Search Results for author: Danica Kragic

Found 54 papers, 16 papers with code

Learning Geometric Representations of Objects via Interaction

1 code implementation11 Sep 2023 Alfredo Reichlin, Giovanni Luca Marchetti, Hang Yin, Anastasiia Varava, Danica Kragic

We address the problem of learning representations from observations of a scene involving an agent and an external object the agent interacts with.

Representation Learning

TD-GEM: Text-Driven Garment Editing Mapper

1 code implementation29 May 2023 Reza Dadfar, Sanaz Sabzevari, Mårten Björkman, Danica Kragic

An optimization-based Contrastive Language-Image Pre-training (CLIP) is then utilized to guide the latent representation of a fashion image in the direction of a target attribute expressed in terms of a text prompt.

Controllable Motion Synthesis and Reconstruction with Autoregressive Diffusion Models

no code implementations3 Apr 2023 Wenjie Yin, Ruibo Tu, Hang Yin, Danica Kragic, Hedvig Kjellström, Mårten Björkman

Data-driven and controllable human motion synthesis and prediction are active research areas with various applications in interactive media and social robotics.

Motion Synthesis

Equivariant Representation Learning in the Presence of Stabilizers

1 code implementation12 Jan 2023 Luis Armando Pérez Rey, Giovanni Luca Marchetti, Danica Kragic, Dmitri Jarnikov, Mike Holenderski

We introduce Equivariant Isomorphic Networks (EquIN) -- a method for learning representations that are equivariant with respect to general group actions over data.

Representation Learning

EDO-Net: Learning Elastic Properties of Deformable Objects from Graph Dynamics

no code implementations19 Sep 2022 Alberta Longhini, Marco Moletta, Alfredo Reichlin, Michael C. Welle, David Held, Zackory Erickson, Danica Kragic

We study the problem of learning graph dynamics of deformable objects that generalizes to unknown physical properties.

Dance Style Transfer with Cross-modal Transformer

no code implementations19 Aug 2022 Wenjie Yin, Hang Yin, Kim Baraka, Danica Kragic, Mårten Björkman

We present CycleDance, a dance style transfer system to transform an existing motion clip in one dance style to a motion clip in another dance style while attempting to preserve motion context of the dance.

Style Transfer

Digraphwave: Scalable Extraction of Structural Node Embeddings via Diffusion on Directed Graphs

no code implementations20 Jul 2022 Ciwan Ceylan, Kambiz Ghoorchian, Danica Kragic

Structural node embeddings, vectors capturing local connectivity information for each node in a graph, have many applications in data mining and machine learning, e. g., network alignment and node classification, clustering and anomaly detection.

Anomaly Detection Node Classification

Back to the Manifold: Recovering from Out-of-Distribution States

no code implementations18 Jul 2022 Alfredo Reichlin, Giovanni Luca Marchetti, Hang Yin, Ali Ghadirzadeh, Danica Kragic

However, a major challenge is a distributional shift between the states in the training dataset and the ones visited by the learned policy at the test time.

On the Subspace Structure of Gradient-Based Meta-Learning

no code implementations8 Jul 2022 Gustaf Tegnér, Alfredo Reichlin, Hang Yin, Mårten Björkman, Danica Kragic

In this work we provide an analysis of the distribution of the post-adaptation parameters of Gradient-Based Meta-Learning (GBML) methods.

Few-Shot Learning Image Classification +1

Equivariant Representation Learning via Class-Pose Decomposition

1 code implementation7 Jul 2022 Giovanni Luca Marchetti, Gustaf Tegnér, Anastasiia Varava, Danica Kragic

We introduce a general method for learning representations that are equivariant to symmetries of data.

Representation Learning

Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models

no code implementations18 Apr 2022 Ali Ghadirzadeh, Petra Poklukar, Karol Arndt, Chelsea Finn, Ville Kyrki, Danica Kragic, Mårten Björkman

We present a data-efficient framework for solving sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative models.

Decision Making reinforcement-learning +2

GraphDCA -- a Framework for Node Distribution Comparison in Real and Synthetic Graphs

no code implementations8 Feb 2022 Ciwan Ceylan, Petra Poklukar, Hanna Hultin, Alexander Kravchenko, Anastasia Varava, Danica Kragic

We argue that when comparing two graphs, the distribution of node structural features is more informative than global graph statistics which are often used in practice, especially to evaluate graph generative models.

Geometric Multimodal Contrastive Representation Learning

1 code implementation7 Feb 2022 Petra Poklukar, Miguel Vasco, Hang Yin, Francisco S. Melo, Ana Paiva, Danica Kragic

Learning representations of multimodal data that are both informative and robust to missing modalities at test time remains a challenging problem due to the inherent heterogeneity of data obtained from different channels.

Reinforcement Learning (RL) Representation Learning

Comparing Reconstruction- and Contrastive-based Models for Visual Task Planning

no code implementations14 Sep 2021 Constantinos Chamzas, Martina Lippi, Michael C. Welle, Anastasia Varava, Lydia E. Kavraki, Danica Kragic

Most methods learn state representations by utilizing losses based on the reconstruction of the raw observations from a lower-dimensional latent space.

Representation Learning

Batch Curation for Unsupervised Contrastive Representation Learning

no code implementations19 Aug 2021 Michael C. Welle, Petra Poklukar, Danica Kragic

The state-of-the-art unsupervised contrastive visual representation learning methods that have emerged recently (SimCLR, MoCo, SwAV) all make use of data augmentations in order to construct a pretext task of instant discrimination consisting of similar and dissimilar pairs of images.

Representation Learning

GeomCA: Geometric Evaluation of Data Representations

1 code implementation26 May 2021 Petra Poklukar, Anastasia Varava, Danica Kragic

Evaluating the quality of learned representations without relying on a downstream task remains one of the challenges in representation learning.

Contrastive Learning Representation Learning

Graph-based Normalizing Flow for Human Motion Generation and Reconstruction

no code implementations7 Apr 2021 Wenjie Yin, Hang Yin, Danica Kragic, Mårten Björkman

Data-driven approaches for modeling human skeletal motion have found various applications in interactive media and social robotics.


no code implementations ICLR Workshop Learning_to_Learn 2021 Ali Ghadirzadeh, Petra Poklukar, Xi Chen, Huaxiu Yao, Hossein Azizpour, Mårten Björkman, Chelsea Finn, Danica Kragic

Few-shot meta-learning methods aim to learn the common structure shared across a set of tasks to facilitate learning new tasks with small amounts of data.

Meta-Learning Variational Inference

Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms

no code implementations5 Mar 2021 Ali Ghadirzadeh, Xi Chen, Petra Poklukar, Chelsea Finn, Mårten Björkman, Danica Kragic

Our results show that the proposed method can successfully adapt a trained policy to different robotic platforms with novel physical parameters and the superiority of our meta-learning algorithm compared to state-of-the-art methods for the introduced few-shot policy adaptation problem.


Graph-based Task-specific Prediction Models for Interactions between Deformable and Rigid Objects

1 code implementation4 Mar 2021 Zehang Weng, Fabian Paus, Anastasiia Varava, Hang Yin, Tamim Asfour, Danica Kragic

In an ablation study, we show the benefits of the two-stage model for single time step prediction and the effectiveness of the mixed-horizon model for long-term prediction tasks.


Enabling Visual Action Planning for Object Manipulation through Latent Space Roadmap

1 code implementation3 Mar 2021 Martina Lippi, Petra Poklukar, Michael C. Welle, Anastasia Varava, Hang Yin, Alessandro Marino, Danica Kragic

We present a framework for visual action planning of complex manipulation tasks with high-dimensional state spaces, focusing on manipulation of deformable objects.

Interpretability in Contact-Rich Manipulation via Kinodynamic Images

1 code implementation23 Feb 2021 Ioanna Mitsioni, Joonatan Mänttäri, Yiannis Karayiannidis, John Folkesson, Danica Kragic

In this work, we address the interpretability of NN-based models by introducing the kinodynamic images.


Sequential Topological Representations for Predictive Models of Deformable Objects

no code implementations23 Nov 2020 Rika Antonova, Anastasiia Varava, Peiyang Shi, J. Frederico Carvalho, Danica Kragic

Deformable objects present a formidable challenge for robotic manipulation due to the lack of canonical low-dimensional representations and the difficulty of capturing, predicting, and controlling such objects.

Data-efficient visuomotor policy training using reinforcement learning and generative models

no code implementations26 Jul 2020 Ali Ghadirzadeh, Petra Poklukar, Ville Kyrki, Danica Kragic, Mårten Björkman

We present a data-efficient framework for solving visuomotor sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative models.

Decision Making Disentanglement +3

The effect of Target Normalization and Momentum on Dying ReLU

no code implementations13 May 2020 Isac Arnekvist, J. Frederico Carvalho, Danica Kragic, Johannes A. Stork

To further investigate this matter, we analyze a discrete-time linear autonomous system, and show theoretically how this relates to a model with a single ReLU and how common properties can result in dying ReLU.

Fashion Landmark Detection and Category Classification for Robotics

1 code implementation26 Mar 2020 Thomas Ziegler, Judith Butepage, Michael C. Welle, Anastasiia Varava, Tonci Novkovic, Danica Kragic

Research on automated, image based identification of clothing categories and fashion landmarks has recently gained significant interest due to its potential impact on areas such as robotic clothing manipulation, automated clothes sorting and recycling, and online shopping.

Classification Data Augmentation +1

Latent Space Roadmap for Visual Action Planning of Deformable and Rigid Object Manipulation

1 code implementation19 Mar 2020 Martina Lippi, Petra Poklukar, Michael C. Welle, Anastasiia Varava, Hang Yin, Alessandro Marino, Danica Kragic

We present a framework for visual action planning of complex manipulation tasks with high-dimensional state spaces such as manipulation of deformable objects.

Benchmarking In-Hand Manipulation

no code implementations9 Jan 2020 Silvia Cruciani, Balakumar Sundaralingam, Kaiyu Hang, Vikash Kumar, Tucker Hermans, Danica Kragic

The purpose of this benchmark is to evaluate the planning and control aspects of robotic in-hand manipulation systems.


Learning Task-Oriented Grasping from Human Activity Datasets

no code implementations25 Oct 2019 Mia Kokic, Danica Kragic, Jeannette Bohg

We develop a model that takes as input an RGB image and outputs a hand pose and configuration as well as an object pose and a shape.

Seeing the whole picture instead of a single point: Self-supervised likelihood learning for deep generative models

no code implementations pproximateinference AABI Symposium 2019 Petra Poklukar, Judith Bütepage, Danica Kragic

Recent findings show that deep generative models can judge out-of-distribution samples as more likely than those drawn from the same distribution as the training data.

Probabilistic Model Learning and Long-term Prediction for Contact-rich Manipulation Tasks

no code implementations11 Sep 2019 Shahbaz Abdul Khader, Hang Yin, Pietro Falco, Danica Kragic

Learning dynamics models is an essential component of model-based reinforcement learning.


Fast Adaptation with Meta-Reinforcement Learning for Trust Modelling in Human-Robot Interaction

no code implementations12 Aug 2019 Yuan Gao, Elena Sibirtseva, Ginevra Castellano, Danica Kragic

In socially assistive robotics, an important research area is the development of adaptation techniques and their effect on human-robot interaction.

Meta-Learning Meta Reinforcement Learning +3

Bayesian Optimization in Variational Latent Spaces with Dynamic Compression

1 code implementation10 Jul 2019 Rika Antonova, Akshara Rai, Tianyu Li, Danica Kragic

We propose a model and architecture for a sequential variational autoencoder that embeds the space of simulated trajectories into a lower-dimensional space of latent paths in an unsupervised way.

Bayesian Optimization

Learning to Estimate Pose and Shape of Hand-Held Objects from RGB Images

no code implementations8 Mar 2019 Mia Kokic, Danica Kragic, Jeannette Bohg

The qualitative experiments show results of pose and shape estimation of objects held by a hand "in the wild".

Image-to-Image Translation Translation

Global Search with Bernoulli Alternation Kernel for Task-oriented Grasping Informed by Simulation

no code implementations10 Oct 2018 Rika Antonova, Mia Kokic, Johannes A. Stork, Danica Kragic

Our further contribution is a neural network architecture and training pipeline that use experience from grasping objects in simulation to learn grasp stability scores.

Bayesian Optimization

A Probabilistic Semi-Supervised Approach to Multi-Task Human Activity Modeling

1 code implementation24 Sep 2018 Judith Bütepage, Hedvig Kjellström, Danica Kragic

Therefore, video-based human activity modeling is concerned with a number of tasks such as inferring current and future semantic labels, predicting future continuous observations as well as imagining possible future label and feature sequences.

Action Classification General Classification +2

Detect, anticipate and generate: Semi-supervised recurrent latent variable models for human activity modeling

no code implementations19 Sep 2018 Judith Bütepage, Danica Kragic

In this work we introduce semi-supervised variational recurrent neural networks which are able to a) model temporal distributions over latent factors and the observable feature space, b) incorporate discrete labels such as activity type when available, and c) generate possible future action sequences on both feature and label level.

Affordance Detection

VPE: Variational Policy Embedding for Transfer Reinforcement Learning

no code implementations10 Sep 2018 Isac Arnekvist, Danica Kragic, Johannes A. Stork

The low-dimensional space, and master policy found by our method enables policies to quickly adapt to new environments.

reinforcement-learning Reinforcement Learning (RL) +1

Rearrangement with Nonprehensile Manipulation Using Deep Reinforcement Learning

no code implementations15 Mar 2018 Weihao Yuan, Johannes A. Stork, Danica Kragic, Michael Y. Wang, Kaiyu Hang

Usually, this is achieved by precisely modeling physical properties of the objects, robot, and the environment for explicit planning.

reinforcement-learning Reinforcement Learning (RL)

Reinforcement Learning for Pivoting Task

1 code implementation1 Mar 2017 Rika Antonova, Silvia Cruciani, Christian Smith, Danica Kragic

In this work we propose an approach to learn a robust policy for solving the pivoting task.

Continuous Control Friction +2

Deep representation learning for human motion prediction and classification

no code implementations CVPR 2017 Judith Bütepage, Michael Black, Danica Kragic, Hedvig Kjellström

To quantify the learned features, we use the output of different layers for action classification and visualize the receptive fields of the network units.

Action Classification Classification +4

Feature Descriptors for Tracking by Detection: a Benchmark

no code implementations21 Jul 2016 Alessandro Pieropan, Mårten Björkman, Niklas Bergström, Danica Kragic

In this paper, we provide an extensive evaluation of the performance of local descriptors for tracking applications.

3D Reconstruction Object Recognition

Interactive Perception: Leveraging Action in Perception and Perception in Action

no code implementations13 Apr 2016 Jeannette Bohg, Karol Hausman, Bharath Sankaran, Oliver Brock, Danica Kragic, Stefan Schaal, Gaurav Sukhatme

Recent approaches in robotics follow the insight that perception is facilitated by interaction with the environment.


Data-Driven Grasp Synthesis - A Survey

no code implementations10 Sep 2013 Jeannette Bohg, Antonio Morales, Tamim Asfour, Danica Kragic

In the case of known objects, we concentrate on the approaches that are based on object recognition and pose estimation.


Persistent Homology for Learning Densities with Bounded Support

no code implementations NeurIPS 2012 Florian T. Pokorny, Hedvig Kjellström, Danica Kragic, Carl Ek

We present a novel method for learning densities with bounded support which enables us to incorporate `hard' topological constraints.

Density Estimation

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