Search Results for author: Jan van Gemert

Found 50 papers, 23 papers with code

Do Object Detection Localization Errors Affect Human Performance and Trust?

no code implementations31 Jan 2024 Sven de Witte, Ombretta Strafforello, Jan van Gemert

Bounding boxes are often used to communicate automatic object detection results to humans, aiding humans in a multitude of tasks.

Object Object Counting +2

Contrast-Agnostic Groupwise Registration by Robust PCA for Quantitative Cardiac MRI

no code implementations3 Nov 2023 Xinqi Li, Yi Zhang, Yidong Zhao, Jan van Gemert, Qian Tao

To address the challenge, we propose a novel motion correction framework based on robust principle component analysis (rPCA) that decomposes quantitative cardiac MRI into low-rank and sparse components, and we integrate the groupwise CNN-based registration backbone within the rPCA framework.

End-to-End Chess Recognition

1 code implementation6 Oct 2023 Athanasios Masouris, Jan van Gemert

Chess recognition is the task of extracting the chess piece configuration from a chessboard image.


Can we predict the Most Replayed data of video streaming platforms?

1 code implementation12 Sep 2023 Alessandro Duico, Ombretta Strafforello, Jan van Gemert

To this end, we curate a large video benchmark, the YTMR500 dataset, which comprises 500 YouTube videos with MR data annotations.

SSIG: A Visually-Guided Graph Edit Distance for Floor Plan Similarity

1 code implementation8 Sep 2023 Casper van Engelenburg, Seyran Khademi, Jan van Gemert

In this paper, an effective evaluation metric for judging the structural similarity of floor plans, coined SSIG (Structural Similarity by IoU and GED), is proposed based on both image and graph distances.

Graph Matching Metric Learning +2

Are current long-term video understanding datasets long-term?

1 code implementation22 Aug 2023 Ombretta Strafforello, Klamer Schutte, Jan van Gemert

In the current deep learning paradigm for automatic action recognition, it is imperative that models are trained and tested on datasets and tasks that evaluate if such models actually learn and reason over long-term information.

Action Recognition Video Understanding

Video BagNet: short temporal receptive fields increase robustness in long-term action recognition

1 code implementation22 Aug 2023 Ombretta Strafforello, Xin Liu, Klamer Schutte, Jan van Gemert

Previous work on long-term video action recognition relies on deep 3D-convolutional models that have a large temporal receptive field (RF).

Action Recognition Temporal Action Localization

Using and Abusing Equivariance

no code implementations22 Aug 2023 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.

VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challenges

no code implementations31 May 2023 Robert-Jan Bruintjes, Attila Lengyel, Marcos Baptista Rios, Osman Semih Kayhan, Davide Zambrano, Nergis Tomen, Jan van Gemert

The third edition of the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" workshop featured four data-impaired challenges, focusing on addressing the limitations of data availability in training deep learning models for computer vision tasks.

Data Augmentation Representation Learning +1

What Affects Learned Equivariance in Deep Image Recognition Models?

no code implementations5 Apr 2023 Robert-Jan Bruintjes, Tomasz Motyka, Jan van Gemert

We therefore investigate what can increase the learned equivariance in neural networks, and find that data augmentation, reduced model capacity and inductive bias in the form of convolutions induce higher learned equivariance in neural networks.

Data Augmentation Inductive Bias +1

Understanding weight-magnitude hyperparameters in training binary networks

1 code implementation4 Mar 2023 Joris Quist, Yunqiang Li, Jan van Gemert

Our analysis makes it possible to understand how magnitude-based hyperparameters influence the training of binary networks which allows for new optimization filters specifically designed for binary neural networks that are independent of their real-valued interpretation.

Towards Single Camera Human 3D-Kinematics

1 code implementation13 Jan 2023 Marian Bittner, Wei-Tse Yang, Xucong Zhang, Ajay Seth, Jan van Gemert, Frans C. T. van der Helm

Markerless estimation of 3D Kinematics has the great potential to clinically diagnose and monitor movement disorders without referrals to expensive motion capture labs; however, current approaches are limited by performing multiple de-coupled steps to estimate the kinematics of a person from videos.

Markerless Motion Capture

Copy-Pasting Coherent Depth Regions Improves Contrastive Learning for Urban-Scene Segmentation

1 code implementation25 Nov 2022 Liang Zeng, Attila Lengyel, Nergis Tömen, Jan van Gemert

For unsupervised semantic segmentation of urban scenes, our method surpasses the previous state-of-the-art baseline by +7. 14% in mIoU on Cityscapes and +6. 65% on KITTI.

Contrastive Learning Depth Estimation +3

LAB: Learnable Activation Binarizer for Binary Neural Networks

1 code implementation25 Oct 2022 Sieger Falkena, Hadi Jamali-Rad, Jan van Gemert

Binary Neural Networks (BNNs) are receiving an upsurge of attention for bringing power-hungry deep learning towards edge devices.


Explainability of Deep Learning models for Urban Space perception

1 code implementation29 Aug 2022 Ruben Sangers, Jan van Gemert, Sander van Cranenburgh

However, the blackbox nature of deep learning models hampers urban planners to understand what landscape objects contribute to a particularly high quality or low quality urban space perception.

Decision Making Object Detection

Humans disagree with the IoU for measuring object detector localization error

1 code implementation28 Jul 2022 Ombretta Strafforello, Vanathi Rajasekart, Osman S. Kayhan, Oana Inel, Jan van Gemert

Our work is the first to evaluate IoU with humans and makes it clear that relying on IoU scores alone to evaluate localization errors might not be sufficient.

Proximally Sensitive Error for Anomaly Detection and Feature Learning

no code implementations1 Jun 2022 Amogh Gudi, Fritjof Büttner, Jan van Gemert

Mean squared error (MSE) is one of the most widely used metrics to expression differences between multi-dimensional entities, including images.

Anomaly Detection

AmsterTime: A Visual Place Recognition Benchmark Dataset for Severe Domain Shift

1 code implementation30 Mar 2022 Burak Yildiz, Seyran Khademi, Ronald Maria Siebes, Jan van Gemert

Our result credits the best accuracy to the ResNet-101 model pre-trained on the Landmarks dataset for both verification and retrieval tasks by 84% and 24%, respectively.

 Ranked #1 on Image Classification on AmsterTime (using extra training data)

Image Classification Image Retrieval +3

VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges

no code implementations21 Jan 2022 Attila Lengyel, Robert-Jan Bruintjes, Marcos Baptista Rios, Osman Semih Kayhan, Davide Zambrano, Nergis Tomen, Jan van Gemert

The second edition of the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" challenges featured five data-impaired challenges, where models are trained from scratch on a reduced number of training samples for various key computer vision tasks.

Data Augmentation Transfer Learning

NeRD++: Improved 3D-mirror symmetry learning from a single image

no code implementations23 Dec 2021 Yancong Lin, Silvia-Laura Pintea, Jan van Gemert

Experiments on both synthetic and real-world datasets show the benefit of our proposed changes for improved data efficiency and inference speed.

Inductive Bias Symmetry Detection

Domain Adaptation for Rare Classes Augmented with Synthetic Samples

no code implementations23 Oct 2021 Tuhin Das, Robert-Jan Bruintjes, Attila Lengyel, Jan van Gemert, Sara Beery

While domain adaptation is generally applied on completely synthetic source domains and real target domains, we explore how domain adaptation can be applied when only a single rare class is augmented with simulated samples.

Domain Adaptation

Heuristics2Annotate: Efficient Annotation of Large-Scale Marathon Dataset For Bounding Box Regression

no code implementations6 Apr 2021 Pranjal Singh Rajput, Yeshwanth Napolean, Jan van Gemert

Additionally, due to crowdedness and occlusion in the videos, aligning the identity of runners across multiple disjoint cameras is a challenge.

Person Re-Identification regression

Spectral Leakage and Rethinking the Kernel Size in CNNs

1 code implementation ICCV 2021 Nergis Tomen, Jan van Gemert

We show that the small size of CNN kernels make them susceptible to spectral leakage, which may induce performance-degrading artifacts.

Less bits is more: How pruning deep binary networks increases weight capacity

no code implementations1 Jan 2021 Yunqiang Li, Silvia Laura Pintea, Jan van Gemert

We make the observation that pruning weights adds the value 0 as an additional symbol and thus increases the information capacity of the network.

Real-time Webcam Heart-Rate and Variability Estimation with Clean Ground Truth for Evaluation

no code implementations31 Dec 2020 Amogh Gudi, Marian Bittner, Jan van Gemert

We introduce a refined and efficient real-time rPPG pipeline with novel filtering and motion suppression that not only estimates heart rates, but also extracts the pulse waveform to time heart beats and measure heart rate variability.

Benchmarking Heart Rate Variability

Deep Unsupervised Image Hashing by Maximizing Bit Entropy

1 code implementation22 Dec 2020 Yunqiang Li, Jan van Gemert

This layer is shown to minimize a penalized term of the Wasserstein distance between the learned continuous image features and the optimal half-half bit distribution.

Deep Hashing Semantic Retrieval

Zoom-CAM: Generating Fine-grained Pixel Annotations from Image Labels

no code implementations16 Oct 2020 Xiangwei Shi, Seyran Khademi, Yunqiang Li, Jan van Gemert

Current weakly supervised object localization and segmentation rely on class-discriminative visualization techniques to generate pseudo-labels for pixel-level training.

Segmentation Weakly-Supervised Object Localization +2

Respecting Domain Relations: Hypothesis Invariance for Domain Generalization

no code implementations15 Oct 2020 Ziqi Wang, Marco Loog, Jan van Gemert

In this work, we define DIRs employed by existing works in probabilistic terms and show that by learning DIRs, overly strict requirements are imposed concerning the invariance.

Domain Generalization

WeightAlign: Normalizing Activations by Weight Alignment

no code implementations14 Oct 2020 Xiangwei Shi, Yunqiang Li, Xin Liu, Jan van Gemert

Such methods are less stable than BN as they critically depend on the statistics of a single input sample.

Domain Adaptation Semantic Segmentation

Efficiency in Real-time Webcam Gaze Tracking

no code implementations2 Sep 2020 Amogh Gudi, Xin Li, Jan van Gemert

To do so, we evaluate the computational speed/accuracy trade-off for the CNN and the calibration effort/accuracy trade-off for screen calibration.

Computational Efficiency regression

Black Magic in Deep Learning: How Human Skill Impacts Network Training

1 code implementation13 Aug 2020 Kanav Anand, Ziqi Wang, Marco Loog, Jan van Gemert

Our study investigates the subjective human factor in comparisons of state of the art results and scientific reproducibility in deep learning.

Hyperparameter Optimization

Evaluating the performance of the LIME and Grad-CAM explanation methods on a LEGO multi-label image classification task

no code implementations4 Aug 2020 David Cian, Jan van Gemert, Attila Lengyel

In this paper, we run two methods of explanation, namely LIME and Grad-CAM, on a convolutional neural network trained to label images with the LEGO bricks that are visible in them.

Multi-Label Image Classification

Attention-Aware Age-Agnostic Visual Place Recognition

no code implementations11 Sep 2019 Ziqi Wang, Jiahui Li, Seyran Khademi, Jan van Gemert

Different from conventional VPR settings where the query images and gallery images come from the same domain, we propose a more common but challenging setup where the query images are collected under a new unseen condition.

Domain Adaptation Image Retrieval +3

Running Event Visualization using Videos from Multiple Cameras

no code implementations6 Sep 2019 Yeshwanth Napolean, Priadi Teguh Wibowo, Jan van Gemert

To this end, we identify two methods for runner identification at different points of the event, for determining their trajectory.

Person Re-Identification Scene Text Detection +2

Push for Quantization: Deep Fisher Hashing

no code implementations31 Aug 2019 Yunqiang Li, Wenjie Pei, Yufei zha, Jan van Gemert

In this paper we push for quantization: We optimize maximum class separability in the binary space.

Quantization Semantic Similarity +1

Deep Visual City Recognition Visualization

1 code implementation6 May 2019 Xiangwei Shi, Seyran Khademi, Jan van Gemert

(ii) A pretrained semantic segmentation model is used to label objects in pixel level, and then we introduce statistical measures to quantitatively evaluate the interpretability of discriminate objects.

Image Classification Semantic Segmentation

ViDeNN: Deep Blind Video Denoising

1 code implementation24 Apr 2019 Michele Claus, Jan van Gemert

We propose ViDeNN: a CNN for Video Denoising without prior knowledge on the noise distribution (blind denoising).

Denoising Test +1

Object-Extent Pooling for Weakly Supervised Single-Shot Localization

no code implementations19 Jul 2017 Amogh Gudi, Nicolai van Rosmalen, Marco Loog, Jan van Gemert

To facilitate this, we propose a novel global pooling technique called Spatial Pyramid Averaged Max (SPAM) pooling for training this CAM-based network for object extent localisation with only weak image-level supervision.

Object Region Proposal +1

One-Step Time-Dependent Future Video Frame Prediction with a Convolutional Encoder-Decoder Neural Network

no code implementations14 Feb 2017 Vedran Vukotić, Silvia-Laura Pintea, Christian Raymond, Guillaume Gravier, Jan van Gemert

There is an inherent need for autonomous cars, drones, and other robots to have a notion of how their environment behaves and to anticipate changes in the near future.

Optical Flow Estimation

Tubelets: Unsupervised action proposals from spatiotemporal super-voxels

no code implementations7 Jul 2016 Mihir Jain, Jan van Gemert, Hervé Jégou, Patrick Bouthemy, Cees G. M. Snoek

First, inspired by selective search for object proposals, we introduce an approach to generate action proposals from spatiotemporal super-voxels in an unsupervised manner, we call them Tubelets.

Action Localization

Structured Receptive Fields in CNNs

3 code implementations CVPR 2016 Jörn-Henrik Jacobsen, Jan van Gemert, Zhongyu Lou, Arnold W. M. Smeulders

We combine these ideas into structured receptive field networks, a model which has a fixed filter basis and yet retains the flexibility of CNNs.

Action Localization with Tubelets from Motion

no code implementations CVPR 2014 Mihir Jain, Jan van Gemert, Herve Jegou, Patrick Bouthemy, Cees G. M. Snoek

Our approach significantly outperforms the state-of-the-art on both datasets, while restricting the search of actions to a fraction of possible bounding box sequences.

Action Localization

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