Search Results for author:
Found 30 papers, 5 papers with code
uTRAND: Unsupervised Anomaly Detection in Traffic Trajectories
Deep learning-based approaches have achieved significant improvements on public video anomaly datasets, but often do not perform well in real-world applications.
Detection of Object Throwing Behavior in Surveillance Videos
Second, we compare the performance of different feature extractors for our anomaly detection method on the UCF-Crime and Throwing-Action datasets.
Transformer-based Fusion of 2D-pose and Spatio-temporal Embeddings for Distracted Driver Action Recognition
The model uses 2D-pose features as the positional embedding of the transformer architecture and spatio-temporal features as the main input to the encoder of the transformer.
Density-Guided Label Smoothing for Temporal Localization of Driving Actions
Temporal localization of driving actions plays a crucial role in advanced driver-assistance systems and naturalistic driving studies.
Automated Camera Calibration via Homography Estimation with GNNs
We propose a framework involving the generation of a set of synthetic intersection viewpoint images from a bird's-eye-view image, framed as a graph of virtual cameras to model these images.
IndustReal: A Dataset for Procedure Step Recognition Handling Execution Errors in Egocentric Videos in an Industrial-Like Setting
Annotations and benchmark performance are provided for action recognition and assembly state detection, as well as the new PSR task.
Homography Estimation in Complex Topological Scenes
Surveillance videos and images are used for a broad set of applications, ranging from traffic analysis to crime detection.
Investigating and Improving Latent Density Segmentation Models for Aleatoric Uncertainty Quantification in Medical Imaging
The results indicate that by encouraging a homogeneous latent space, one can significantly improve latent density modeling for medical image segmentation.
A signal processing interpretation of noise-reduction convolutional neural networks
Encoding-decoding CNNs play a central role in data-driven noise reduction and can be found within numerous deep-learning algorithms.
Probabilistic 3D segmentation for aleatoric uncertainty quantification in full 3D medical data
To this end, we have developed a 3D probabilistic segmentation framework augmented with NFs, to enable capturing the distributions of various complexity.
Towards real-time 6D pose estimation of objects in single-view cone-beam X-ray
Deep learning-based pose estimation algorithms can successfully estimate the pose of objects in an image, especially in the field of color images.
Efficient Out-of-Distribution Detection of Melanoma with Wavelet-based Normalizing Flows
In this work, we aim at using these biases with domain-level knowledge of melanoma, to improve likelihood-based OOD detection of malignant images.
Improved Pancreatic Tumor Detection by Utilizing Clinically-Relevant Secondary Features
Pancreatic cancer is one of the global leading causes of cancer-related deaths.
Medical Instrument Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning
These results are better than the state-of-the-art SSL methods and the inference time is comparable to the supervised approaches.
Safe Fakes: Evaluating Face Anonymizers for Face Detectors
Our experiments investigate the suitability of anonymization methods for maintaining face detector performance, the effect of detectors overtraining on anonymization artefacts, dataset size for training an anonymizer, and the effect of training time of anonymization GANs.
Weakly-supervised Learning For Catheter Segmentation in 3D Frustum Ultrasound
Accurate and efficient catheter segmentation in 3D ultrasound (US) is essential for cardiac intervention.
Medical Instrument Detection in Ultrasound-Guided Interventions: A Review
Medical instrument detection is essential for computer-assisted interventions since it would facilitate the surgeons to find the instrument efficiently with a better interpretation, which leads to a better outcome.
Deep Q-Network-Driven Catheter Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning and Dual-UNet
To train the Dual-UNet with limited labeled images and leverage information of unlabeled images, we propose a novel semi-supervised scheme, which exploits unlabeled images based on hybrid constraints from predictions.
Dual Embedding Expansion for Vehicle Re-identification
In contrast, our work concentrates on re-ranking and embedding expansion techniques.
Contextual Pyramid Attention Network for Building Segmentation in Aerial Imagery
Building extraction from aerial images has several applications in problems such as urban planning, change detection, and disaster management.
Adversarial Loss for Semantic Segmentation of Aerial Imagery
We also perform ablation studies to understand the impact of the adversarial loss.
Gradient Boosting on Decision Trees for Mortality Prediction in Transcatheter Aortic Valve Implantation
In combination with a recent technique for model interpretations, we developed a feature analysis and selection stage, enabling to identify the most important features for the prediction.
Privacy Protection in Street-View Panoramas using Depth and Multi-View Imagery
The current paradigm in privacy protection in street-view images is to detect and blur sensitive information.
Aggregated Deep Local Features for Remote Sensing Image Retrieval
In this paper, we present an image retrieval pipeline that uses attentive, local convolutional features and aggregates them using the Vector of Locally Aggregated Descriptors (VLAD) to produce a global descriptor.
LiDAR-assisted Large-scale Privacy Protection in Street-view Cycloramas
We propose a system that is cost-effective even after increasing the resolution by a factor of 2. 5.
Improving Catheter Segmentation & Localization in 3D Cardiac Ultrasound Using Direction-Fused FCN
Fast and accurate catheter detection in cardiac catheterization using harmless 3D ultrasound (US) can improve the efficiency and outcome of the intervention.
Bootstrapped CNNs for Building Segmentation on RGB-D Aerial Imagery
Detection of buildings and other objects from aerial images has various applications in urban planning and map making.
Conditional Transfer with Dense Residual Attention: Synthesizing traffic signs from street-view imagery
We have performed detection and classification tests across a large number of traffic sign classes, by training the detector using the combination of real and generated data.
Proceedings of Workshop AEW10: Concepts in Information Theory and Communications
The 10th Asia-Europe workshop in "Concepts in Information Theory and Communications" AEW10 was held in Boppard, Germany on June 21-23, 2017.
Information Theory Information Theory 68P30, 94A05
Free-Space Detection with Self-Supervised and Online Trained Fully Convolutional Networks
Experiments show that the online training boosts performance with 5% when compared to offline training, both for Fmax and AP.
