Search Results for author: Bodo Rosenhahn

Found 78 papers, 35 papers with code

The voraus-AD Dataset for Anomaly Detection in Robot Applications

1 code implementation8 Nov 2023 Jan Thieß Brockmann, Marco Rudolph, Bodo Rosenhahn, Bastian Wandt

During the operation of industrial robots, unusual events may endanger the safety of humans and the quality of production.

Anomaly Detection Benchmarking +2

FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing

no code implementations9 Oct 2023 Yuren Cong, Mengmeng Xu, Christian Simon, Shoufa Chen, Jiawei Ren, Yanping Xie, Juan-Manuel Perez-Rua, Bodo Rosenhahn, Tao Xiang, Sen He

In this paper, for the first time, we introduce optical flow into the attention module in the diffusion model's U-Net to address the inconsistency issue for text-to-video editing.

Optical Flow Estimation Text-to-Video Editing +1

HyperSparse Neural Networks: Shifting Exploration to Exploitation through Adaptive Regularization

1 code implementation14 Aug 2023 Patrick Glandorf, Timo Kaiser, Bodo Rosenhahn

Sparse neural networks are a key factor in developing resource-efficient machine learning applications.

Sparse Learning

Markerless human pose estimation for biomedical applications: a survey

no code implementations1 Aug 2023 Andrea Avogaro, Federico Cunico, Bodo Rosenhahn, Francesco Setti

Markerless Human Pose Estimation (HPE) proved its potential to support decision making and assessment in many fields of application.

Decision Making Pose Estimation

Human Spine Motion Capture using Perforated Kinesiology Tape

1 code implementation5 Jun 2023 Hendrik Hachmann, Bodo Rosenhahn

A maximal focus is on the accurate detection of markers and fast usage of the system.

Color-aware Deep Temporal Backdrop Duplex Matting System

no code implementations5 Jun 2023 Hendrik Hachmann, Bodo Rosenhahn

In addition, the proposed studio set is actor friendly, and produces high-quality, temporal consistent alpha and color estimations that include a superior color spill compensation.

Image Matting

Compensation Learning in Semantic Segmentation

1 code implementation26 Apr 2023 Timo Kaiser, Christoph Reinders, Bodo Rosenhahn

In this paper, we propose Compensation Learning in Semantic Segmentation, a framework to identify and compensate ambiguities as well as label noise.

Segmentation Semantic Segmentation

Learning Similarity between Scene Graphs and Images with Transformers

no code implementations2 Apr 2023 Yuren Cong, Wentong Liao, Bodo Rosenhahn, Michael Ying Yang

Scene graph generation is conventionally evaluated by (mean) Recall@K, which measures the ratio of correctly predicted triplets that appear in the ground truth.

Contrastive Learning Graph Generation +3

Take 5: Interpretable Image Classification with a Handful of Features

no code implementations23 Mar 2023 Thomas Norrenbrock, Marco Rudolph, Bodo Rosenhahn

We argue that a human can only understand the decision of a machine learning model, if the features are interpretable and only very few of them are used for a single decision.

Fine-Grained Image Classification Interpretable Machine Learning

Attribute-Centric Compositional Text-to-Image Generation

no code implementations4 Jan 2023 Yuren Cong, Martin Renqiang Min, Li Erran Li, Bodo Rosenhahn, Michael Ying Yang

We further propose an attribute-centric contrastive loss to avoid overfitting to overrepresented attribute compositions.


Blind Knowledge Distillation for Robust Image Classification

1 code implementation21 Nov 2022 Timo Kaiser, Lukas Ehmann, Christoph Reinders, Bodo Rosenhahn

We introduce Blind Knowledge Distillation - a novel teacher-student approach for learning with noisy labels by masking the ground truth related teacher output to filter out potentially corrupted knowledge and to estimate the tipping point from generalizing to overfitting.

Classification Knowledge Distillation +1

SSGVS: Semantic Scene Graph-to-Video Synthesis

no code implementations11 Nov 2022 Yuren Cong, Jinhui Yi, Bodo Rosenhahn, Michael Ying Yang

A semantic scene graph-to-video synthesis framework (SSGVS), based on the pre-trained VSG encoder, VQ-VAE, and auto-regressive Transformer, is proposed to synthesize a video given an initial scene image and a non-fixed number of semantic scene graphs.

Image Generation

Asymmetric Student-Teacher Networks for Industrial Anomaly Detection

1 code implementation14 Oct 2022 Marco Rudolph, Tom Wehrbein, Bodo Rosenhahn, Bastian Wandt

We train a normalizing flow for density estimation as a teacher and a conventional feed-forward network as a student to trigger large distances for anomalies: The bijectivity of the normalizing flow enforces a divergence of teacher outputs for anomalies compared to normal data.

 Ranked #1 on Anomaly Detection on MVTEC 3D-AD (Detection AUROC metric, using extra training data)

3D Anomaly Detection Defect Detection +2

AdaCC: Cumulative Cost-Sensitive Boosting for Imbalanced Classification

1 code implementation17 Sep 2022 Vasileios Iosifidis, Symeon Papadopoulos, Bodo Rosenhahn, Eirini Ntoutsi

Class imbalance poses a major challenge for machine learning as most supervised learning models might exhibit bias towards the majority class and under-perform in the minority class.

Classification imbalanced classification

POLTER: Policy Trajectory Ensemble Regularization for Unsupervised Reinforcement Learning

no code implementations23 May 2022 Frederik Schubert, Carolin Benjamins, Sebastian Döhler, Bodo Rosenhahn, Marius Lindauer

The goal of Unsupervised Reinforcement Learning (URL) is to find a reward-agnostic prior policy on a task domain, such that the sample-efficiency on supervised downstream tasks is improved.

Open-Ended Question Answering reinforcement-learning +2

Contextualize Me -- The Case for Context in Reinforcement Learning

1 code implementation9 Feb 2022 Carolin Benjamins, Theresa Eimer, Frederik Schubert, Aditya Mohan, Sebastian Döhler, André Biedenkapp, Bodo Rosenhahn, Frank Hutter, Marius Lindauer

While Reinforcement Learning ( RL) has made great strides towards solving increasingly complicated problems, many algorithms are still brittle to even slight environmental changes.

reinforcement-learning Reinforcement Learning (RL)

RelTR: Relation Transformer for Scene Graph Generation

1 code implementation27 Jan 2022 Yuren Cong, Michael Ying Yang, Bodo Rosenhahn

Different objects in the same scene are more or less related to each other, but only a limited number of these relationships are noteworthy.

Graph Generation object-detection +2

LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Tracking

no code implementations CVPR 2022 Duy M. H. Nguyen, Roberto Henschel, Bodo Rosenhahn, Daniel Sonntag, Paul Swoboda

Multi-Camera Multi-Object Tracking is currently drawing attention in the computer vision field due to its superior performance in real-world applications such as video surveillance in crowded scenes or in wide spaces.

Multi-Object Tracking Multiple Object Tracking

Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection

1 code implementation6 Oct 2021 Marco Rudolph, Tom Wehrbein, Bodo Rosenhahn, Bastian Wandt

In industrial manufacturing processes, errors frequently occur at unpredictable times and in unknown manifestations.

Defect Detection Unsupervised Anomaly Detection

CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning

1 code implementation5 Oct 2021 Carolin Benjamins, Theresa Eimer, Frederik Schubert, André Biedenkapp, Bodo Rosenhahn, Frank Hutter, Marius Lindauer

While Reinforcement Learning has made great strides towards solving ever more complicated tasks, many algorithms are still brittle to even slight changes in their environment.

Physical Simulations reinforcement-learning +2

Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths

2 code implementations ICCV 2021 Andrea Hornakova, Timo Kaiser, Paul Swoboda, Michal Rolinek, Bodo Rosenhahn, Roberto Henschel

We present an efficient approximate message passing solver for the lifted disjoint paths problem (LDP), a natural but NP-hard model for multiple object tracking (MOT).

Multiple Object Tracking

Disentangled Lifespan Face Synthesis

no code implementations ICCV 2021 Sen He, Wentong Liao, Michael Ying Yang, Yi-Zhe Song, Bodo Rosenhahn, Tao Xiang

The generated face image given a target age code is expected to be age-sensitive reflected by bio-plausible transformations of shape and texture, while being identity preserving.

Face Generation

Spatial-Temporal Transformer for Dynamic Scene Graph Generation

1 code implementation ICCV 2021 Yuren Cong, Wentong Liao, Hanno Ackermann, Bodo Rosenhahn, Michael Ying Yang

Compared to the task of scene graph generation from images, it is more challenging because of the dynamic relationships between objects and the temporal dependencies between frames allowing for a richer semantic interpretation.

Scene Graph Generation Video Understanding +1

World-GAN: a Generative Model for Minecraft Worlds

1 code implementation18 Jun 2021 Maren Awiszus, Frederik Schubert, Bodo Rosenhahn

This work introduces World-GAN, the first method to perform data-driven Procedural Content Generation via Machine Learning in Minecraft from a single example.

Automatic Risk Adaptation in Distributional Reinforcement Learning

no code implementations11 Jun 2021 Frederik Schubert, Theresa Eimer, Bodo Rosenhahn, Marius Lindauer

The use of Reinforcement Learning (RL) agents in practical applications requires the consideration of suboptimal outcomes, depending on the familiarity of the agent with its environment.

Distributional Reinforcement Learning reinforcement-learning +1

Text to Image Generation with Semantic-Spatial Aware GAN

1 code implementation CVPR 2022 Kai Hu, Wentong Liao, Michael Ying Yang, Bodo Rosenhahn

Text-to-image synthesis (T2I) aims to generate photo-realistic images which are semantically consistent with the text descriptions.

Sentence Embedding Sentence-Embedding

Context-Aware Layout to Image Generation with Enhanced Object Appearance

1 code implementation CVPR 2021 Sen He, Wentong Liao, Michael Ying Yang, Yongxin Yang, Yi-Zhe Song, Bodo Rosenhahn, Tao Xiang

We argue that these are caused by the lack of context-aware object and stuff feature encoding in their generators, and location-sensitive appearance representation in their discriminators.

Layout-to-Image Generation

Localization of Cochlear Implant Electrodes from Cone Beam Computed Tomography using Particle Belief Propagation

no code implementations18 Mar 2021 Hendrik Hachmann, Benjamin Krüger, Bodo Rosenhahn, Waldo Nogueira

Currently the methods used in clinics to characterize the geometry of the cochlea as well as to estimate the electrode positions are manual, error-prone and time consuming.

Exploring Dynamic Context for Multi-path Trajectory Prediction

2 code implementations30 Oct 2020 Hao Cheng, Wentong Liao, Xuejiao Tang, Michael Ying Yang, Monika Sester, Bodo Rosenhahn

In our framework, first, the spatial context between agents is explored by using self-attention architectures.

Trajectory Forecasting

TOAD-GAN: Coherent Style Level Generation from a Single Example

2 code implementations4 Aug 2020 Maren Awiszus, Frederik Schubert, Bodo Rosenhahn

In this work, we present TOAD-GAN (Token-based One-shot Arbitrary Dimension Generative Adversarial Network), a novel Procedural Content Generation (PCG) algorithm that generates token-based video game levels.

Lifted Disjoint Paths with Application in Multiple Object Tracking

1 code implementation ICML 2020 Andrea Hornakova, Roberto Henschel, Bodo Rosenhahn, Paul Swoboda

We present an extension to the disjoint paths problem in which additional \emph{lifted} edges are introduced to provide path connectivity priors.

Multiple Object Tracking

AMENet: Attentive Maps Encoder Network for Trajectory Prediction

1 code implementation15 Jun 2020 Hao Cheng, Wentong Liao, Michael Ying Yang, Bodo Rosenhahn, Monika Sester

Trajectory prediction is critical for applications of planning safe future movements and remains challenging even for the next few seconds in urban mixed traffic.

Trajectory Prediction

LR-CNN: Local-aware Region CNN for Vehicle Detection in Aerial Imagery

no code implementations28 May 2020 Wentong Liao, Xiang Chen, Jingfeng Yang, Stefan Roth, Michael Goesele, Michael Ying Yang, Bodo Rosenhahn

This strengthens the local feature invariance for the resampled features and enables detecting vehicles in an arbitrary orientation.

object-detection Object Detection +1

Image Captioning through Image Transformer

2 code implementations29 Apr 2020 Sen He, Wentong Liao, Hamed R. -Tavakoli, Michael Yang, Bodo Rosenhahn, Nicolas Pugeault

Inspired by the successes in text analysis and translation, previous work have proposed the \textit{transformer} architecture for image captioning.

Image Captioning object-detection +3

FairNN- Conjoint Learning of Fair Representations for Fair Decisions

1 code implementation5 Apr 2020 Tongxin Hu, Vasileios Iosifidis, Wentong Liao, Hang Zhang, Michael YingYang, Eirini Ntoutsi, Bodo Rosenhahn

In this paper, we propose FairNN a neural network that performs joint feature representation and classification for fairness-aware learning.

Classification Decision Making +3

MCENET: Multi-Context Encoder Network for Homogeneous Agent Trajectory Prediction in Mixed Traffic

1 code implementation14 Feb 2020 Hao Cheng, Wentong Liao, Michael Ying Yang, Monika Sester, Bodo Rosenhahn

In inference time, we combine the past context and motion information of the target agent with samplings of the latent variables to predict multiple realistic trajectories in the future.

Autonomous Driving Intent Detection +1

NODIS: Neural Ordinary Differential Scene Understanding

1 code implementation ECCV 2020 Cong Yuren, Hanno Ackermann, Wentong Liao, Michael Ying Yang, Bodo Rosenhahn

Detected objects, their labels and the discovered relations can be used to construct a scene graph which provides an abstract semantic interpretation of an image.

Graph Generation Relationship Detection +2

Neural Random Forest Imitation

no code implementations25 Nov 2019 Christoph Reinders, Bodo Rosenhahn

We present Neural Random Forest Imitation - a novel approach for transforming random forests into neural networks.

Structuring Autoencoders

no code implementations7 Aug 2019 Marco Rudolph, Bastian Wandt, Bodo Rosenhahn

In this paper we propose Structuring AutoEncoders (SAE).

Temporally Consistent Horizon Lines

1 code implementation23 Jul 2019 Florian Kluger, Hanno Ackermann, Michael Ying Yang, Bodo Rosenhahn

The horizon line is an important geometric feature for many image processing and scene understanding tasks in computer vision.

3D Reconstruction Autonomous Vehicles +2

Target-Tailored Source-Transformation for Scene Graph Generation

no code implementations3 Apr 2019 Wentong Liao, Cuiling Lan, Wen-Jun Zeng, Michael Ying Yang, Bodo Rosenhahn

We further explore more powerful representations by integrating language prior with the visual context in the transformation for the scene graph generation.

graph construction Graph Generation +4

Security Event Recognition for Visual Surveillance

no code implementations26 Oct 2018 Michael Ying Yang, Wentong Liao, Chun Yang, Yanpeng Cao, Bodo Rosenhahn

The experimental results show that the proposed approach outperforms the state-of-the-art methods and effective in recognizing complex security events.

Recovering Accurate 3D Human Pose in The Wild Using IMUs and a Moving Camera

no code implementations ECCV 2018 Timo von Marcard, Roberto Henschel, Michael J. Black, Bodo Rosenhahn, Gerard Pons-Moll

In this work, we propose a method that combines a single hand-held camera and a set of Inertial Measurement Units (IMUs) attached at the body limbs to estimate accurate 3D poses in the wild.

3D Pose Estimation

Markov Chain Neural Networks

no code implementations2 May 2018 Maren Awiszus, Bodo Rosenhahn

In this work we present a modified neural network model which is capable to simulate Markov Chains.

Temporally Object-based Video Co-Segmentation

no code implementations9 Feb 2018 Michael Ying Yang, Matthias Reso, Jun Tang, Wentong Liao, Bodo Rosenhahn

Therefore, we formulate a graphical model to select a proposal stream for each object in which the pairwise potentials consist of the appearance dissimilarity between different streams in the same video and also the similarity between the streams in different videos.


Video Event Recognition and Anomaly Detection by Combining Gaussian Process and Hierarchical Dirichlet Process Models

no code implementations9 Feb 2018 Michael Ying Yang, Wentong Liao, Yanpeng Cao, Bodo Rosenhahn

In our framework, three levels of video events are connected by Hierarchical Dirichlet Process (HDP) model: low-level visual features, simple atomic activities, and multi-agent interactions.

Anomaly Detection General Classification

Slice Sampling Particle Belief Propagation

no code implementations9 Feb 2018 Oliver Mueller, Michael Ying Yang, Bodo Rosenhahn

We propose to avoid dependence on a proposal distribution by introducing a slice sampling based PBP algorithm.

Image Denoising

Triplet-based Deep Similarity Learning for Person Re-Identification

1 code implementation9 Feb 2018 Wentong Liao, Michael Ying Yang, Ni Zhan, Bodo Rosenhahn

Moreover, we trained the model jointly on six different datasets, which differs from common practice - one model is just trained on one dataset and tested also on the same one.

Person Re-Identification

Vehicle Detection in Aerial Images

no code implementations22 Jan 2018 Michael Ying Yang, Wentong Liao, Xinbo Li, Bodo Rosenhahn

Also, the focal loss function is used to substitute for conventional cross entropy loss function in both of the region proposed network and the final classifier.

object-detection Object Detection

Natural Language Guided Visual Relationship Detection

no code implementations16 Nov 2017 Wentong Liao, Lin Shuai, Bodo Rosenhahn, Michael Ying Yang

Most of the existing works treat this task as a pure visual classification task: each type of relationship or phrase is classified as a relation category based on the extracted visual features.

Relationship Detection Visual Relationship Detection

Object Recognition from very few Training Examples for Enhancing Bicycle Maps

no code implementations18 Sep 2017 Christoph Reinders, Hanno Ackermann, Michael Ying Yang, Bodo Rosenhahn

These algorithms are usually trained on large datasets consisting of thousands or millions of labeled training examples.

Object Recognition Transfer Learning

Automatic tracking of vessel-like structures from a single starting point

no code implementations8 Jun 2017 Dario Augusto Borges Oliveira, Laura Leal-Taixe, Raul Queiroz Feitosa, Bodo Rosenhahn

Further visual results also show the potential of our approach for identifying vascular networks topologies.

Fusion of Head and Full-Body Detectors for Multi-Object Tracking

no code implementations23 May 2017 Roberto Henschel, Laura Leal-Taixé, Daniel Cremers, Bodo Rosenhahn

In order to track all persons in a scene, the tracking-by-detection paradigm has proven to be a very effective approach.

Multi-Object Tracking

Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs

no code implementations23 Mar 2017 Timo von Marcard, Bodo Rosenhahn, Michael J. Black, Gerard Pons-Moll

We address the problem of making human motion capture in the wild more practical by using a small set of inertial sensors attached to the body.

3D Human Pose Estimation

A Kinematic Chain Space for Monocular Motion Capture

no code implementations1 Feb 2017 Bastian Wandt, Hanno Ackermann, Bodo Rosenhahn

This paper deals with motion capture of kinematic chains (e. g. human skeletons) from monocular image sequences taken by uncalibrated cameras.

Industrial Robots

Motion Segmentation via Global and Local Sparse Subspace Optimization

no code implementations24 Jan 2017 Michael Ying Yang, Hanno Ackermann, Weiyao Lin, Sitong Feng, Bodo Rosenhahn

In this paper, we propose a new framework for segmenting feature-based moving objects under affine subspace model.

Clustering Motion Segmentation +2

On Support Relations and Semantic Scene Graphs

no code implementations19 Sep 2016 Michael Ying Yang, Wentong Liao, Hanno Ackermann, Bodo Rosenhahn

In contrast to previous methods for extracting support relations, the proposed approach generates more accurate results, and does not require a pixel-wise semantic labeling of the scene.

Scene Understanding

Tracking with multi-level features

no code implementations25 Jul 2016 Roberto Henschel, Laura Leal-Taixé, Bodo Rosenhahn, Konrad Schindler

We present a novel formulation of the multiple object tracking problem which integrates low and mid-level features.

Clustering Multiple Object Tracking

Multicamera Calibration From Visible and Mirrored Epipoles

no code implementations CVPR 2016 Andrey Bushnevskiy, Lorenzo Sorgi, Bodo Rosenhahn

Multicamera rigs are used in a large number of 3D Vision applications, such as 3D modeling, motion capture or telepresence and a robust calibration is of utmost importance in order to achieve a high accuracy results.

3D Reconstruction

PSyCo: Manifold Span Reduction for Super Resolution

no code implementations CVPR 2016 Eduardo Perez-Pellitero, Jordi Salvador, Javier Ruiz-Hidalgo, Bodo Rosenhahn

The main challenge in Super Resolution (SR) is to discover the mapping between the low- and high-resolution manifolds of image patches, a complex ill-posed problem which has recently been addressed through piecewise linear regression with promising results.

regression Super-Resolution

Automatic 3D Liver Segmentation Using Sparse Representation of Global and Local Image Information via Level Set Formulation

no code implementations6 Aug 2015 Saif Dawood Salman Al-Shaikhli, Michael Ying Yang, Bodo Rosenhahn

A sparse representation of both global (region-based) and local (voxel-wise) image information is embedded in a level set formulation to innovate a new cost function.

Liver Segmentation Segmentation

Expanding Object Detector's Horizon: Incremental Learning Framework for Object Detection in Videos

no code implementations CVPR 2015 Alina Kuznetsova, Sung Ju Hwang, Bodo Rosenhahn, Leonid Sigal

By incrementally detecting object instances in video and adding confident detections into the model, we are able to dynamically adjust the complexity of the detector over time by instantiating new prototypes to span all domains the model has seen.

Domain Adaptation Incremental Learning +3

Learning an Image-based Motion Context for Multiple People Tracking

no code implementations CVPR 2014 Laura Leal-Taixe, Michele Fenzi, Alina Kuznetsova, Bodo Rosenhahn, Silvio Savarese

We present a novel method for multiple people tracking that leverages a generalized model for capturing interactions among individuals.

Multiple People Tracking

Class Generative Models Based on Feature Regression for Pose Estimation of Object Categories

no code implementations CVPR 2013 Michele Fenzi, Laura Leal-Taixe, Bodo Rosenhahn, Jorn Ostermann

In this paper, we propose a method for learning a class representation that can return a continuous value for the pose of an unknown class instance using only 2D data and weak 3D labelling information.

Pose Estimation regression

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