Search Results for author: Jan C. van Gemert

Found 32 papers, 15 papers with code

Evaluating Context for Deep Object Detectors

1 code implementation5 May 2022 Osman Semih Kayhan, Jan C. van Gemert

Which object detector is suitable for your context sensitive task?

Equal Bits: Enforcing Equally Distributed Binary Network Weights

1 code implementation2 Dec 2021 Yunqiang Li, Silvia L. Pintea, Jan C. van Gemert

We investigate experimentally that equal bit ratios are indeed preferable and show that our method leads to optimization benefits.

Binarization Quantization

Frequency learning for structured CNN filters with Gaussian fractional derivatives

no code implementations12 Nov 2021 Nikhil Saldanha, Silvia L. Pintea, Jan C. van Gemert, Nergis Tomen

Frequency information lies at the base of discriminating between textures, and therefore between different objects.

FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes

1 code implementation ICLR 2022 David W. Romero, Robert-Jan Bruintjes, Jakub M. Tomczak, Erik J. Bekkers, Mark Hoogendoorn, Jan C. van Gemert

In this work, we propose FlexConv, a novel convolutional operation with which high bandwidth convolutional kernels of learnable kernel size can be learned at a fixed parameter cost.

 Ranked #1 on Time Series on Speech Commands (% Test Accuracy (Raw Data) metric)

Sequential Image Classification Time Series

Investigating transformers in the decomposition of polygonal shapes as point collections

no code implementations17 Aug 2021 Andrea Alfieri, Yancong Lin, Jan C. van Gemert

Transformers can generate predictions in two approaches: 1. auto-regressively by conditioning each sequence element on the previous ones, or 2. directly produce an output sequences in parallel.

Zero-Shot Day-Night Domain Adaptation with a Physics Prior

1 code implementation ICCV 2021 Attila Lengyel, Sourav Garg, Michael Milford, Jan C. van Gemert

The traditional domain adaptation setting is to train on one domain and adapt to the target domain by exploiting unlabeled data samples from the test set.

Domain Adaptation Semantic Segmentation

The Arm-Swing Is Discriminative in Video Gait Recognition for Athlete Re-Identification

no code implementations21 Jun 2021 Yapkan Choi, Yeshwanth Napolean, Jan C. van Gemert

In this paper we evaluate running gait as an attribute for video person re-identification in a long-distance running event.

Gait Recognition Semantic Parsing +1

Exploiting Learned Symmetries in Group Equivariant Convolutions

1 code implementation9 Jun 2021 Attila Lengyel, Jan C. van Gemert

Group Equivariant Convolutions (GConvs) enable convolutional neural networks to be equivariant to various transformation groups, but at an additional parameter and compute cost.

Resolution learning in deep convolutional networks using scale-space theory

1 code implementation7 Jun 2021 Silvia L. Pintea, Nergis Tomen, Stanley F. Goes, Marco Loog, Jan C. van Gemert

We use scale-space theory to obtain a self-similar parametrization of filters and make use of the N-Jet: a truncated Taylor series to approximate a filter by a learned combination of Gaussian derivative filters.

Hallucination In Object Detection -- A Study In Visual Part Verification

1 code implementation4 Jun 2021 Osman Semih Kayhan, Bart Vredebregt, Jan C. van Gemert

We show that object detectors can hallucinate and detect missing objects; potentially even accurately localized at their expected, but non-existing, position.

Object Detection

t-EVA: Time-Efficient t-SNE Video Annotation

no code implementations26 Nov 2020 Soroosh Poorgholi, Osman Semih Kayhan, Jan C. van Gemert

Video understanding has received more attention in the past few years due to the availability of several large-scale video datasets.

Dimensionality Reduction Video Classification +1

Deep Hough-Transform Line Priors

1 code implementation ECCV 2020 Yancong Lin, Silvia L. Pintea, Jan C. van Gemert

Here, we reduce the dependency on labeled data by building on the classic knowledge-based priors while using deep networks to learn features.

Line Segment Detection

Top-Down Networks: A coarse-to-fine reimagination of CNNs

1 code implementation16 Apr 2020 Ioannis Lelekas, Nergis Tomen, Silvia L. Pintea, Jan C. van Gemert

Biological vision adopts a coarse-to-fine information processing pathway, from initial visual detection and binding of salient features of a visual scene, to the enhanced and preferential processing given relevant stimuli.

Decision Making

Cross Domain Image Matching in Presence of Outliers

no code implementations8 Sep 2019 Xin Liu, Seyran Khademi, Jan C. van Gemert

Cross domain image matching between image collections from different source and target domains is challenging in times of deep learning due to i) limited variation of image conditions in a training set, ii) lack of paired-image labels during training, iii) the existing of outliers that makes image matching domains not fully overlap.

Domain Adaptation Outlier Detection

Using phase instead of optical flow for action recognition

1 code implementation10 Sep 2018 Omar Hommos, Silvia L. Pintea, Pascal S. M. Mettes, Jan C. van Gemert

We design these complex filters to resemble complex Gabor filters, typically employed for phase-information extraction.

Action Recognition Frame +2

Hand-tremor frequency estimation in videos

no code implementations10 Sep 2018 Silvia L. Pintea, Jian Zheng, XiLin Li, Paulina J. M. Bank, Jacobus J. van Hilten, Jan C. van Gemert

We focus on the problem of estimating human hand-tremor frequency from input RGB video data.


Recurrent knowledge distillation

no code implementations18 May 2018 Silvia L. Pintea, Yue Liu, Jan C. van Gemert

Knowledge distillation compacts deep networks by letting a small student network learn from a large teacher network.

Knowledge Distillation

Deja Vu: Motion Prediction in Static Images

no code implementations19 Mar 2018 Silvia L. Pintea, Jan C. van Gemert, Arnold W. M. Smeulders

This paper proposes motion prediction in single still images by learning it from a set of videos.

Action Recognition Frame +1

Featureless: Bypassing feature extraction in action categorization

no code implementations19 Mar 2018 Silvia L. Pintea, Pascal S. Mettes, Jan C. van Gemert, Arnold W. M. Smeulders

This method introduces an efficient manner of learning action categories without the need of feature estimation.

Action Recognition

Asymmetric kernel in Gaussian Processes for learning target variance

no code implementations19 Mar 2018 Silvia L. Pintea, Jan C. van Gemert, Arnold W. M. Smeulders

This enables each center to adjust the kernel space in its vicinity in correspondence with the topology of the targets --- a multi-modal approach.

Gaussian Processes Metric Learning

Video Acceleration Magnification

no code implementations CVPR 2017 Yichao Zhang, Silvia L. Pintea, Jan C. van Gemert

In these contexts there is often large motion present which severely distorts current video amplification methods that magnify change linearly.

Optical Flow Estimation

Active Decision Boundary Annotation with Deep Generative Models

1 code implementation ICCV 2017 Miriam W. Huijser, Jan C. van Gemert

This paper is on active learning where the goal is to reduce the data annotation burden by interacting with a (human) oracle during training.

Active Learning

Searching Scenes by Abstracting Things

no code implementations6 Oct 2016 Svetlana Kordumova, Jan C. van Gemert, Cees G. M. Snoek, Arnold W. M. Smeulders

Second, we propose translating the things syntax in linguistic abstract statements and study their descriptive effect to retrieve scenes.

Spot On: Action Localization from Pointly-Supervised Proposals

no code implementations26 Apr 2016 Pascal Mettes, Jan C. van Gemert, Cees G. M. Snoek

Rather than annotating boxes, we propose to annotate actions in video with points on a sparse subset of frames only.

Action Localization Multiple Instance Learning +1

Evaluation of Color STIPs for Human Action Recognition

no code implementations CVPR 2013 Ivo Everts, Jan C. van Gemert, Theo Gevers

Existing STIP-based action recognition approaches operate on intensity representations of the image data.

Action Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.