Research

P1 Publications

  • Interspeech 2025

    AxLSTMs: learning self-supervised audio representations with xLSTMs

    Sarthak Yadav, Sergios Theodoridis, Zheng‐Hua Tan

  • 2025 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)

    AutoFish: Dataset and Benchmark for Fine-Grained Analysis of Fish

    Stefan H. Bengtson, Daniel Lehotský, Vasiliki Ismiroglou, Niels Madsen, Thomas B. Moeslund, Malte Pedersen

  • 2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)

    AudioMAE++: Learning Better Masked Audio Representations with Swiglu FFNS

    Sarthak Yadav, Sergios Theodoridis, Zheng‐Hua Tan

  • UIST '25: Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology

    At a Glance to Your Fingertips: Enabling Direct Manipulation of Distant Objects Through SightWarp

    Yang Liu, Thorbjørn Mikkelsen, Zehai Liu, Gengchen Tian, Diako Mardanbegi, Qiushi Zhou, Hans Gellersen, Ken Pfeuffer

  • Image Analysis (SCIA 2025)

    Assessing the Efficacy of Multi-task Learning in Mammographic Density Classification: A Study on Class Imbalance and Model Performance

    Suaiba A. Salahuddin, Elisabeth Wetzer, Kristoffer Wickstrøm, Solveig Thrun, Michael Kampffmeyer, Robert Jenssen

  • Image Analysis (SCIA 2025)

    Are Generative Models Fair? A Study of Racial Bias in Dermatological Image Generation

    Miguel López-Pérez, Søren Hauberg, Aasa Feragen

  • Interspeech 2025

    Analysis and Extension of a Near-End Listening Enhancement Method Based on Long-Term Fractile Noise Statistics

    Filippo Villani, Wai-Yip Chan, Zheng‐Hua Tan, Jan Østergaard, Jesper Jensen

  • Proceedings of The 28th International Conference on Artificial Intelligence and Statistics

    All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling

    Emanuele Marconato, Sébastien Lachapelle, Sebastian Weichwald, Luigi Gresele

  • Proceedings of the 42nd International Conference on Machine Learning

    Aggregation of Dependent Expert Distributions in Multimodal Variational Autoencoders

    Rogelio A. Mancisidor, Robert Jenssen, Shujian Yu, Michael Kampffmeyer

  • Technology, Mind, and Behavior

    Adopting the intentional stance affects social attention when interacting with a humanoid robot.

    Serena Marchesi, Kyveli Kompatsiari, Davide De Tommaso, Agnieszka Wykowska

  • 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

    Action Valuation in Sports: A Survey

    Artur Xarles, Sérgio Escalera, Thomas B. Moeslund, Albert Clapés

  • 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

    Action Anticipation from Soccernet Football Video Broadcasts

    Mohamad Dalal, Artur Xarles, Anthony Cioppa, Silvio Giancola, Marc Van Droogenbroeck, Bernard Ghanem, Albert Clapés, Sérgio Escalera, Thomas B. Moeslund

  • Association for Computational Linguistics

    A Template Is All You Meme

    Luke Bates, Peter E. Christensen, Preslav Nakov, Iryna Gurevych

  • Journal of Ocean Technology

    What can Camera Concepts Sense for You-that Conventional Sampling Methods do not?

    Niels Madsen, Amanda F. Irlind, Alex Jørgensen, Karen A. Sønnichsen, Malte Pedersen, Jonathan E. Schmidt, Anders S. Johansen, Galadrielle Humblot-Renaux, Thomas B. Moeslund, Nadieh de Jonge, Jeppe L. Nielsen

  • Journal of Documentation

    Understanding complex casual leisure information needs: an analysis of search requests for books, games, movies and music

    Toine Bogers, Maria Gäde, Marijn Koolen, Vivien Petras, Mette Skov

  • Speech Communication

    A survey of deep learning for complex speech spectrograms

    Yuying Xie, Zheng‐Hua Tan

  • 2025 IEEE International Symposium on Mixed and Augmented Reality (ISMAR)

    A Study of Multimodal Pen + Gaze Interaction Techniques for Shape Point Translation in Extended Reality

    Uta Wagner, Jinwook Kim, Zhikun Wu, Qiushi Zhou, Mario Romero, Alessandro Iop

  • Association for Computational Linguistics

    A Reality Check on Context Utilisation for Retrieval-Augmented Generation

    Lovisa Hagström, Sara V. Marjanovic, Haeun Yu, Arnav Arora, Christina Lioma, Maria Maistro, Pepa Atanasova, Isabelle Augenstein

  • MM '25: Proceedings of the 33rd ACM International Conference on Multimedia

    8th ACM International Workshop on Multimedia Content Analysis in Sports (ACM MMSports'25)

    Rainer Lienhart, Thomas B. Moeslund, Hideo Saitô

  • Human-Computer Interaction (HCII 2025)

    “A False Reality”? A Micro-phenomenology of Avatars in VR

    Xinyue Hu, Tor-Salve Dalsgaard, Kasper Hornbæk

  • University of Tartu Library

    SnakModel: Lessons Learned from Training an Open Danish Large Language Model

    Mike Zhang, Max Müller-Eberstein, Elisa Bassignana, Rob van der Goot

  • Association for Computational Linguistics

    DaKultur: Evaluating the Cultural Awareness of Language Models for Danish with Native Speakers

    Max Müller-Eberstein, Mike Zhang, Elisa Bassignana, Peter B. Trolle, Rob Van Der Goot

  • ELRA and ICCL

    Can Humans Identify Domains?

    Maria Barrett, Max Müller-Eberstein, Elisa Bassignana, Amalie B. Pauli, Mike Zhang, Rob van der Goot

  • SIGIR '25: Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval

    Efficiency and Effectiveness of LLM-Based Summarization of Evidence in Crowdsourced Fact-Checking

    Kevin Roitero, Dustin Wright, Michael Soprano, Isabelle Augenstein, Stefano Mizzaro

  • Simplifying Medical Ultrasound (ASMUS 2025)

    Diffusion-based Iterative Counterfactual Explanations for Fetal Ultrasound Image Quality Assessment

    Paraskevas Pegios, Manxi Lin, Nina Weng, Morten B. S. Svendsen, Zahra Bashir, Siavash Bigdeli, Anders N. Christensen, Martin Tolsgaard, Aasa Feragen