Search Results for author: Rainer Lienhart

Found 29 papers, 9 papers with code

A Fair Ranking and New Model for Panoptic Scene Graph Generation

no code implementations12 Jul 2024 Julian Lorenz, Alexander Pest, Daniel Kienzle, Katja Ludwig, Rainer Lienhart

The observed scores for existing methods increase by up to 7. 4 mR@50 for all two-stage methods, while dropping by up to 19. 3 mR@50 for all one-stage methods, highlighting the importance of a correct evaluation.

WSESeg: Introducing a Dataset for the Segmentation of Winter Sports Equipment with a Baseline for Interactive Segmentation

no code implementations12 Jul 2024 Robin Schön, Daniel Kienzle, Rainer Lienhart

In this paper we introduce a new dataset containing instance segmentation masks for ten different categories of winter sports equipment, called WSESeg (Winter Sports Equipment Segmentation).

Segformer++: Efficient Token-Merging Strategies for High-Resolution Semantic Segmentation

1 code implementation23 May 2024 Daniel Kienzle, Marco Kantonis, Robin Schön, Rainer Lienhart

Utilizing transformer architectures for semantic segmentation of high-resolution images is hindered by the attention's quadratic computational complexity in the number of tokens.

Image Classification Pose Estimation +2

A Review and Efficient Implementation of Scene Graph Generation Metrics

no code implementations15 Apr 2024 Julian Lorenz, Robin Schön, Katja Ludwig, Rainer Lienhart

Scene graph generation has emerged as a prominent research field in computer vision, witnessing significant advancements in the recent years.

Benchmarking Graph Generation +1

Adapting the Segment Anything Model During Usage in Novel Situations

no code implementations12 Apr 2024 Robin Schön, Julian Lorenz, Katja Ludwig, Rainer Lienhart

The interactive segmentation task consists in the creation of object segmentation masks based on user interactions.

Interactive Segmentation Object +2

Towards Learning Monocular 3D Object Localization From 2D Labels using the Physical Laws of Motion

1 code implementation26 Oct 2023 Daniel Kienzle, Julian Lorenz, Katja Ludwig, Rainer Lienhart

We present a novel method for precise 3D object localization in single images from a single calibrated camera using only 2D labels.

Monocular 3D Object Localization Object

Haystack: A Panoptic Scene Graph Dataset to Evaluate Rare Predicate Classes

no code implementations5 Sep 2023 Julian Lorenz, Florian Barthel, Daniel Kienzle, Rainer Lienhart

We construct a new panoptic scene graph dataset and a set of metrics that are designed as a benchmark for the predictive performance especially on rare predicate classes.

Graph Generation Scene Graph Generation

Impact of Pseudo Depth on Open World Object Segmentation with Minimal User Guidance

no code implementations12 Apr 2023 Robin Schön, Katja Ludwig, Rainer Lienhart

In order to tell our network which object to segment, we provide the network with a single click on the object's surface on the pseudo depth map of the image as input.

Object Semantic Segmentation

Detecting Arbitrary Keypoints on Limbs and Skis with Sparse Partly Correct Segmentation Masks

1 code implementation17 Nov 2022 Katja Ludwig, Daniel Kienzle, Julian Lorenz, Rainer Lienhart

We analyze different training techniques for freely selected and standard keypoints, including pseudo labels, and show in our experiments that only a few partly correct segmentation masks are sufficient for learning to detect arbitrary keypoints on limbs and skis.

Segmentation

Pseudo-Label Noise Suppression Techniques for Semi-Supervised Semantic Segmentation

1 code implementation19 Oct 2022 Sebastian Scherer, Robin Schön, Rainer Lienhart

Current SSL approaches use an initially supervised trained model to generate predictions for unlabelled images, called pseudo-labels, which are subsequently used for training a new model from scratch.

Pose Estimation Pseudo Label +2

Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers

1 code implementation12 Oct 2022 Moritz Einfalt, Katja Ludwig, Rainer Lienhart

The state-of-the-art for monocular 3D human pose estimation in videos is dominated by the paradigm of 2D-to-3D pose uplifting.

2D Pose Estimation Monocular 3D Human Pose Estimation

COVID Detection and Severity Prediction with 3D-ConvNeXt and Custom Pretrainings

1 code implementation30 Jun 2022 Daniel Kienzle, Julian Lorenz, Robin Schön, Katja Ludwig, Rainer Lienhart

We introduce a neural network for the prediction of the severity of lung damage and the detection of a COVID-infection using three-dimensional CT-data.

severity prediction

Recognition of Freely Selected Keypoints on Human Limbs

no code implementations13 Apr 2022 Katja Ludwig, Daniel Kienzle, Rainer Lienhart

Nearly all Human Pose Estimation (HPE) datasets consist of a fixed set of keypoints.

Pose Estimation

Synchronized Audio-Visual Frames with Fractional Positional Encoding for Transformers in Video-to-Text Translation

no code implementations28 Dec 2021 Philipp Harzig, Moritz Einfalt, Rainer Lienhart

Video-to-Text (VTT) is the task of automatically generating descriptions for short audio-visual video clips, which can support visually impaired people to understand scenes of a YouTube video for instance.

Image Captioning Machine Translation +2

Extended Self-Critical Pipeline for Transforming Videos to Text (TRECVID-VTT Task 2021) -- Team: MMCUniAugsburg

no code implementations28 Dec 2021 Philipp Harzig, Moritz Einfalt, Katja Ludwig, Rainer Lienhart

For both models, we train on the complete VATEX dataset and 90% of the TRECVID-VTT dataset for pretraining while using the remaining 10% for validation.

Image Captioning

Semantically Consistent Image-to-Image Translation for Unsupervised Domain Adaptation

no code implementations5 Nov 2021 Stephan Brehm, Sebastian Scherer, Rainer Lienhart

Unsupervised Domain Adaptation (UDA) aims to adapt models trained on a source domain to a new target domain where no labelled data is available.

Image-to-Image Translation Semantic Segmentation +2

Error Bounds of Projection Models in Weakly Supervised 3D Human Pose Estimation

no code implementations23 Oct 2020 Nikolas Klug, Moritz Einfalt, Stephan Brehm, Rainer Lienhart

Our paper thus establishes a theoretical baseline that shows the importance of suitable projection models in weakly supervised 3D human pose estimation.

Monocular 3D Human Pose Estimation Position +1

Decoupling Video and Human Motion: Towards Practical Event Detection in Athlete Recordings

no code implementations21 Apr 2020 Moritz Einfalt, Rainer Lienhart

In this paper we address the problem of motion event detection in athlete recordings from individual sports.

Event Detection

Addressing Data Bias Problems for Chest X-ray Image Report Generation

no code implementations6 Aug 2019 Philipp Harzig, Yan-Ying Chen, Francine Chen, Rainer Lienhart

Automatic medical report generation from chest X-ray images is one possibility for assisting doctors to reduce their workload.

Medical Report Generation Sentence

Image Captioning with Clause-Focused Metrics in a Multi-Modal Setting for Marketing

1 code implementation6 May 2019 Philipp Harzig, Dan Zecha, Rainer Lienhart, Carolin Kaiser, René Schallner

Furthermore, we introduce a novel metric that allows us to assess whether the generated captions meet our requirements (i. e., subject, predicate, object, and product name) and describe a series of experiments on caption quality and how to address annotator disagreements for the image ratings with an approach called soft targets.

Descriptive Image Captioning +2

Mining Automatically Estimated Poses from Video Recordings of Top Athletes

no code implementations24 Apr 2018 Rainer Lienhart, Moritz Einfalt, Dan Zecha

Human pose detection systems based on state-of-the-art DNNs are on the go to be extended, adapted and re-trained to fit the application domain of specific sports.

Multimodal Image Captioning for Marketing Analysis

no code implementations6 Feb 2018 Philipp Harzig, Stephan Brehm, Rainer Lienhart, Carolin Kaiser, René Schallner

Thanks to adding the third output modality, it also considerably improves the quality of generated captions for images depicting branded products.

Image Captioning Marketing

Activity-conditioned continuous human pose estimation for performance analysis of athletes using the example of swimming

no code implementations2 Feb 2018 Moritz Einfalt, Dan Zecha, Rainer Lienhart

Our main contributions are threefold: (a) We apply and evaluate a fine-tuned Convolutional Pose Machine architecture as a baseline in our very challenging aquatic environment and discuss its error modes, (b) we propose an extension to input swimming style information into the fully convolutional architecture and (c) modify the architecture for continuous pose estimation in videos.

Pose Estimation

Diversity in Object Proposals

no code implementations14 Mar 2016 Anton Winschel, Rainer Lienhart, Christian Eggert

Current top performing object recognition systems build on object proposals as a preprocessing step.

Diversity Object +1

Key-Pose Prediction in Cyclic Human Motion

no code implementations21 Apr 2015 Dan Zecha, Rainer Lienhart

In this paper we study the problem of estimating innercyclic time intervals within repetitive motion sequences of top-class swimmers in a swimming channel.

Pose Prediction

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