Course Summary

This graduate course is especially meant for Ph.D. students who have basic familiarity with computer vision, image processing, and pattern recognition and want to upsurge their knowledge and machinery to the state-of-the-art, with direct utility in their own research.

The topic of attention is the challenge of computer vision by learning. We address the theoretical foundations of computer vision in conjunction with machine learning and present algorithms that achieve state-of-the-art performance while maintaining efficient execution with minimal supervision. This year we explain and emphasize on computer vision by deep learning, including challenges like image classification by convolutional neural networks, object tracking by Siamese networks, action recognition with attention LSTMs, and event recognition by video embeddings. We give an overview of the latest developments and future trends in the field on the basis of several recent challenges, including the ImageNet and TRECVID benchmarks, the leading competitions for visual search engines based on computer vision by learning, and we indicate how to obtain improvements in the near future.

Course Schedule

Wednesday February 22, 2017: Fundamentals

TimeRoom TopicLecturer
0900-0930C3.163Welcome with coffee and tea
0930-1010C3.163Introduction, ObservablesArnold Smeulders
1010-1020Short break
1020-1100C3.163Invariance, CodebooksArnold Smeulders
1100-1130Break in common room - C3.239
1130-1215C3.163Encoders, KernelsCees Snoek
1215-1330Lunch break
1330-1700B1.24 A/B/CLab session - day 1 

Thursday February 23, 2017: Computer vision by deep learning

TimeRoom TopicLecturer
0900-0930C3.163Welcome with coffee and tea
0930-1010C3.163Vision in the Deep Learning Era IEfstratios Gavves
1010-1020Short break
1020-1100C3.163Vision in the Deep Learning Era IIEfstratios Gavves
1100-1130Break in common room - C3.239
1130-1215C3.163Action recognition by learningCees Snoek
1215-1330Lunch break
1330-1700B1.24 B/C/DLab session - day 2 

Friday February 24, 2017: Structure, visualizationa and tracking

TimeRoom TopicLecturer
0900-0930C3.163Welcome with coffee and tea
0930-1010C3.163Bringing Structure to Visual Deep LearningEfstratios Gavves
1010-1020Short break
1020-1100C3.163Understanding Deep Networks VisuallyEfstratios Gavves
1100-1130Break in common room - C3.239
1130-1215C3.163Object tracking by learningArnold Smeulders
1215-1330Lunch break
1330-1700B1.24 A/B/CLab session - day 3 

Monday February 27, 2017: Large-scale computer vision by learning

TimeRoom TopicLecturer
0900-0930C3.163Welcome with coffee and tea
0930-1010C3.163BenchmarkingCees Snoek
1010-1020Short break
1020-1100C3.163Weakly-supervised computer visionCees Snoek
1100-1130Break in common room - C3.239
1130-1215C3.163Event recognition by learningAmirhossein Habibian
1215-1330Lunch break
1330-1700B1.24 A/B/CLab session - day 4  

Tuesday February 28, 2017: Invited tutorial by Laurens van der Maaten

TimeRoom TopicLecturer
0900-0930CWI - NewtonzaalWelcome with coffee and tea
0930-1045CWI - Z009 Eulerzaal Understanding and Improving Convolutional NetworksLaurens van der Maaten
1045-1115Break - CWI Newtonzaal
1115-1215CWI - Z009 Eulerzaal From Visual Recognition to Visual ReasoningLaurens van der Maaten
1215-1330Lunch break
1330-1600B1.24 A/B/CLab session - day 5Challenge Data
1600Common room - C3.239Borrel 

Invited tutorial

  • Laurens van der Maaten

    is a Research Scientist at Facebook AI Research in New York, working on machine learning and computer vision. Before, he worked as an Assistant Professor at Delft University of Technology, as a post-doctoral researcher at UC San Diego, and as a Ph.D. student at Tilburg University. He is interested in a variety of topics in machine learning and computer vision.

Lecturers

  • Cees Snoek

    is currently a director of the QUVA Lab, the joint research lab of Qualcomm and the University of Amsterdam on deep learning and computer vision. He is also an Associate Professor at the University of Amsterdam and Principal Engineer/Manager at Qualcomm Research Netherlands. He was a visiting scientist at Carnegie Mellon University, Pittsburgh and the University of California, Berkeley. His research interest is video and image search by computer vision and machine learning.

  • Efstratios Gavves

    is an Assistant Professor with the University of Amsterdam in the Netherlands. He received his Ph.D. in 2014 at the University of Amsterdam. He was a post-doctoral researcher at the KU Leuven from 2014 - 2015. He has authored several papers in major computer vision and multimedia conferences and journals. His research interests include statistical and deep learning with applications on computer vision.

  • Arnold Smeulders

    is professor in visual information analysis at the University of Amsterdam. He has an interest in computer vision, content-based image retrieval and the picture-language question. Currently, he is with the University of Amsterdam, scientific director of the large public-private COMMIT research program in the Netherlands, and member of the Academia Europeana. He has graduated some 50 PhD-students. He has co-founded Euvision Technologies, an UvA-spinoff for image search engine technologies.

Guest Lecturer

  • Amirhossein Habibian

    received a B.Sc. in computer engineering (2008) and a M.Sc. in artificial intelligence (2011), both from University of Tehran, Iran. He received a Ph.D. at the University of Amsterdam in 2016. Currently, he is a senior engineer at Qualcomm Research in Amsterdam working on deep learning and computer vision. He received the Best Paper Award of ACM Multimedia 2014. His research interests include multimedia retrieval, computer vision and machine learning.