 2015, Prague, Czech Republic, June 10-12, 2015.
The MediaEval 2014 Affect Task: Violent Scenes Detection
Mats Sjöberg, Bogdan Ionescu, Yu-Gang Jiang, Vu Lam Quang, Markus Schedl, and Claire-Hélène Demarty. In Proceedings of the MediaEval 2014 Multimedia Benchmark Workshop, Barcelona, Spain, October 16-17, 2014.
[PDF] [Slides PDF]
Content-based Prediction of Movie Style, Aesthetics and Affect: Data Set and Baseline Experiments
Jussi Tarvainen, Mats Sjöberg, Stina Westman, Jorma Laaksonen, Pirkko Oittinen. In IEEE Transactions on Multimedia, 2014.
Using semantic features to detect novel visual concepts.
Mats Sjöberg and Jorma Laaksonen. In Proceedings of the 12th International Content Based Multimedia Indexing Workshop (CBMI 2014), Klagenfurt, Austria, June, 2014.
Large-Scale Visual Concept Detection with Explicit Kernel Maps and Power Mean SVM.
Mats Sjöberg, Markus Koskela, Satoru Ishikawa and Jorma Laaksonen. In Proceedings of ACM International Conference on Multimedia Retrieval (ICMR 2013), Dallas, Texas, USA, April, 2013.
Analysing the structure of semantic concepts in visual databases.
Mats Sjöberg and Jorma Laaksonen. In Proceedings of 8th International Workshop on Self-Organizing Maps (WSOM 2011), Espoo, Finland, 2011.
Optimal combination of SOM search in best-matching units and map neighborhood.
Mats Sjöberg and Jorma Laaksonen. In Proceedings of 7th International Workshop on Self-Organizing Maps (WSOM 2009), St. Augustine, Florida, USA, 2009.
Improving automatic video retrieval with semantic concept detection.
Markus Koskela and Mats Sjöberg and Jorma Laaksonen. In Proceedings of 16th Scandinavian Conference on Image Analysis (SCIA 2009), Oslo, Norway, 2009.
Inferring Semantics from Textual Information in Multimedia Retrieval.
Mats Sjöberg and Jorma Laaksonen and Timo Honkela and Matti Pöllä. In Neurocomputing, 2008.
My ORCID is 0000-0002-3157-7668.
From pixels to semantics: visual concept detection and its
Department of Information and Computer Science, Aalto University School of Science.