Mats Sjöberg

Postdoctoral Researcher

Research outputs

  1. 2018
  2. Published

    DeepCaption: PyTorch-based framework for image captioning research using deep learning

    Sjöberg, M., Polis, A., Surikuchi, A. & Laaksonen, J., 5 Dec 2018

    Research output: Artistic and non-textual formSoftwareScientific

  3. Published

    PicSOM Experiments in TRECVID 2018

    Sjöberg, M., Tavakoli, H. R., Xu, Z., Mantecón, H. L. & Laaksonen, J., 1 Nov 2018, Proceedings of the TRECVID 2018 Workshop. Gaithersburg, MD, USA

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientific

  4. Published

    Proactive information retrieval by capturing search intent from primary task context

    Koskela, M., Luukkonen, P., Ruotsalo, T., Sjöberg, M. & Floréen, P., 1 Jul 2018, In : ACM Transactions on Interactive Intelligent Systems. 8, 3, A20.

    Research output: Contribution to journalArticleScientificpeer-review

  5. Published

    MediaEval 2018: Predicting Media Memorability

    Cohendet, R., Demarty, C-H., Duong, N. Q. K., Sjöberg, M., Ionescu, B. & Do, T. T., 2018, MediaEval 2018 - Multimedia Benchmark Workshop: Working Notes Proceedings of the MediaEval 2018 Workshop, Sophia, Antipolis, France, 29-31 October 2018. CEUR, 3 p. (CEUR Workshop Proceedings; vol. 2283).

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  6. Published

    The MediaEval 2018 Emotional Impact of Movies Task

    Dellandréa, E., Huigsloot, M., Chen, L., Baveye, Y., Xiao, Z. & Sjöberg, M., 2018, MediaEval 2018 - Multimedia Benchmark Workshop: Working Notes Proceedings of the MediaEval 2018 Workshop, Sophia, Antipolis, France, 29-31 October 2018. CEUR, 3 p. (CEUR Workshop Proceedings; vol. 2283).

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  7. Published

    The MeMAD submission to the WMT18 multimodal translation task

    Grönroos, S-A., Huet, B., Kurimo, M., Laaksonen, J., Merialdo, B., Pham, P., Sjöberg, M., Sulubacak, U., Tiedemann, J., Troncy, R. & 1 othersVázquez, R., 2018, Proceedings of the Third Conference on Machine Translation (WMT), Volume 2: Shared Task Papers. Vol. 2. p. 609-617 9 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  8. 2017
  9. Published

    Predicting Interestingness of Visual Content

    Demarty, C-H., Sjöberg, M., Constantin, G. G., Duong, N. Q. K., Ionescu, B., Do, T-T. & Wang, H., 1 Mar 2017, Visual Content Indexing and Retrieval with Psycho-Visual Models.

    Research output: Chapter in Book/Report/Conference proceedingChapterScientific

  10. Published

    Digital Me: Controlling and Making Sense of My Digital Footprint

    Sjöberg, M., Chen, H-H., Floreen, P., Koskela, M., Kuikkaniemi, K., Lehtiniemi, T. & Peltonen, J., 2017, Symbiotic Interaction: 5th International Workshop, Symbiotic 2016, Padua, Italy, September 29–30, 2016, Revised Selected Papers. Gamberini, L., Spagnolli, A., Jacucci, G., Blankertz, B. & Freeman, J. (eds.). Cham, p. 155-167 (Lecture Notes in Computer Science; vol. 9961).

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  11. Published

    Mediaeval 2017 predicting media interestingness task

    Demarty, C. H., Sjöberg, M., Ionescu, B., Do, T. T., Gygli, M. & Duong, N. Q. K., 2017, Multimedia Benchmark Workshop: Working Notes Proceedings of the MediaEval 2017 Workshop, co-located with the Conference and Labs of the Evaluation Forum (CLEF 2017), Dublin, Ireland, September 13-15, 2017. CEUR, 3 p. (CEUR Workshop Proceedings; vol. 1984). (CEUR Workshop Proceedings).

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  12. Published

    The MediaEval 2017 Emotional Impact of Movies Task

    Dellandra, E., Huigsloot, M., Chen, L., Baveye, Y. & Sjoberg, M., 2017, Multimedia Benchmark Workshop: Working Notes Proceedings of the MediaEval 2017 Workshop, co-located with the Conference and Labs of the Evaluation Forum (CLEF 2017), Dublin, Ireland, September 13-15, 2017. CEUR, 3 p. (CEUR Workshop Proceedings; vol. 1984). (CEUR Workshop Proceedings).

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  13. 2016
  14. Published

    MediaEval 2016 predicting media interestingness task

    Demarty, C. H., Sjöberg, M., Ionescu, B., Do, T. T., Wang, H., Duong, N. Q. K. & Lefebvre, F., 2016, In : CEUR Workshop Proceedings. 1739, 3 p.

    Research output: Contribution to journalConference articleScientificpeer-review

  15. Published

    The MediaEval 2016 emotional impact of movies task

    Dellandréa, E., Chen, L., Baveye, Y., Sjöberg, M. & Chamaret, C., 2016, In : CEUR Workshop Proceedings. 1739

    Research output: Contribution to journalConference articleScientificpeer-review

  16. 2015
  17. Published

    VSD2014: A dataset for violent scenes detection in Hollywood movies and web videos

    Schedl, M., Sjöberg, M., Mironicə, I., Ionescu, B., Quang, V. L., Jiang, Y. G. & Demarty, C. H., 9 Jul 2015, 2015 13th International Workshop on Content-Based Multimedia Indexing, CBMI 2015. Vol. 2015-July. 7153604

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  18. Published

    Advances in Visual Concept Detection: Ten Years of TRECVID

    Viitaniemi, V., Sjöberg, M., Koskela, M., Ishikawa, S. & Laaksonen, J., 2015, Advances in Independent Component Analysis and Learning Machines. Bingham, E., Kaski, S., Laaksonen, J. & Lampinen, J. (eds.). 1st Edition ed. Amsterdam, The Netherlands, p. 249-278

    Research output: Chapter in Book/Report/Conference proceedingChapterScientificpeer-review

  19. Published

    PicSOM Content-Based Information Retrieval System

    Laaksonen, J., Koskela, M., Sjöberg, M. & Viitaniemi, V., 2015

    Research output: Artistic and non-textual formSoftwareScientific

  20. Published

    RFA at MediaEval 2015 affective impact of movies task: A multimodal approach

    Mironica, I., Ionescu, B., Sjöberg, M., Schedl, M. & Skowron, M., 2015, Multimedia Benchmark Workshop: Working Notes Proceedings of the MediaEval 2015 Workshop, Wurzen, Germany, September 14-15, 2015. CEUR, 3 p. (CEUR Workshop Proceedings; vol. 1436). (CEUR Workshop Proceedings).

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  21. Published

    The MediaEval 2015 affective impact of movies task

    Sjöberg, M., Baveye, Y., Wang, H., Quang, V. L., Ionescu, B., Dellandréa, E., Schedl, M., Demarty, C. H. & Chen, L., 2015, Multimedia Benchmark Workshop: Working Notes Proceedings of the MediaEval 2015 Workshop, Wurzen, Germany, September 14-15, 2015. CEUR, 3 p. (CEUR Workshop Proceedings; vol. 1436). (CEUR Workshop Proceedings).

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  22. 2014
  23. Published

    Content-based prediction of movie style, aesthetics and affect: Data set and baseline experiments

    Tarvainen, J., Sjöberg, M., Westman, S., Laaksonen, J. & Oittinen, P., 2014, In : IEEE Transactions on Multimedia. 16, 8, p. 2085-2098

    Research output: Contribution to journalArticleScientificpeer-review

  24. Published

    Far at MediaEval 2014 Violent Scenes Detection: A concept-Based fusion approach

    Sjöberg, M., Mironica, I., Schedl, M. & Ionescu, B., 2014, Multimedia Benchmark Workshop: Working Notes Proceedings of the MediaEval 2014 Workshop, Barcelona, Catalunya, Spain, October 16-17, 2014. CEUR, 2 p. (CEUR Workshop Proceedings ; vol. 1263). (CEUR Workshop Proceedings).

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  25. Published

    From pixels to semantics: visual concept detection and its applications

    Sjöberg, M., 2014, Aalto University. 202 p.

    Research output: ThesisDoctoral ThesisCollection of Articles

  26. Published

    PicSOM Experiments in TRECVID 2014

    Ishikawa, S., Koskela, M., Sjöberg, M., Anwer, R. M., Laaksonen, J. & Oja, E., 2014, TRECVID workshop, TRECVID, Orlando, USA, November 10-12 2014.

    Research output: Chapter in Book/Report/Conference proceedingConference contributionProfessional

  27. Published

    The MediaEval 2014 Affect Task: Violent Scenes Detection

    Sjöberg, M., Ionescu, B., Jiang, Y-G., Quang, V. L., Schedl, M. & Demarty, C-H., 2014, MediaEval 2014 Workshop, Barcelona, Spain, October 16-17, 2014. Barcelona: CEUR WORKSHOP PROCEEDINGS

    Research output: Chapter in Book/Report/Conference proceedingConference contributionProfessional

  28. Published

    Using semantic features to improve large-scale visual concept detection

    Sjöberg, M. & Laaksonen, J., 2014, 2014 12th International Workshop on Content-Based Multimedia Indexing, CBMI 2014. 6 p. 6849817. (International Workshop on Content-Based Multimedia Indexing).

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  29. 2013
  30. Published

    FAR at MediaEval 2013 Violent Scenes Detection: Concept-based Violent Scenes Detection in Movies

    Sjöberg, M., Schlüter, J., Ionescu, B. & Schedl, M., 2013, MediaEval 2013 Workshop, Barcelona, Spain, October 18-19, 2013. Barcelona: CEUR WORKSHOP PROCEEDINGS

    Research output: Chapter in Book/Report/Conference proceedingConference contributionProfessional

  31. Published

    Large-Scale Visual Concept Detection with Explicit Kernel Maps and Power Mean SVM

    Sjöberg, M., Koskela, M., Ishikawa, S. & Laaksonen, J., 2013, ACM International Conference on Multimedia Retrieval, Dallas, Texas, USA, April 16 - 19, 2013. Dallas, p. 239-246

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  32. Published

    PicSOM Experiments in TRECVID 2013

    Ishikawa, S., Koskela, M., Sjöberg, M., Laaksonen, J., Oja, E., Amid, E., Palomäki, K., Mesaros, A. & Kurimo, M., 2013, TRECVID 2013 Workshop, Gaithersburg, USA, November 20-22, 2013. Gaithersburg

    Research output: Chapter in Book/Report/Conference proceedingConference contributionProfessional

  33. 2012
  34. Published

    PicSOM Experiments in TRECVID 2012

    Sjöberg, M., Ishikawa, S., Koskela, M., Laaksonen, J. & Oja, E., 2012, TRECVID 2012 Workshop, Gaithersburg, USA, November 26-28, 2012. Gaithersburg

    Research output: Chapter in Book/Report/Conference proceedingConference contributionProfessional

  35. Published

    Real-Time Large-Scale Visual Concept Detection with Linear Classifiers

    Sjöberg, M., Koskela, M., Ishikawa, S. & Laaksonen, J., 2012, ICPR 21st International Conference on Pattern Recognition (ICPR 2012) ICPR, Tsukuba, Japan, November 11-15, 2012. Tsukuba

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  36. 2011
  37. Published

    A Multimodal Information Collector for Content-Based Image Retrieval System

    Zhang, H., Sjöberg, M., Laaksonen, J. & Oja, E., 2011, ICONIP 18th International Conference on Neural Information Processing (ICONIP 2011) ICONIP. p. 737-746

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  38. Published

    Analysing the structure of semantic concepts in visual databases

    Sjöberg, M. & Laaksonen, J., 2011, WSOM Advances in Self-Organizing Maps (WSOM 2011) WSOM. Laaksonen, J. & Honkela, T. (eds.). p. 338-347 (Lecture Notes in Computer Science; vol. 6731).

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  39. Published

    PicSOM Experiments in TRECVID 2011

    Sjöberg, M., Ishikawa, S., Koskela, M., Laaksonen, J. & Oja, E., 2011, The TRECVID 2011 Workshop. Gaithersburg

    Research output: Chapter in Book/Report/Conference proceedingConference contributionProfessional

  40. 2010
  41. Published

    Automatic video search using semantic concepts

    Viitaniemi, V., Sjöberg, M., Koskela, M. & Laaksonen, J., 2010, 8th European Conference on Interactive TV and Video (EuroITV 2010). Tampere

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  42. Published

    Concept-based Video Search with the PicSOM Multimedia Retrieval System

    Viitaniemi, V., Sjöberg, M., Koskela, M. & Laaksonen, J., 2010, Espoo, p. 48, (TKK Reports in Information and Computer Science; no. TKK-ICS-R39).

    Research output: Working paperProfessional

  43. Published

    Indoor Location Recognition Using Fusion of SVM-based Visual Classifiers

    Sjöberg, M., Koskela, M., Viitaniemi, V. & Laaksonen, J., 2010, 2010 IEEE International Workshop on Machine Learning for Signal Processing. Kittilä

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  44. Published

    PicSOM Experiments in ImageCLEF RobotVision

    Sjöberg, M., Koskela, M., Viitaniemi, V. & Laaksonen, J., 2010, Recognizing Patterns in Signals, Speech, Images and Videos. Istanbul: Springer Berlin / Heidelberg, p. 190-199

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientific

  45. Published

    PicSOM Experiments in TRECVID 2010

    Sjöberg, M., Koskela, M., Chechev, M. & Laaksonen, J., 2010, The TRECVID 2010 Workshop. Gaithersburg

    Research output: Chapter in Book/Report/Conference proceedingConference contributionProfessional

  46. 2009
  47. Published

    Image Theft Detection with Self-Organising Maps

    Prentis, P., Sjöberg, M., Koskela, M. & Laaksonen, J., 2009, 19th International Conference on Artificial Neural Networks (ICANN 2009). Limassol, p. 495-504

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  48. Published

    Improving automatic video retrieval with semantic concept detection

    Koskela, M., Sjöberg, M. & Laaksonen, J., 2009, 16th Scandinavian Conference on Image Analysis (SCIA 2009). Oslo, p. 480-489

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  49. Published

    Optimal combination of SOM search in best-matching units and map neighborhood

    Sjöberg, M. & Laaksonen, J., 2009, 7th International Workshop on Self-Organizing Maps (WSOM 2009). St. Augustine, p. 281-289

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  50. Published

    PicSOM Content-Based Information Retrieval System

    Laaksonen, J., Koskela, M., Viitaniemi, V., Sjöberg, M., Zhang, H., Hussain, Z. & Leung, A., 2009

    Research output: Artistic and non-textual formSoftwareScientific

  51. Published

    PicSOM Experiments in TRECVID 2009

    Sjöberg, M., Viitaniemi, V., Koskela, M. & Laaksonen, J., 2009, The TRECVID 2009 Workshop. Gaithersburg

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  52. Published

    PinView Mozilla Browser extension

    Laaksonen, J., Sjöberg, M., Zhang, H. & Ajanki, A., 2009

    Research output: Artistic and non-textual formSoftwareScientific

  53. 2008
  54. Published

    Exploiting Temporal and Inter-Concept Co-Occurrence Structure to Detect High-Level Features in Broadcast Videos

    Viitaniemi, V., Sjöberg, M., Koskela, M. & Laaksonen, J., 2008, 9th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS 2008). Klagenfurt, p. 12-15

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  55. Published

    Inferring Semantics from Textual Information in Multimedia Retrieval

    Sjöberg, M., Laaksonen, J., Honkela, T. & Pöllä, M., 2008, In : Neurocomputing. 71, 13-15, p. 2576-2586

    Research output: Contribution to journalArticleScientificpeer-review

  56. Published

    PicSOM Experiments in TRECVID 2008

    Koskela, M., Sjöberg, M., Viitaniemi, V. & Laaksonen, J., 2008, The TRECVID 2008 Workshop. Gaithersburg, p. 408-416

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  57. 2007
  58. Published

    PicSOM Experiments in TRECVID 2007

    Koskela, M., Sjöberg, M., Viitaniemi, V., Laaksonen, J. & Prentis, P., 2007, The TRECVID 2007 Workshop. Gaithersburg

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  59. Published

    Rushes Summarization with Self-Organizing Maps

    Koskela, M., Sjöberg, M., Laaksonen, J., Viitaniemi, V. & Muurinen, H., 2007, The TRECVID Workshop on Video Summarization (TVS'07). Augsburg: ACM Press, p. 45-49

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  60. Published

    Video Summarization with SOMs

    Laaksonen, J., Koskela, M., Sjöberg, M., Viitaniemi, V. & Muurinen, H., 2007, The 6th Int. Workshop on Self-Organizing Maps (WSOM 2007). Bielefeld

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  61. 2006
  62. Published

    Analysis of Semantic Information Available in an Image Collection Augmented with Auxiliary Data

    Sjöberg, M., Viitaniemi, V., Laaksonen, J. & Honkela, T., 2006, 3rd IFIP Conference on Artificial Intelligence Applications and Innovations, Athens, Greece, 2006. Maglogiannis, I., Karpouzis, K. & Bramer, M. (eds.). Athens: IFIP, p. 600-608

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  63. Published

    Emergence of Semantics from Multimedia Databases

    Oja, E., Sjöberg, M., Viitaniemi, V. & Laaksonen, J., 2006, IEEE World Congress on Computational Intelligence, Vancouver, BC, Canada, 2006. IEEE Computational Intelligence Society

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Previous 1 2 Next

ID: 82362