People

Thomas Moeslund

P1 Collaboratory Co-Lead and Professor, Aalborg University

Department of Architecture, Design and Media Technology

Thomas's P1 Publications

Post-hoc XAI method for Visual Question Answering(VQA)

Satya M. Muddamsetty, Alina B. Schmidt, Thomas B. Moeslund

Harborfront Anomaly Detection
Jacob V. Dueholm, Mia Siemon, Radu T. Ionescu, Thomas B. Moeslund, Kamal Nasrollahi
Verifying Machine Unlearning with Explainable AI
Àlex P. Vidal, Anders S. Johansen, Mohammad N. S. Jahromi, Sergio Escalera, Kamal Nasrollahi, Thomas B. Moeslund
Bounding Boxes and Probabilistic Graphical Models
Mia Siemon, Thomas B. Moeslund, Barry Norton, Kamal Nasrollahi
What is Proactive Human-Robot Interaction? – A Review of a Progressive Field and Its Definitions
Marike K. van Den Broek, Thomas B. Moeslund
UPAR Challenge 2024: Pedestrian Attribute Recognition and Attribute-Based Person Retrieval – Dataset, Design, and Results
Mickael Cormier, Andreas Specker, Julio C. S. Jacques, Lennart Moritz, Jürgen Metzler, Thomas B. Moeslund
Underwater Uncertainty: A Multi-Annotator Image Dataset for Benthic Habitat Classification
Galadrielle Humblot-Renaux, Anders S. Johansen, Jonathan E. Schmidt, Amanda F. Irlind, Niels Madsen, Thomas B. Moeslund, Malte Pedersen
The (Computer) Vision of Sports: Recent Trends in Research and Commercial Systems for Sport Analytics
Rikke Gade, Michele Merler, Graham Thomas, Thomas B. Moeslund
T-DEED: Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in Sports Videos
Artur Xarles, Sergio Escalera, Thomas B. Moeslund, Albert Clapés
Swin on Axes: Extending Swin Transformers to Quadtree Image Representations
Thomas B. Moeslund
SoccerNet 2023 challenges results (Review article)
Anthony Cioppa, Silvio Giancola, Vladimir Somers, Floriane Magera, Xin Zhou, Hassan Mkhallati, Adrien Deliège, Jan Held, Carlos Hinojosa, Amir M. Mansourian, Pierre Miralles, Olivier Barnich, Christophe De Vleeschouwer, Alexandre Alahi, Bernard Ghanem, Marc Van Droogenbroeck, Abdullah Kamal, Adrien Maglo, Albert Clapés, Amr Abdelaziz, Artur Xarles, Astrid Orcesi, Atom Scott, Bin Liu, Byoungkwon Lim, Chen Chen, Fabian Deuser, Feng Yan, Fufu Yu, Gal Shitrit, Guanshuo Wang, Gyusik Choi, Hankyul Kim, Hao Guo, Hasby Fahrudin, Hidenari Koguchi, Håkan Ardö, Ibrahim Salah, Ido Yerushalmy, Iftikar Muhammad, Ikuma Uchida, Ishay Be'ery, Jaonary Rabarisoa, Jeongae Lee, Jiajun Fu, Jianqin Yin, Jinghang Xu, Jongho Nang, Julien Denize, Junjie Li, Junpei Zhang, Juntae Kim, Kamil Synowiec, Kenji Kobayashi, Kexin Zhang, Konrad Habel, Kota Nakajima, Licheng Jiao, Lin Ma, Lizhi Wang, Luping Wang, Menglong Li, Mengying Zhou, Mohamed Nasr, Mohamed Abdelwahed, Mykola Liashuha, Nikolay Falaleev, Norbert Oswald, Qiong Jia, Quoc-Cuong Pham, Ran Song, Romain Hérault, Rui Peng, Ruilong Chen, Ruixuan Liu, Ruslan Baikulov, Ryuto Fukushima, Sergio Escalera, Seungcheon Lee, Shimin Chen, Shouhong Ding, Taiga Someya, Thomas B. Moeslund, Tianjiao Li, Wei Shen, Wei Zhang, Wei Li, Wei Dai, Weixin Luo, Wending Zhao, Wenjie Zhang, Xinquan Yang, Yanbiao Ma, Yeeun Joo, Yingsen Zeng, Yiyang Gan, Yongqiang Zhu, Yujie Zhong, Zheng Ruan, Zhiheng Li, Zhijian Huang, Ziyu Meng
SIDU-TXT: An XAI algorithm for NLP with a holistic assessment approach
Radu T. Ionescu, Kamal Nasrollahi, Fahad S. Khan, Thomas B. Moeslund
Remote Tongue-based Control of a Wheelchair Mounted Assistive Robotic Manipulator and the Effect of Adaptive Semi-automation
Ásgerður Pálsdóttir, Rasmus L. Kæseler, Stefan H. Bengtson, Thomas B. Moeslund, Lotte N. S. A. Struijk
PDA-RWSR: Pixel-Wise Degradation Adaptive Real-World Super-Resolution
Andreas Aakerberg, Majed El Helou, Kamal Nasrollahi, Thomas B. Moeslund
OpenTrench3D: A Photogrammetric 3D Point Cloud Dataset for Semantic Segmentation of Underground Utilities
Lasse H. Hansen, Simon B. Jensen, Mark P. Philipsen, Andreas Møgelmose, Lars Bodum, Thomas B. Moeslund
Exploring the Limits: Applying State-of-the-Art Stereo Matching Algorithms to Rectified Ultra-Wide Stereo
Filip Slezák, Morten S. Laursen, Thomas B. Moeslund
Enhancing Direct Visual Odometry with Deblurring and Saliency Maps
Magnus K. Gjerde, Kamal Nasrollahi, Thomas B. Moeslund, Joakim B. Haurum
Enabling RAW Image Classification Using Existing RGB Classifiers
Rasmus Munksø, Mathias V. Andersen, Lau Nørgaard, Andreas Møgelmose, Thomas B. Moeslund
CL-MAE: Curriculum-Learned Masked Autoencoders
Neelu Madan, Nicolae C. Ristea, Kamal Nasrollahi, Thomas B. Moeslund, Radu T. Ionescu
Agglomerative Token Clustering
Joakim B. Haurum, Sergio Escalera, Graham W. Taylor, Thomas B. Moeslund
Advantages and Limitations of Using Cameras on Small, Low-Cost ROVS for Seabed Monitoring (Review Article)
Amanda F. Irlind, Alex Jørgensen, Jonathan E. Schmidt, Anders S. Johansen, Thomas B. Moeslund, Karen A. Sønnichsen, Niels Madsen
A Noisy Elephant in the Room: Is Your out-of-Distribution Detector Robust to Label Noise?
Galadrielle Humblot-Renaux, Sergio Escalera, Thomas B. Moeslund
Finding Nemo’s Giant Cousin: Keypoint Matching for Robust Re-Identification of Giant Sunfish
Malte Pedersen, Marianne Nyegaard, Thomas B. Moeslund
Explainable AI and Law: An Evidential Survey
Karen McGregor Richmond, Satya M. Muddamsetty, Thomas Gammeltoft-Hansen, Henrik P. Olsen, Thomas B. Moeslund
BrackishMOT: The Brackish Multi-Object Tracking Dataset
Malte Pedersen, Daniel Lehotský, Ivan Nikolov, Thomas B. Moeslund
Beyond AUROC & co. for evaluating out-of-distribution detection performance
Galadrielle Humblot-Renaux, Sergio Escalera, Thomas B. Moeslund
Video Transformers: A Survey
Javier Selva, Anders S. Johansen, Sergio Escalera, Kamal Nasrollahi, Thomas B. Moeslund, Albert Clapés
Which Tokens to Use? Investigating Token Reduction in Vision Transformers
Joakim B. Haurum, Sergio Escalera, Graham W. Taylor, Thomas B. Moeslund
Interpretation of convolutional neural networks for acid sulfate soil classification
Amelie Beucher, Christoffer B. Rasmussen, Thomas B. Moeslund, Mogens H. Greve
Real-world super-resolution of face-images from surveillance cameras
Andreas Aakerberg, Kamal Nasrollahi, Thomas B. Moeslund
Data-Driven Drift Detection in Real Process Tanks: Bridging the Gap between Academia and Practice
Bolette D. Hansen, Thomas B. Hansen, Thomas B. Moeslund, David G. Jensen
The Challenge of Data Annotation in Deep Learning—A Case Study on Whole Plant Corn Silage
Christoffer B. Rasmussen, Kristian Kirk, Thomas B. Moeslund
ChaLearn LAP Challenges on Self-Reported Personality Recognition and Non-Verbal Behavior Forecasting During Social Dyadic Interactions: Dataset, Design, and Results
Cristina Palmero, German Barquero, Julio C. S. J. Junior, Albert Clapés, Johnny Núñez, David Curto, Sorina Smeureanu, Javier Selva, Zejian Zhang, David Saeteros, David Gallardo-Pujol, Georgina Guilera, David Leiva, Feng Han, Xiaoxue Feng, Jennifer He, Wei-Wei Tu, Thomas B. Moeslund, Isabelle Guyon, Sergio Escalera
Anomaly Detection for Agricultural Vehicles Using Autoencoders
Esma Mujkic, Mark P. Philipsen, Thomas B. Moeslund, Martin P. Christiansen, Ole Ravn
Autoencoders for Semi-Supervised Water Level Modeling in Sewer Pipes with Sparse Labeled Data
Ferran P. Rius, Mark P. Philipsen, Josep M. M. Tur, Thomas B. Moeslund, Cecilio A. Bahón, Marc Casas
Navigation-Oriented Scene Understanding for Robotic Autonomy: Learning to Segment Driveability in Egocentric Images
Galadrielle Humblot-Renaux, Letizia Marchegiani, Thomas B. Moeslund, Rikke Gade
Imitating Emergencies: Generating Thermal Surveillance Fall Data Using Low-Cost Human-like Dolls
Ivan Nikolov, Jinsong Liu, Thomas B. Moeslund
Clothing Insulation Rate and Metabolic Rate Estimation for Individual Thermal Comfort Assessment in Real Life
Jinsong Liu, Isak W. Foged, Thomas B. Moeslund
Multi-scale hybrid vision transformer and Sinkhorn tokenizer for sewer defect classification
Joakim B. Haurum, Meysam Madadi, Sergio Escalera, Thomas B. Moeslund
User Based Development and Test of the EXOTIC Exoskeleton: Empowering Individuals with Tetraplegia Using a Compact, Versatile, 5-DoF Upper Limb Exoskeleton Controlled through Intelligent Semi-Automated Shared Tongue Control
Mikkel B. Thøgersen, Mostafa Mahammadi, Muhammad A. Gull, Stefan H. Bengtson, Frederik V. Kobbelgaard, Bo Bentsen, Benjamin Y. A. Khan, Kåre E. Severinsen, Shaoping Bai, Thomas Bak, Thomas B. Moeslund, Anne M. Kanstrup, Lotte N. S. A. Struijk
Visual explanation of black-box model: Similarity Difference and Uniqueness (SIDU) method
Satya M. Muddamsetty, Mohammad N. S. Jahromi, Andreea E. Ciontos, Laura M. Fenoy, Thomas B. Moeslund
Computer Vision-Based Adaptive Semi-Autonomous Control of an Upper Limb Exoskeleton for Individuals with Tetraplegia
Stefan H. Bengtson, Mikkel B. Thøgersen, Mostafa Mohammadi, Frederik V. Kobbelgaard, Muhammad A. Gull, Lotte N. S. A. Struijk, Thomas Bak, Thomas B. Moeslund
Presenting a Novel Pipeline for Performance Comparison of V-PCC and G-PCC Point Cloud Compression Methods on Datasets with Varying Properties
Albert Christensen, Daniel Lehotský, Mathias Poulsen, Thomas B. Moeslund
Semantic Segmentation Guided Real-World Super-Resolution
Andreas Aakerberg, Anders S. Johansen, Kamal Nasrollahi, Thomas B. Moeslund
SieveNet: Estimating the Particle Size Distribution of Kernel Fragments in Whole Plant Corn Silage
Christoffer B. Rasmussen, Kristian Kirk, Thomas B. Moeslund
Detecting Anomalies Reliably in Long-term Surveillance Systems
Jinsong Liu, Ivan Nikolov, Mark P. Philipsen, Thomas B. Moeslund
Multi-Task Classification og Sewer Pipe Defects and Properties using a Cross-Task Graph Neural Network Decoder
Joakim B. Haurum, Meysam Madadi, Sergio Escalera, Thomas B. Moeslund
Exploring loss functions for optimising the accuracy of Siamese neural networks in re-identification applications
Jonathan E. Schmidt, Oscar E. Mäkinen, Simon G. F. Nielsen, Anders S. Johansen, Kamal Nasrollahi, Thomas B. Moeslund
MOTCOM: The Multi-Object Tracking Dataset Complexity Metric
Malte Pedersen, Joakim B. Haurum, Patrick Dendorfer, Thomas B. Moeslund
Re-Identification of Giant Sunfish using Keypoint Matching
Malte Pedersen, Joakim B. Haurum, Thomas B. Moeslund, Marianne Nyegaard
Autonomous monitoring of finishing pigs using side-view cameras and deep learning
Mathias S. Lynge, Kasper S. Henriksen, Thomas B. Moeslund
Real-World Thermal Image Super-Resolution
Moaaz M. J. Allahham, Andreas Aakerberg, Kamal Nasrollahi, Thomas B. Moeslund
Attention-Enabled Object Detection to Improve One-Stage Tracker
Neelu Madan, Kamal Nasrollahi, Thomas B. Moeslund
Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection
Nicolae-Cătălin Ristea, Neelu Madan, Radu T. Ionescu, Kamal Nasrollahi, Fahad S. Khan, Thomas B. Moeslund, Mubarak Shah
SoccerNet 2022 Challenges Results
Silvio Giancola, Anthony Cioppa, Adrien Deliège, Floriane Magera, Vladimir Somers, Le Kang, Xin Zhou, Olivier Barnich, Christophe De Vleeschouwer, Alexandre Alahi, Bernard Ghanem, Marc Van Droogenbroeck, Abdulrahman Darwish, Adrien Maglo, Albert Clapés, Andreas Luyts, Andrei Boiarov, Artur Xarles, Astrid Orcesi, Avijit Shah, Baoyu Fan, Bharath Comandur, Chen Chen, Chen Zhang, Chen Zhao, Chengzhi Lin, Cheuk-Yiu Chan, Chun C. Hui, Dengjie Li, Fan Yang, Fan Liang, Fang Da, Feng Yan, Fufu Yu, Guanshuo Wang, H. A. Chan, He Zhu, Hongwei Kan, Jiaming Chu, Jianming Hu, Jianyang Gu, Jin Chen, João V. B. Soares, Jonas Theiner, Jorge De Corte, José H. Brito, Jun Zhang, Junjie Li, Junwei Liang, Leqi Shen, Lin Ma, Lingchi Chen, Miguel S. Marques, Mike Azatov, Nikita Kasatkin, Ning Wang, Qiong Jia, Quoc C. Pham, Ralph Ewerth, Ran Song, Rengang Li, Rikke Gade, Ruben Debien, Runze Zhang, Sangrok Lee, Sergio Escalera, Shan Jiang, Shigeyuki Odashima, Shimin Chen, Shoichi Masui, Shouhong Ding, Sin-wai Chan, Siyu Chen, Tallal El-Shabrawy, Tao He, Thomas B. Moeslund, Wan-Chi Siu, Wei Zhang, Wei Li, Xiangwei Wang, Xiao Tan, Xiaochuan Li, Xiaolin Wei, Xiaoqing Ye, Xing Liu, Xinying Wang, Yandong Guo, Yaqian Zhao, Yi Yu, Yingying Li, Yue He, Yujie Zhong, Zhenhua Guo, Zhiheng Li
Deep Learning-based Anomaly Detection on X-ray Images of Fuel Cell Electrodes
Simon B. Jensen, Thomas B. Moeslund, Søren J. Andreasen

View all People

People

Thomas Moeslund

P1 Collaboratory Co-Lead and Professor, Aalborg University

Department of Architecture, Design and Media Technology

Contact

Collaboratory

Websites

Collaboratories

FG

Fine grained analysis

Thomas's P1 Publications

Post-hoc XAI method for Visual Question Answering(VQA)

Harborfront Anomaly Detection

Verifying Machine Unlearning with Explainable AI

Bounding Boxes and Probabilistic Graphical Models

What is Proactive Human-Robot Interaction? – A Review of a Progressive Field and Its Definitions

UPAR Challenge 2024: Pedestrian Attribute Recognition and Attribute-Based Person Retrieval – Dataset, Design, and Results

Underwater Uncertainty: A Multi-Annotator Image Dataset for Benthic Habitat Classification

The (Computer) Vision of Sports: Recent Trends in Research and Commercial Systems for Sport Analytics

T-DEED: Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in Sports Videos

Swin on Axes: Extending Swin Transformers to Quadtree Image Representations

SoccerNet 2023 challenges results (Review article)

SIDU-TXT: An XAI algorithm for NLP with a holistic assessment approach

Remote Tongue-based Control of a Wheelchair Mounted Assistive Robotic Manipulator and the Effect of Adaptive Semi-automation

PDA-RWSR: Pixel-Wise Degradation Adaptive Real-World Super-Resolution

OpenTrench3D: A Photogrammetric 3D Point Cloud Dataset for Semantic Segmentation of Underground Utilities

Exploring the Limits: Applying State-of-the-Art Stereo Matching Algorithms to Rectified Ultra-Wide Stereo

Enhancing Direct Visual Odometry with Deblurring and Saliency Maps

Enabling RAW Image Classification Using Existing RGB Classifiers

CL-MAE: Curriculum-Learned Masked Autoencoders

Agglomerative Token Clustering

Advantages and Limitations of Using Cameras on Small, Low-Cost ROVS for Seabed Monitoring (Review Article)

A Noisy Elephant in the Room: Is Your out-of-Distribution Detector Robust to Label Noise?

Finding Nemo’s Giant Cousin: Keypoint Matching for Robust Re-Identification of Giant Sunfish

Explainable AI and Law: An Evidential Survey

BrackishMOT: The Brackish Multi-Object Tracking Dataset

Beyond AUROC & co. for evaluating out-of-distribution detection performance

Video Transformers: A Survey

Which Tokens to Use? Investigating Token Reduction in Vision Transformers

Interpretation of convolutional neural networks for acid sulfate soil classification

Real-world super-resolution of face-images from surveillance cameras

Data-Driven Drift Detection in Real Process Tanks: Bridging the Gap between Academia and Practice

The Challenge of Data Annotation in Deep Learning—A Case Study on Whole Plant Corn Silage

ChaLearn LAP Challenges on Self-Reported Personality Recognition and Non-Verbal Behavior Forecasting During Social Dyadic Interactions: Dataset, Design, and Results

Anomaly Detection for Agricultural Vehicles Using Autoencoders

Autoencoders for Semi-Supervised Water Level Modeling in Sewer Pipes with Sparse Labeled Data

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

Imitating Emergencies: Generating Thermal Surveillance Fall Data Using Low-Cost Human-like Dolls

Clothing Insulation Rate and Metabolic Rate Estimation for Individual Thermal Comfort Assessment in Real Life

Multi-scale hybrid vision transformer and Sinkhorn tokenizer for sewer defect classification

User Based Development and Test of the EXOTIC Exoskeleton: Empowering Individuals with Tetraplegia Using a Compact, Versatile, 5-DoF Upper Limb Exoskeleton Controlled through Intelligent Semi-Automated Shared Tongue Control

Visual explanation of black-box model: Similarity Difference and Uniqueness (SIDU) method

Computer Vision-Based Adaptive Semi-Autonomous Control of an Upper Limb Exoskeleton for Individuals with Tetraplegia

Presenting a Novel Pipeline for Performance Comparison of V-PCC and G-PCC Point Cloud Compression Methods on Datasets with Varying Properties

Semantic Segmentation Guided Real-World Super-Resolution

SieveNet: Estimating the Particle Size Distribution of Kernel Fragments in Whole Plant Corn Silage

Detecting Anomalies Reliably in Long-term Surveillance Systems

Multi-Task Classification og Sewer Pipe Defects and Properties using a Cross-Task Graph Neural Network Decoder

Exploring loss functions for optimising the accuracy of Siamese neural networks in re-identification applications

MOTCOM: The Multi-Object Tracking Dataset Complexity Metric

Re-Identification of Giant Sunfish using Keypoint Matching

Autonomous monitoring of finishing pigs using side-view cameras and deep learning

Real-World Thermal Image Super-Resolution

Attention-Enabled Object Detection to Improve One-Stage Tracker

Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection

SoccerNet 2022 Challenges Results

Deep Learning-based Anomaly Detection on X-ray Images of Fuel Cell Electrodes