Search Results for author:
Found 26 papers, 8 papers with code
A Review and Efficient Implementation of Scene Graph Generation Metrics
Scene graph generation has emerged as a prominent research field in computer vision, witnessing significant advancements in the recent years.
Adapting the Segment Anything Model During Usage in Novel Situations
The interactive segmentation task consists in the creation of object segmentation masks based on user interactions.
Towards Learning Monocular 3D Object Localization From 2D Labels using the Physical Laws of Motion
We present a novel method for precise 3D object localization in single images from a single calibrated camera using only 2D labels.
Haystack: A Panoptic Scene Graph Dataset to Evaluate Rare Predicate Classes
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.
The STOIC2021 COVID-19 AI challenge: applying reusable training methodologies to private data
STOIC2021 consisted of a Qualification phase, where participants developed challenge solutions using 2000 publicly available CT scans, and a Final phase, where participants submitted their training methodologies with which solutions were trained on CT scans of 9724 subjects.
Impact of Pseudo Depth on Open World Object Segmentation with Minimal User Guidance
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.
All Keypoints You Need: Detecting Arbitrary Keypoints on the Body of Triple, High, and Long Jump Athletes
Performance analyses based on videos are commonly used by coaches of athletes in various sports disciplines.
Detecting Arbitrary Keypoints on Limbs and Skis with Sparse Partly Correct Segmentation Masks
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.
Pseudo-Label Noise Suppression Techniques for Semi-Supervised Semantic Segmentation
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.
Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers
The state-of-the-art for monocular 3D human pose estimation in videos is dominated by the paradigm of 2D-to-3D pose uplifting.
COVID Detection and Severity Prediction with 3D-ConvNeXt and Custom Pretrainings
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.
Recognition of Freely Selected Keypoints on Human Limbs
Nearly all Human Pose Estimation (HPE) datasets consist of a fixed set of keypoints.
Extended Self-Critical Pipeline for Transforming Videos to Text (TRECVID-VTT Task 2021) -- Team: MMCUniAugsburg
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.
Synchronized Audio-Visual Frames with Fractional Positional Encoding for Transformers in Video-to-Text Translation
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.
Semantically Consistent Image-to-Image Translation for Unsupervised Domain Adaptation
Unsupervised Domain Adaptation (UDA) aims to adapt models trained on a source domain to a new target domain where no labelled data is available.
Error Bounds of Projection Models in Weakly Supervised 3D Human Pose Estimation
Our paper thus establishes a theoretical baseline that shows the importance of suitable projection models in weakly supervised 3D human pose estimation.
Decoupling Video and Human Motion: Towards Practical Event Detection in Athlete Recordings
In this paper we address the problem of motion event detection in athlete recordings from individual sports.
Addressing Data Bias Problems for Chest X-ray Image Report Generation
Automatic medical report generation from chest X-ray images is one possibility for assisting doctors to reduce their workload.
Image Captioning with Clause-Focused Metrics in a Multi-Modal Setting for Marketing
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.
Mining Automatically Estimated Poses from Video Recordings of Top Athletes
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
Thanks to adding the third output modality, it also considerably improves the quality of generated captions for images depicting branded products.
Activity-conditioned continuous human pose estimation for performance analysis of athletes using the example of swimming
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.
Improving Small Object Proposals for Company Logo Detection
Many modern approaches for object detection are two-staged pipelines.
Diversity in Object Proposals
Current top performing object recognition systems build on object proposals as a preprocessing step.
Key-Pose Prediction in Cyclic Human Motion
In this paper we study the problem of estimating innercyclic time intervals within repetitive motion sequences of top-class swimmers in a swimming channel.
Scalable logo recognition in real-world images
In this paper we propose a highly effective and scalable framework for recognizing logos in images.
