23 citations · 57 across the 37 of their papers we have counts for
8 papers · 1 filter
End-to-End Chess Recognition
Athanasios Masouris, Jan van Gemert
Chess recognition is the task of extracting the chess piece configuration from a chessboard image. Current approaches use a pipeline of separate, independent, modules such as chess…
SSIG: A Visually-Guided Graph Edit Distance for Floor Plan Similarity
Casper van Engelenburg, Seyran Khademi, Jan van Gemert
We propose a simple yet effective metric that measures structural similarity between visual instances of architectural floor plans, without the need for learning. Qualitatively, ou…
Using and Abusing Equivariance
Tom Edixhoven, Attila Lengyel, Jan van Gemert
In this paper we show how Group Equivariant Convolutional Neural Networks use subsampling to learn to break equivariance to their symmetries. We focus on 2D rotations and reflectio…
Are current long-term video understanding datasets long-term?
Ombretta Strafforello, Klamer Schutte, Jan van Gemert
Many real-world applications, from sport analysis to surveillance, benefit from automatic long-term action recognition. In the current deep learning paradigm for automatic action r…
A step towards understanding why classification helps regression
Silvia L. Pintea, Yancong Lin, Jouke Dijkstra +1
A number of computer vision deep regression approaches report improved results when adding a classification loss to the regression loss. Here, we explore why this is useful in prac…
Is there progress in activity progress prediction?
Frans de Boer, Jan C. van Gemert, Jouke Dijkstra +1
Activity progress prediction aims to estimate what percentage of an activity has been completed. Currently this is done with machine learning approaches, trained and evaluated on c…
Understanding weight-magnitude hyperparameters in training binary networks
Joris Quist, Yunqiang Li, Jan van Gemert
Binary Neural Networks (BNNs) are compact and efficient by using binary weights instead of real-valued weights. Current BNNs use latent real-valued weights during training, where s…
Towards Single Camera Human 3D-Kinematics
Marian Bittner, Wei-Tse Yang, Xucong Zhang +3
Markerless estimation of 3D Kinematics has the great potential to clinically diagnose and monitor movement disorders without referrals to expensive motion capture labs; however, cu…