Stefan Wermter
201 publications
21 venues
H Index 26
| Name | Venue | Year | citations |
|---|---|---|---|
RankCut: A Ranking-Based LLM Approach to Extractive Summarization for Transcript-Based Video Editing.
|
IUI | 2026 | 0 |
| Agentic skill discovery.
|
Robotics and Autonomous Systems | 2026 | 0 |
| LLM-based Interactive Imitation Learning for Robotic Manipulation.
|
IJCNN | 2025 | 3 |
| Keypoint-Based Diffusion for Robotic Motion Planning on the NICOL Robot.
|
ICANN | 2025 | 0 |
| Pointing-Guided Target Estimation via Transformer-Based Attention.
|
ICANN | 2025 | 0 |
| Shaken, Not Stirred: A Novel Dataset for Visual Understanding of Glasses in Human-Robot Bartending Tasks.
|
IROS | 2025 | 0 |
| QT-TDM: Planning With Transformer Dynamics Model and Autoregressive Q-Learning.
|
IEEE Robotics and Automation Letters | 2025 | 0 |
| Robots Can Multitask Too: Integrating a Memory Architecture and LLMs for Enhanced Cross-Task Robot Action Generation.
|
Humanoids | 2024 | 8 |
| Large Language Models for Orchestrating Bimanual Robots.
|
Humanoids | 2024 | 13 |
| When Robots Get Chatty: Grounding Multimodal Human-Robot Conversation and Collaboration.
|
ICANN | 2024 | 24 |
| Inverse Kinematics for Neuro-Robotic Grasping with Humanoid Embodied Agents.
|
IROS | 2024 | 9 |
| Details Make a Difference: Object State-Sensitive Neurorobotic Task Planning.
|
ICANN | 2024 | 4 |
| Domain Adaption as Auxiliary Task for Sim-to-Real Transfer in Vision-based Neuro-Robotic Control.
|
IJCNN | 2024 | 3 |
| Embodying Language Models in Robot Action.
|
ESANN | 2024 | 1 |
| An Energy Sampling Replay-Based Continual Learning Framework.
|
ICANN | 2024 | 1 |
| Diffusing in Someone Else's Shoes: Robotic Perspective-Taking with Diffusion.
|
Humanoids | 2024 | 0 |
| Neural Field Conditioning Strategies for 2D Semantic Segmentation.
|
ICANN | 2023 | 2 |
| Replay to Remember: Continual Layer-Specific Fine-Tuning for German Speech Recognition.
|
ICANN | 2023 | 4 |
| CycleIK: Neuro-inspired Inverse Kinematics.
|
ICANN | 2023 | 8 |
| Sample-Efficient Real-Time Planning with Curiosity Cross-Entropy Method and Contrastive Learning.
|
IROS | 2023 | 4 |
| Bring the Noise: Introducing Noise Robustness to Pretrained Automatic Speech Recognition.
|
ICANN | 2023 | 4 |
| Clarifying the Half Full or Half Empty Question: Multimodal Container Classification.
|
ICANN | 2023 | 0 |
| Chat with the Environment: Interactive Multimodal Perception Using Large Language Models.
|
IROS | 2023 | 71 |
| Internally Rewarded Reinforcement Learning.
|
ICML | 2023 | 17 |
| Visually Grounded Commonsense Knowledge Acquisition.
|
AAAI | 2023 | 0 |
| Impact Makes a Sound and Sound Makes an Impact: Sound Guides Representations and Explorations.
|
IROS | 2022 | 10 |
| Learning Flexible Translation Between Robot Actions and Language Descriptions.
|
ICANN | 2022 | 2 |
| What is Right for Me is Not Yet Right for You: A Dataset for Grounding Relative Directions via Multi-Task Learning.
|
IJCAI | 2022 | 12 |
| Word-by-Word Generation of Visual Dialog Using Reinforcement Learning.
|
ICANN | 2022 | 1 |
| Learning Visually Grounded Human-Robot Dialog in a Hybrid Neural Architecture.
|
ICANN | 2022 | 3 |
| More Diverse Training, Better Compositionality! Evidence from Multimodal Language Learning.
|
ICANN | 2022 | 0 |
| Learning to Autonomously Reach Objects with NICO and Grow-When-Required Networks.
|
Humanoids | 2022 | 2 |
| Sim-to-Real Neural Learning with Domain Randomisation for Humanoid Robot Grasping.
|
ICANN | 2022 | 3 |
| NeoSLAM: Neural Object SLAM for Loop Closure and Navigation.
|
ICANN | 2022 | 2 |
| Semantic Object Accuracy for Generative Text-to-Image Synthesis.
|
TPAMI | 2022 | 0 |
| Improving Model-Based Reinforcement Learning with Internal State Representations through Self-Supervision.
|
IJCNN | 2021 | 5 |
| Lifelong Learning from Event-based Data.
|
ESANN | 2021 | 0 |
| DRILL: Dynamic Representations for Imbalanced Lifelong Learning.
|
ICANN | 2021 | 7 |
| Controlling the Noise Robustness of End-to-End Automatic Speech Recognition Systems.
|
IJCNN | 2021 | 3 |
| Behavior Self-Organization Supports Task Inference for Continual Robot Learning.
|
IROS | 2021 | 13 |
| FaVoA: Face-Voice Association Favours Ambiguous Speaker Detection.
|
ICANN | 2021 | 9 |
| Generalization in Multimodal Language Learning from Simulation.
|
IJCNN | 2021 | 9 |
| Planning-integrated Policy for Efficient Reinforcement Learning in Sparse-reward Environments.
|
IJCNN | 2021 | 0 |
| Visual Distant Supervision for Scene Graph Generation.
|
ICCV | 2021 | 41 |
| Robotic Occlusion Reasoning for Efficient Object Existence Prediction.
|
IROS | 2021 | 9 |
| GASP: Gated Attention for Saliency Prediction.
|
IJCAI | 2021 | 7 |
| Pruning Neural Networks with Supermasks.
|
ESANN | 2021 | 2 |
| Improving robot dual-system motor learning with intrinsically motivated meta-control and latent-space experience imagination.
|
Robotics and Autonomous Systems | 2020 | 16 |
| Variational Autoencoder with Global- and Medium Timescale Auxiliaries for Emotion Recognition from Speech.
|
ICANN | 2020 | 1 |
| Neuro-Genetic Visuomotor Architecture for Robotic Grasping.
|
ICANN | 2020 | 6 |
| Neural Networks for Detecting Irrelevant Questions During Visual Question Answering.
|
ICANN | 2020 | 6 |
| Self-Organizing Kernel-based Convolutional Echo State Network for Human Actions Recognition.
|
ESANN | 2020 | 1 |
| New Results on Sparse Autoencoders for Posture Classification and Segmentation.
|
ESANN | 2020 | 0 |
| Efficient Facial Feature Learning with Wide Ensemble-Based Convolutional Neural Networks.
|
AAAI | 2020 | 134 |
| Curious Hierarchical Actor-Critic Reinforcement Learning.
|
ICANN | 2020 | 22 |
| Tell Me Why You Feel That Way: Processing Compositional Dependency for Tree-LSTM Aspect Sentiment Triplet Extraction (TASTE).
|
ICANN | 2020 | 0 |
| The Conditional Boundary Equilibrium Generative Adversarial Network and its Application to Facial Attributes.
|
IJCNN | 2019 | 9 |
| Leveraging Recursive Processing for Neural-Symbolic Affect-Target Associations.
|
IJCNN | 2019 | 2 |
| Curious Meta-Controller: Adaptive Alternation between Model-Based and Model-Free Control in Deep Reinforcement Learning.
|
IJCNN | 2019 | 11 |
| Incorporating End-to-End Speech Recognition Models for Sentiment Analysis.
|
ICRA | 2019 | 24 |
| Designing a Personality-Driven Robot for a Human-Robot Interaction Scenario.
|
ICRA | 2019 | 9 |
| Question Answering with Hierarchical Attention Networks.
|
IJCNN | 2019 | 3 |
| Exploring Low-level and High-level Transfer Learning for Multi-task Facial Recognition with a Semi-supervised Neural Network.
|
IROS | 2019 | 0 |
| Neuro-Robotic Haptic Object Classification by Active Exploration on a Novel Dataset.
|
IJCNN | 2019 | 16 |
| Effect of Pruning on Catastrophic Forgetting in Growing Dual Memory Networks.
|
IJCNN | 2019 | 9 |
| Mixed-Reality Deep Reinforcement Learning for a Reach-to-grasp Task.
|
ICANN | 2019 | 6 |
| Evaluating Defensive Distillation for Defending Text Processing Neural Networks Against Adversarial Examples.
|
ICANN | 2019 | 24 |
| A Personalized Affective Memory Model for Improving Emotion Recognition.
|
ICML | 2019 | 0 |
| Accelerating Deep Continuous Reinforcement Learning through Task Simplification.
|
IJCNN | 2018 | 17 |
| Learning Empathy-Driven Emotion Expressions using Affective Modulations.
|
IJCNN | 2018 | 27 |
| Multi-modal Feedback for Affordance-driven Interactive Reinforcement Learning.
|
IJCNN | 2018 | 29 |
| Image-to-Text Transduction with Spatial Self-Attention.
|
ESANN | 2018 | 1 |
| The OMG-Emotion Behavior Dataset.
|
IJCNN | 2018 | 105 |
| Hear the Egg - Demonstrating Robotic Interactive Auditory Perception.
|
IROS | 2018 | 5 |
| A Self-organizing Method for Robot Navigation based on Learned Place and Head-Direction Cells.
|
IJCNN | 2018 | 7 |
| A Hybrid Planning Strategy Through Learning from Vision for Target-Directed Navigation.
|
ICANN | 2018 | 2 |
| Surprisal-based activation in recurrent neural networks.
|
ESANN | 2018 | 0 |
| Slowness-based neural visuomotor control with an Intrinsically motivated Continuous Actor-Critic.
|
ESANN | 2018 | 3 |
| An analysis of subtask-dependency in robot command interpretation with dilated CNNs.
|
ESANN | 2018 | 2 |
| Expectation Learning and Crossmodal Modulation with a Deep Adversarial Network.
|
IJCNN | 2018 | 1 |
| Sparse Autoencoders for Posture Recognition.
|
IJCNN | 2018 | 2 |
| Recognition and Prediction of Human-Object Interactions with a Self-Organizing Architecture.
|
IJCNN | 2018 | 5 |
| An Ensemble with Shared Representations Based on Convolutional Networks for Continually Learning Facial Expressions.
|
IROS | 2018 | 11 |
| Image Generation and Translation with Disentangled Representations.
|
IJCNN | 2018 | 8 |
| Inferencing based on unsupervised learning of disentangled representations.
|
ESANN | 2018 | 7 |
| Disambiguating Affective Stimulus Associations for Robot Perception and Dialogue.
|
Humanoids | 2018 | 8 |
| Point Cloud Object Recognition using 3D Convolutional Neural Networks.
|
IJCNN | 2018 | 2 |
| Continuous convolutional object tracking.
|
ESANN | 2018 | 8 |
| Object Detection and Pose Estimation Based on Convolutional Neural Networks Trained with Synthetic Data.
|
IROS | 2018 | 35 |
| EmoRL: Continuous Acoustic Emotion Classification Using Deep Reinforcement Learning.
|
ICRA | 2018 | 24 |
| Towards End-to-End Raw Audio Music Synthesis.
|
ICANN | 2018 | 5 |
| Combining Articulatory Features with End-to-End Learning in Speech Recognition.
|
ICANN | 2018 | 8 |
| Deep Neural Object Analysis by Interactive Auditory Exploration with a Humanoid Robot.
|
IROS | 2018 | 21 |
| Classification of MRI Migraine Medical Data Using 3D Convolutional Neural Network.
|
ICANN | 2018 | 7 |
| On the Robustness of Speech Emotion Recognition for Human-Robot Interaction with Deep Neural Networks.
|
IROS | 2018 | 60 |
| De-noise-GAN: De-noising Images to Improve RoboCup Soccer Ball Detection.
|
ICANN | 2018 | 0 |
| A Sub-Layered Hierarchical Pyramidal Neural Architecture for Facial Expression Recognition.
|
ESANN | 2018 | 0 |
| A Neurorobotic Experiment for Crossmodal Conflict Resolution in Complex Environments.
|
IROS | 2018 | 0 |
| Dialogue-Based Neural Learning to Estimate the Sentiment of a Next Upcoming Utterance.
|
ICANN | 2017 | 16 |
| Semi-supervised Phoneme Recognition with Recurrent Ladder Networks.
|
ICANN | 2017 | 4 |
| Haptic material classification with a multi-channel neural network.
|
IJCNN | 2017 | 35 |
| Combining deep learning for visuomotor coordination with object identification to realize a high-level interface for robot object-picking.
|
Humanoids | 2017 | 6 |
| Robot Localization and Orientation Detection Based on Place Cells and Head-Direction Cells.
|
ICANN | 2017 | 9 |
| A self-organizing model for affective memory.
|
IJCNN | 2017 | 13 |
| Emergence of multimodal action representations from neural network self-organization.
|
Cognitive System Research | 2017 | 43 |
| Neural End-to-End Self-learning of Visuomotor Skills by Environment Interaction.
|
ICANN | 2017 | 23 |
| Automatically augmenting an emotion dataset improves classification using audio.
|
EACL | 2017 | 3 |
| Teaching emotion expressions to a human companion robot using deep neural architectures.
|
IJCNN | 2017 | 32 |
| Semantic Role Labelling for Robot Instructions using Echo State Networks.
|
ESANN | 2016 | 8 |
| Understanding how deep neural networks learn face expressions.
|
IJCNN | 2016 | 25 |
| Multi-modal integration of dynamic audiovisual patterns for an interactive reinforcement learning scenario.
|
IROS | 2016 | 37 |
| Recognition of Transitive Actions with Hierarchical Neural Network Learning.
|
ICANN | 2016 | 5 |
| Learning Multiple Timescales in Recurrent Neural Networks.
|
ICANN | 2016 | 12 |
| Learning auditory neural representations for emotion recognition.
|
IJCNN | 2016 | 12 |
| The Effects of Regularization on Learning Facial Expressions with Convolutional Neural Networks.
|
ICANN | 2016 | 11 |
| Learning contextual affordances with an associative neural architecture.
|
ESANN | 2016 | 17 |
| Activity recognition with echo state networks using 3D body joints and objects category.
|
ESANN | 2016 | 6 |
| Gesture Recognition with a Convolutional Long Short-Term Memory Recurrent Neural Network.
|
ESANN | 2016 | 43 |
| Learning objects from RGB-D sensors using point cloud-based neural networks.
|
ESANN | 2015 | 5 |
| Recognizing complex mental states with deep hierarchical features for Human-Robot Interaction.
|
IROS | 2015 | 1 |
| Emotional expression recognition with a cross-channel convolutional neural network for human-robot interaction.
|
Humanoids | 2015 | 49 |
| Interactive reinforcement learning through speech guidance in a domestic scenario.
|
IJCNN | 2015 | 57 |
| Learning human motion feedback with neural self-organization.
|
IJCNN | 2015 | 18 |
| Face expression recognition with a 2-channel Convolutional Neural Network.
|
IJCNN | 2015 | 122 |
| Dynamic gesture recognition using Echo State Networks.
|
ESANN | 2015 | 9 |
| A Multichannel Convolutional Neural Network for Hand Posture Recognition.
|
ICANN | 2014 | 74 |
| RatSLAM on Humanoids - A Bio-Inspired SLAM Model Adapted to a Humanoid Robot.
|
ICANN | 2014 | 12 |
| An Incremental Approach to Language Acquisition: Thematic Role Assignment with Echo State Networks.
|
ICANN | 2014 | 13 |
| Robust fall detection with an assistive humanoid robot.
|
Humanoids | 2014 | 2 |
| FINGeR: Framework for interactive neural-based gesture recognition.
|
ESANN | 2014 | 10 |
| Improving Domain-independent Cloud-Based Speech Recognition with Domain-Dependent Phonetic Post-Processing.
|
AAAI | 2014 | 53 |
| Human Action Recognition with Hierarchical Growing Neural Gas Learning.
|
ICANN | 2014 | 22 |
| Improving Humanoid Robot Speech Recognition with Sound Source Localisation.
|
ICANN | 2014 | 3 |
| Interactive Language Understanding with Multiple Timescale Recurrent Neural Networks.
|
ICANN | 2014 | 9 |
| Real-time gesture recognition using a humanoid robot with a deep neural architecture.
|
Humanoids | 2014 | 43 |
| Embodied Language Understanding with a Multiple Timescale Recurrent Neural Network.
|
ICANN | 2013 | 6 |
| Self-Organized Neural Learning of Statistical Inference from High-Dimensional Data.
|
IJCAI | 2013 | 6 |
| Neural Hopfield-ensemble for multi-class head pose detection.
|
IJCNN | 2013 | 0 |
| Hierarchical SOM-based detection of novel behavior for 3D human tracking.
|
IJCNN | 2013 | 25 |
| Neural and statistical processing of spatial cues for sound source localisation.
|
IJCNN | 2013 | 8 |
| A neurocomputational amygdala model of auditory fear conditioning: A hybrid system approach.
|
IJCNN | 2012 | 8 |
| Learning Features and Predictive Transformation Encoding Based on a Horizontal Product Model.
|
ICANN | 2012 | 5 |
| Real-world reinforcement learning for autonomous humanoid robot docking.
|
Robotics and Autonomous Systems | 2012 | 49 |
| A neural approach for robot navigation based on cognitive map learning.
|
IJCNN | 2012 | 22 |
| Biomimetic Binaural Sound Source Localisation with Ego-Noise Cancellation.
|
ICANN | 2012 | 13 |
| Adaptive Learning of Linguistic Hierarchy in a Multiple Timescale Recurrent Neural Network.
|
ICANN | 2012 | 10 |
| A SOM-based model for multi-sensory integration in the superior colliculus.
|
IJCNN | 2012 | 16 |
| Hybrid Ensembles Using Hopfield Neural Networks and Haar-Like Features for Face Detection.
|
ICANN | 2012 | 3 |
| Person Tracking Based on a Hybrid Neural Probabilistic Model.
|
ICANN | 2011 | 1 |
| Robot Trajectory Prediction and Recognition Based on a Computational Mirror Neurons Model.
|
ICANN | 2011 | 10 |
| Hybrid Parallel Classifiers for Semantic Subspace Learning.
|
ICANN | 2011 | 0 |
| Semantic Subspace Learning with conditional significance vectors.
|
IJCNN | 2010 | 13 |
| Configuring the stochastic Helmholtz machine for subcortical emotional learning.
|
IJCNN | 2010 | 0 |
| A biomimetic spiking neural network of the auditory midbrain for mobile robot sound localisation in reverberant environments.
|
IJCNN | 2009 | 3 |
| Social Cognition, Marilynn B. Brewer, Miles J. Hewstone (Eds.); Blackwell Publishing, 2004, 368 pages.
|
Cognitive System Research | 2009 | 0 |
| Multiple Sound Source Localisation in Reverberant Environments Inspired by the Auditory Midbrain.
|
ICANN | 2009 | 8 |
| Elden, L (2007). Matrix Methods in Data Mining and Pattern Recognition. Philadelphia (USA): Society for Industrial and Applied Mathematics.
|
Cognitive System Research | 2009 | 0 |
| A neural wake-sleep learning architecture for associating robotic facial emotions.
|
IJCNN | 2008 | 5 |
| Appearance-based localization for mobile robots using digital zoom and visual compass.
|
Robotics and Autonomous Systems | 2008 | 25 |
| Mobile robot broadband sound localisation using a biologically inspired spiking neural network.
|
IROS | 2008 | 8 |
| Hybrid learning architecture for unobtrusive infrared tracking support.
|
IJCNN | 2008 | 3 |
| A Biologically Inspired Spiking Neural Network for Sound Localisation by the Inferior Colliculus.
|
ICANN | 2008 | 9 |
| Visual robot homing using Sarsa(lambda), whole image measure, and radial basis function.
|
IJCNN | 2008 | 0 |
| Bioinspired Auditory Sound Localisation for Improving the Signal to Noise Ratio of Socially Interactive Robots.
|
IROS | 2006 | 9 |
| Reinforcement Learning for Platform-Independent Visual Robot Control.
|
IJCNN | 2006 | 3 |
| A constructive and hierarchical self-organizing model in a non-stationary environment.
|
IJCNN | 2005 | 13 |
| Reinforcement Learning in MirrorBot.
|
ICANN | 2005 | 3 |
| Image Segmentation by Complex-Valued Units.
|
ICANN | 2005 | 5 |
| Training without data: Knowledge Insertion into RBF Neural Networks.
|
IJCAI | 2005 | 3 |
| Auditory robotic tracking of sound sources using hybrid cross-correlation and recurrent networks.
|
IROS | 2005 | 25 |
| Grasping with flexible viewing-direction with a learned coordinate transformation network.
|
Humanoids | 2005 | 3 |
| A recurrent neural network for sound-source motion tracking and prediction.
|
IJCNN | 2005 | 5 |
| Spatio-temporal neural data mining architecture in learning robots.
|
IJCNN | 2005 | 4 |
| An associator network approach to robot learning by imitation through vision, motor control and language.
|
IJCNN | 2004 | 17 |
| Towards multimodal neural robot learning.
|
Robotics and Autonomous Systems | 2004 | 46 |
| Predictive Top-Down Knowledge Improves Neural Exploratory Bottom-Up Clustering.
|
ECIR | 2004 | 4 |
| Self organising neural place codes for vision based robot navigation.
|
IJCNN | 2004 | 2 |
| A time-based self-organising model for document clustering.
|
IJCNN | 2004 | 5 |
| Knowing what and where: a computational model for visual attention.
|
IJCNN | 2004 | 5 |
| Object Localisation Using Laterally Connected "What" and "Where" Associator Networks.
|
ICANN | 2003 | 10 |
| A Dynamic Adaptive Self-Organising Hybrid Model for Text Clustering.
|
ICDM | 2003 | 38 |
| Comparing Support Vector Machines, Recurrent Networks, and Finite State Transducers for Classifying Spoken Utterances.
|
ICANN | 2003 | 4 |
| Learning Localisation Based on Landmarks Using Self-Organisation.
|
ICANN | 2003 | 7 |
| Self-organisation of language instruction for robot action control.
|
IJCNN | 2003 | 5 |
| Spike-Timing Dependent Competitive Learning of Integrate-and-Fire Neurons with Active Dendrites.
|
ICANN | 2002 | 22 |
| Selforganizing Classification on the Reuters News Corpus.
|
COLING | 2002 | 28 |
| Recurrent Neural Learning for Helpdesk Call Routing.
|
ICANN | 2002 | 7 |
| Hybrid preference machines based on inspiration from neuroscience.
|
Cognitive System Research | 2002 | 6 |
| A Mirror Neuron System for Syntax Acquisition.
|
ICANN | 2001 | 6 |
| Knowledge Extraction from Local Function Networks.
|
IJCAI | 2001 | 20 |
| Meaning Spotting and Robustness of Recurrent Networks.
|
IJCNN | 2000 | 1 |
| Complex Preferences for the Integration of Neural Codes.
|
IJCNN | 2000 | 2 |
| Rule generation from neural networks for student assessment.
|
IJCNN | 1999 | 12 |
| Preference Moore Machines for Neural Fuzzy Integration.
|
IJCAI | 1999 | 17 |
| Knowledge extraction from radial basis function networks and multilayer perceptrons.
|
IJCNN | 1999 | 64 |
| SCREEN: Learning a Flat Syntactic and Semantic Spoken Language Analysis Using Artificial Neural Networks.
|
JAIR | 1997 | 0 |
| Towards constructive and destructive dynamic network configuration.
|
ESANN | 1996 | 2 |
| Learning dialog act processing.
|
COLING | 1996 | 28 |
| Learning Fault-Tolerant Speech Parsing with SCREEN.
|
AAAI | 1994 | 26 |
| A Hybrid and Connectionist Architecture for a Scanning Understanding.
|
ECAI | 1992 | 8 |
| Integration of Semantic and Syntactic Constraints for Structural Noun Phrase Disambiguation.
|
IJCAI | 1989 | 23 |