Searched for:
(1 - 20 of 85)

Pages

document
Nieuwenhuizen, R.P.J. (author), Kruithof, M. (author), Schutte, K. (author)
High resolution imagery is of crucial importance for the performance on visual recognition tasks. Super-resolution (SR) reconstruction algorithms aim to enhance the image resolution beyond the capability of the image sensor being used. Traditional SR algorithms approach this inverse problem using physical models for the image formation combined...
conference paper 2017
document
Louizos, C. (author), Shalit, U. (author), Mooij, J. (author), Sontag, D. (author), Zemel, R. (author), Welling, M. (author)
Learning individual-level causal effects from observational data, such as inferring the most effective medication for a specific patient, is a problem of growing importance for policy makers. The most important aspect of inferring causal effects from observational data is the handling of confounders, factors that affect both an intervention and...
conference paper 2017
document
Louizos, C. (author), Ullrich, K. (author), Welling, M. (author)
Compression and computational efficiency in deep learning have become a problem of great significance. In this work, we argue that the most principled and effective way to attack this problem is by adopting a Bayesian point of view, where through sparsity inducing priors we prune large parts of the network. We introduce two novelties in this...
conference paper 2017
document
Fischer, N.M. (author), Kruithof, M.C. (author), Bouma, H. (author)
In the field of security and defense, it is extremely important to reliably detect moving objects, such as cars, ships, drones and missiles. Detection and analysis of moving objects in cameras near borders could be helpful to reduce illicit trading, drug trafficking, irregular border crossing, trafficking in human beings and smuggling. Many...
conference paper 2017
document
Louizos, C. (author), Welling, M. (author)
We reinterpret multiplicative noise in neural networks as auxiliary random variables that augment the approximate posterior in a variational setting for Bayesian neural networks. We show that through this interpretation it is both efficient and straightforward to improve the approximation by employing normalizing flows (Rezende & Mohamed, 2015)...
conference paper 2017
document
Satsangi, Y. (author), Whiteson, S. (author), Oliehoek, F.A. (author), Bouma, H. (author)
Automated tracking is key to many computer vision applications. However, many tracking systems struggle to perform in real-time due to the high computational cost of detecting people, especially in ultra high resolution images. We propose a new algorithm called PartiMax that greatly reduces this cost by applying the person detector only to the...
conference paper 2017
document
Satsangi, Y. (author), Whiteson, S. (author), Oliehoek, F.A. (author), Bouma, H. (author)
article 2017
document
Schutte, K. (author), Burghouts, G. (author), van der Stap, N. (author), Westerwoudt, V.L. (author), Bouma, H. (author), Kruithof, M.C. (author), Baan, J. (author), ten Hove, R.J.M. (author)
The bottleneck in situation awareness is no longer in the sensing domain but rather in the data interpretation domain, since the number of sensors is rapidly increasing and it is not affordable to increase human data-analysis capacity at the same rate. Automatic image analysis can assist a human analyst by alerting when an event of interest...
conference paper 2016
document
van den Broek, S.P. (author), Nieuwenhuizen, R.P.J. (author), Fischer, N.M. (author), ter Haar, F.B. (author), Baan, J. (author), Van Der Stap, N. (author), Dijk, J. (author), Schutte, K. (author)
Naval ships have camera systems available to assist in performing their operational tasks. Some include automatic detection and tracking, assisting an operator by keeping a ship in view or by keeping collected information about ships. Tracking errors limit the use of camera information. When keeping a ship in view, an operator has to re-Target a...
conference paper 2016
document
de Boer, M.H.T. (author), Schutte, K. (author), Zhang, H. (author), Lu, Y.J. (author), Ngo, C.W. (author), Kraaij, W. (author)
One of the challenges in Multimedia Event Retrieval is the integration of data from multiple modalities. A modality is defined as a single channel of sensory input,such as visual or audio. We also refer to this as data source. Previous research has shown that the integration of different data sources can improve performance compared to only...
article 2016
document
Elands, P.J.M. (author)
Kleine onbemande vliegtuigen, ook wel drones genoemd, zijn bezig aan een snelle opmars. Firma’s als DJI, Parrot en 3D Robotics brengen regelmatig nieuwe modellen op de markt die steeds meer functionaliteit hebben, zoals een HD camera en het automatisch volgen van de dronebestuurder (de 'selfie-drone'), en ook steeds makkelijker te bedienen zijn....
article 2016
document
van den Haak, W.P. (author), Emde, M.F. (author)
report 2016
document
Bowman, E.K. (author), Broome, B.D. (author), Holland, V.M. (author), Summers-Stay, D. (author), Rao, R.M. (author), Duselis, J. (author), Howe, J. (author), Madahar, B.K. (author), Boury-Brisset, A.C. (author), Forrester, B. (author), Kwantes, P. (author), Burghouts, G. (author), van Huis, J. (author), Mulayim, A.Y. (author)
This report summarizes the findings of an exploratory team of the North Atlantic Treaty Organization (NATO) Information Systems Technology panel into Content-Based Analytics (CBA). The team carried out a technical review into the current status of theoretical and practical developments of methods, tools and techniques supporting joint...
conference paper 2016
document
Lefter, I. (author), Burghouts, G.J. (author), Rothkrantz, L.J.M. (author)
This paper investigates how speech and gestures convey stress, and how they can be used for automatic stress recognition. As a first step, we look into how humans use speech and gestures to convey stress. In particular, for both speech and gestures, we distinguish between stress conveyed by the intended semantic message (e.g. spoken words for...
article 2016
document
van Aalst, W.L.C. (author), Derksen, G.B. (author), Schackmann, P.P.M. (author), Zwier, E. (author), Bouman, F.G.M. (author), Paffen, P. (author)
conference paper 2016
document
Eendebak, P.T. (author), Schoen, E.D. (author)
We study the design of two-level experiments with N runs and n factors large enough to estimate the interaction model, which contains all the main effects and all the two-factor interactions. Yet, an effect hierarchy assumption suggests that main effect estimation should be given more prominence than the estimation of two-factor interactions....
article 2016
document
Kruithof, M.C. (author), Bouma, H. (author), Fischer, N.M. (author), Schutte, K. (author)
Object recognition is important to understand the content of video and allow flexible querying in a large number of cameras, especially for security applications. Recent benchmarks show that deep convolutional neural networks are excellent approaches for object recognition. This paper describes an approach of domain transfer, where features...
conference paper 2016
document
Baart, T.A. (author), Eendebak, P.T. (author), Reichl, C. (author), Wegscheider, W. (author), Vandersypen, L.M.K. (author)
We report the computer-automated tuning of gate-defined semiconductor double quantum dots in GaAs heterostructures. We benchmark the algorithm by creating three double quantum dots inside a linear array of four quantum dots. The algorithm sets the correct gate voltages for all the gates to tune the double quantum dots into the single-electron...
article 2016
document
Dijk, J. (author), Schutte, K. (author), Nieuwenhuizen, R.P.J. (author)
Visual and infrared imagery is degraded by turbulence caused by atmospheric conditions. Because the degradation gets worse for longer distances, turbulence especially hampers long range observation. At sea this turbulence affects classification and identification of ships and other objects. State of the art software based processing algorithms...
conference paper 2016
document
van Eekeren, A.W.M. (author), van Huis, J.R. (author), Eendebak, P.T. (author), Baan, J. (author)
Airborne platforms, such as UAV's, with Wide Area Motion Imagery (WAMI) sensors can cover multiple square kilometers and produce large amounts of video data. Analyzing all data for information need purposes becomes increasingly labor-intensive for an image analyst. Furthermore, the capacity of the datalink in operational areas may be inadequate...
conference paper 2015
Searched for:
(1 - 20 of 85)

Pages