The NVPHBV fall meeting will be held at Wednesday 27th of November 2019 at the University of Amsterdam.
Venue location will be the Turingzaal at the Centrum Wiskunde & Informatica (CWI), Science Park 123, Amsterdam.
Please register for the meeting through https://www.eventbrite.nl/e/74545669103.
Confirmed keynote speakers are:
- Prof. dr. Cees Snoek, University of Amsterdam.
- Clarisa Sánchez PhD, Associate Professor at Radboud University Medical Center.
- Dr. Thomas Mensink, Google Research/Associate Professor at University of Amsterdam.
- Dr. ir. Ronald Poppe, University of Utrecht.
- Dr. Harro Stokman, CEO of Kepler Vision Technologies, Amsterdam.
- Prof. Raymond van Ee, Leuven University/ Radboud University, Nijmegen /Philips Research, Eindhoven
- Ir. Enrico Liscio, Fizyr, Delft.
11:30 – 12:00 Welcome: walk in with coffee & tea
12:00 – 13:00 Lunch
13:00 – 13:40 “Localizing concepts, the few-shot way”, Prof. dr. Cees Snoek, University of Amsterdam
13:40 – 14:20 Dr. Clarisa Sánchez, Radboud University Medical Center
14:20 – 15:00 “Depth for (and from) Convolutional Neural Networks”, Dr. Thomas Mensink, Google Research/University of Amsterdam
15:00 – 15:30 Break, coffee & tea
15:30 – 16:10 “Driver Handheld Cell Phone Use Detection”, Dr. ir. Ronald Poppe, University of Utrecht
16:10 – 16:50 “Neurostimulation and pattern recognition in personalised medical intervention for enhancement of cognition and visual perception”, Prof. Raymond van Ee, Leuven University/ Radboud University, Nijmegen /Philips Research, Eindhoven
16:50 – 17:10 “Copy right protection of deep neural networks”, Dr. Harro Stokman, Kepler Vision Technologies, Amsterdam
17:10 – 17:30 “Deep Learning: the future of warehouses”, Ir. Enrico Liscio, Fizyr, Delft
17:30 – 18:30 Drinks and networking
Prof. dr. Cees Snoek, University of Amsterdam
Localizing concepts, the few-shot way
Learning to recognize concepts in image and video has witnessed phenomenal progress thanks to improved convolutional networks, more efficient graphical computers and huge amounts of image annotations. Even when image annotations are scarce, classifying objects and activities has proven more than feasible. However, for the localization of objects and activities, existing deep vision algorithms are still very much dependent on many hard to obtain image annotations at the box or pixel-level. In this talk, I will present recent progress of my team in localizing objects and activities when box- and pixel-annotations are scarce or completely absent. I will also present a new object localization task along this research direction. Given a few weakly-supervised support images, we localize the common object in the query image without any box annotation. Finally, I will present recent results on spatio-temporal activity localization when no annotated box, nor tube, examples are available for training.
Dr. Thomas Mensink, Google Research/Associate Professor at University of Amsterdam
Depth for (and from) Convolutional Neural Networks
All state of the art image classification, recognition and segmentation models use convolutions. These (mostly) have a fixed spatial extend in the image plane, by using filters of 3×3 pixels. In this talk I will argue that convolutions should have a fixed spatial extend in the real world, in the XYZ space. We introduce a novel convolutional operator using RGB + depth as input, which yields (approximately) fixed size filters in the real world. We exploit these for image segmentation, and also show that our method is beneficial when we use D inferred from RGB, and then use our proposed RGB-D Neighbourhood Convolution. If time permits I’ll dive further into depth predictions with GANs, showing that GANs only improve monocular depth estimation when the used image reconstruction loss is rather unconstraint.
Dr. ir. Ronald Poppe, University of Utrecht
Driver Handheld Cell Phone Use Detection
Many road accidents are attributed to in-car phone use. Currently, drivers can only be fined if they are caught red-handed. In anticipation of changing legislation to allow for automated fining, we address developing computer vision detection algorithms for this task. In this talk, we discuss the technical challenges in terms of the limited amount of labeled data, low image quality and the ambiguous nature of the footage. Instead of pursuing a pure deep learning approach, we rely on domain knowledge to deal with these challenges. We show results, as well as insights into the inner workings of our approach.
Prof. Raymond van Ee , Leuven University/ Radboud University, Nijmegen /Philips Research, Eindhoven
Neurostimulation and pattern recognition in personalised medical intervention for enhancement of cognition and visual perception
Current medical treatment, including neurostimulation, is based upon a one-size-fits-all approach. Recent findings now contribute to groundwork for non-pharmacological interventions by providing novel opportunities for individual neurostimulation to forcefully tap into the residual potential of the brain. Here I present approaches of neurostimulation and pattern recognition for enhancement of cognition and visual perception. I will further discuss new approaches in deep learning for pattern recognition in behaviour and brain activity.
Dr. Harro Stokman, CEO Kepler Vision Technologies
Copy right protection of deep neural networks
In their quest to become the world’s AI platform, IT giants like Facebook and Google open sourced their deep learning executables. Furthermore, extensive public datasets are available for training while many repositories containing pre-trained models exist. To stand out from the crowd and to provide functionality not yet available out in the open requires annotating enormous amounts of images and videos. How to protect this IP? In this talk, it is argued that standard software license management technologies does not work anymore for neural networks. We’ll review novel copy right protection practices that are currently popping up.
Ir. Enrico Liscio, Deep Learning Developer at Fizyr, Delft
Deep Learning: the future of warehouses
The logistics end e-commerce sectors are rapidly growing, demanding more and more automation to meet the increasing requests. The main challenge is represented by the large variability present in the warehouses, where a single robotic cell must be able to deal with hundreds of thousands of different products. Deep learning candidates itself as the perfect solution, thanks to its ability to generalize from a sub-section of the dataset. Fizyr has successfully developed and integrated a deep learning vision solution capable to help robotic integrators to handle such a large variation of goods. In this presentation, an overview of Fizyr’s solution is presented and advantages and challenges resulting from the use of deep learning in this industrial application are introduced, focusing on aspects such as scalability and reliability.