Search Results for author: Thomas B. Moeslund

Found 19 papers, 8 papers with code

Navigation-Oriented Scene Understanding for Robotic Autonomy: Learning to Segment Driveability in Egocentric Images

no code implementations15 Sep 2021 Galadrielle Humblot-Renaux, Letizia Marchegiani, Thomas B. Moeslund, Rikke Gade

In a zero-shot cross-dataset generalization experiment, we show that our affordance learning scheme can be applied across a diverse mix of datasets and improves driveability estimation in unseen environments compared to general-purpose, single-dataset segmentation.

Autonomous Navigation Decision Making +3

Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark

1 code implementation CVPR 2021 Joakim Bruslund Haurum, Thomas B. Moeslund

To this end, in this work we present a large novel and publicly available multi-label classification dataset for image-based sewer defect classification called Sewer-ML.

Classification General Classification +2

Real-World Super-Resolution of Face-Images from Surveillance Cameras

no code implementations5 Feb 2021 Andreas Aakerberg, Kamal Nasrollahi, Thomas B. Moeslund

Experimental results on both real and artificially corrupted face images show that our method results in more detailed reconstructions with less noise compared to existing State-of-the-Art (SoTA) methods.

Image Quality Assessment Image Super-Resolution

Introducing and assessing the explainable AI (XAI)method: SIDU

no code implementations26 Jan 2021 Satya M. Muddamsetty, Mohammad N. S. Jahromi, Andreea E. Ciontos, Laura M. Fenoy, Thomas B. Moeslund

Explainable Artificial Intelligence (XAI) has in recent years become a well-suited framework to generate human understandable explanations of black box models.

Adversarial Attack Explainable artificial intelligence

SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos

1 code implementation26 Nov 2020 Adrien Deliège, Anthony Cioppa, Silvio Giancola, Meisam J. Seikavandi, Jacob V. Dueholm, Kamal Nasrollahi, Bernard Ghanem, Thomas B. Moeslund, Marc Van Droogenbroeck

In this work, we propose SoccerNet-v2, a novel large-scale corpus of manual annotations for the SoccerNet video dataset, along with open challenges to encourage more research in soccer understanding and broadcast production.

Action Spotting Boundary Detection +5

SIDU: Similarity Difference and Uniqueness Method for Explainable AI

1 code implementation4 Jun 2020 Satya M. Muddamsetty, Mohammad N. S. Jahromi, Thomas B. Moeslund

A new brand of technical artificial intelligence ( Explainable AI ) research has focused on trying to open up the 'black box' and provide some explainability.

Multimodal and multiview distillation for real-time player detection on a football field

1 code implementation16 Apr 2020 Anthony Cioppa, Adrien Deliège, Noor Ul Huda, Rikke Gade, Marc Van Droogenbroeck, Thomas B. Moeslund

As an alternative, we developed a system that detects players from a unique cheap and wide-angle fisheye camera assisted by a single narrow-angle thermal camera.

Data Augmentation Knowledge Distillation +1

Effective Fusion of Deep Multitasking Representations for Robust Visual Tracking

no code implementations3 Apr 2020 Seyed Mojtaba Marvasti-Zadeh, Hossein Ghanei-Yakhdan, Shohreh Kasaei, Kamal Nasrollahi, Thomas B. Moeslund

Then, the proposed method extracts deep semantic information from a fully convolutional FEN and fuses it with the best ResNet-based feature maps to strengthen the target representation in the learning process of continuous convolution filters.

Semantic Segmentation Visual Object Tracking +1

Evaluation of Model Selection for Kernel Fragment Recognition in Corn Silage

no code implementations1 Apr 2020 Christoffer Bøgelund Rasmussen, Thomas B. Moeslund

We show that accuracy improvements can be made with more complex meta-architectures and speed can be optimised by decreasing the image size with only slight losses in accuracy.

Model Selection

Rain Removal in Traffic Surveillance: Does it Matter?

3 code implementations30 Oct 2018 Chris H. Bahnsen, Thomas B. Moeslund

We propose a new evaluation protocol that evaluates the rain removal algorithms on their ability to improve the performance of subsequent segmentation, instance segmentation, and feature tracking algorithms under rain and snow.

Instance Segmentation Rain Removal +1

The AAU Multimodal Annotation Toolboxes: Annotating Objects in Images and Videos

no code implementations10 Sep 2018 Chris H. Bahnsen, Andreas Møgelmose, Thomas B. Moeslund

This tech report gives an introduction to two annotation toolboxes that enable the creation of pixel and polygon-based masks as well as bounding boxes around objects of interest.

General Classification

A Double-Deep Spatio-Angular Learning Framework for Light Field based Face Recognition

no code implementations25 May 2018 Alireza Sepas-Moghaddam, Mohammad A. Haque, Paulo Lobato Correia, Kamal Nasrollahi, Thomas B. Moeslund, Fernando Pereira

This paper proposes a double-deep spatio-angular learning framework for light field based face recognition, which is able to learn both texture and angular dynamics in sequence using convolutional representations; this is a novel recognition framework that has never been proposed before for either face recognition or any other visual recognition task.

Face Recognition

Learning Dynamic Classes of Events using Stacked Multilayer Perceptron Networks

no code implementations23 Jun 2016 Nattiya Kanhabua, Huamin Ren, Thomas B. Moeslund

In general, event-related information needs can be observed in query streams through various temporal patterns of user search behavior, e. g., spiky peaks for popular events, and periodicities for repetitive events.

A comprehensive study of sparse codes on abnormality detection

no code implementations13 Mar 2016 Huamin Ren, Hong Pan, Søren Ingvor Olsen, Thomas B. Moeslund

Sparse representation has been applied successfully in abnormal event detection, in which the baseline is to learn a dictionary accompanied by sparse codes.

Anomaly Detection Event Detection

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