Search Results - "Possegger, Horst"

In defense of color-based model-free tracking by Possegger, Horst, Mauthner, Thomas, Bischof, Horst

“…In this paper, we address the problem of model-free online object tracking based on color representations. According to the findings of recent benchmark…”
Get full text

Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly by Opitz, Michael, Waltner, Georg, Possegger, Horst, Bischof, Horst

“…Learning similarity functions between image pairs with deep neural networks yields highly correlated activations of embeddings. In this work, we show how to…”
Get full text

The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization by Mirza, M. Jehanzeb, Micorek, Jakub, Possegger, Horst, Bischof, Horst

“…Domain adaptation is crucial to adapt a learned model to new scenarios, such as domain shifts or changing data distributions. Current approaches usually…”
Get full text

BIER - Boosting Independent Embeddings Robustly by Opitz, Michael, Waltner, Georg, Possegger, Horst, Bischof, Horst

“…Learning similarity functions between image pairs with deep neural networks yields highly correlated activations of large embeddings. In this work, we show how…”
Get full text

FuseSeg: LiDAR Point Cloud Segmentation Fusing Multi-Modal Data by Krispel, Georg, Opitz, Michael, Waltner, Georg, Possegger, Horst, Bischof, Horst

“…We introduce a simple yet effective fusion method of LiDAR and RGB data to segment LiDAR point clouds. Utilizing the dense native range representation of a…”
Get full text

ATS: Adaptive Temperature Scaling for Enhancing Out-of-Distribution Detection Methods by Krumpl, Gerhard, Avenhaus, Henning, Possegger, Horst, Bischof, Horst

“…Out-of-distribution (OOD) detection is essential to ensure the reliability and robustness of machine learning models in real-world applications. Post-hoc OOD…”
Get full text

Robust Localization of Key Fob Using Channel Impulse Response of Ultra Wide Band Sensors for Keyless Entry Systems by Kolli, Abhiram, Casamassima, Filippo, Possegger, Horst, Bischof, Horst

“…Using neural networks for localization of key fob within and surrounding a car as a security feature for keyless entry is fast emerging. In this paper we…”
Get full text

Spatiotemporal Saliency Estimation by Spectral Foreground Detection by Aytekin, Caglar, Possegger, Horst, Mauthner, Thomas, Kiranyaz, Serkan, Bischof, Horst, Gabbouj, Moncef

“…We present a novel approach for spatiotemporal saliency detection by optimizing a unified criterion of color contrast, motion contrast, appearance, and…”
Get full text

SAILOR: Scaling Anchors via Insights into Latent Object Representation by Malic, Dusan, Fruhwirth-Reisinger, Christian, Possegger, Horst, Bischof, Horst

“…LiDAR 3D object detection models are inevitably biased towards their training dataset. The detector clearly exhibits this bias when employed on a target…”
Get full text

OccAM's Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR Data by Schinagl, David, Krispel, Georg, Possegger, Horst, Roth, Peter M., Bischof, Horst

“…While 3D object detection in LiDAR point clouds is well-established in academia and industry, the explainability of these models is a largely unexplored field…”
Get full text

MAELi: Masked Autoencoder for Large-Scale LiDAR Point Clouds by Krispel, Georg, Schinagl, David, Fruhwirth-Reisinger, Christian, Possegger, Horst, Bischof, Horst

“…The sensing process of large-scale LiDAR point clouds inevitably causes large blind spots, i.e. regions not visible to the sensor. We demonstrate how these…”
Get full text

The Visual Object Tracking VOT2015 Challenge Results by Kristan, Matej, Matas, Jiri, Leonardis, Ale, Felsberg, Michael, Cehovin, Luka, Fernandez, Gustavo, Vojir, Toma, Hager, Gustav, Nebehay, Georg, Pflugfelder, Roman, Gupta, Abhinav, Bibi, Adel, Lukezic, Alan, Garcia-Martin, Alvaro, Saffari, Amir, Petrosino, Alfredo, Solis Montero, Andrés

“…The Visual Object Tracking challenge 2015, VOT2015, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object…”
Get full text

Video Test-Time Adaptation for Action Recognition by Lin, Wei, Mirza, Muhammad Jehanzeb, Kozinski, Mateusz, Possegger, Horst, Kuehne, Hilde, Bischof, Horst

“…Although action recognition systems can achieve top performance when evaluated on in-distribution test points, they are vulnerable to unanticipated…”
Get full text

ActMAD: Activation Matching to Align Distributions for Test-Time-Training by Mirza, M. Jehanzeb, Soneira, Pol Jane, Lin, Wei, Kozinski, Mateusz, Possegger, Horst, Bischof, Horst

“…Test-Time-Training (TTT) is an approach to cope with out-of-distribution (OOD) data by adapting a trained model to distribution shifts occurring at test-time…”
Get full text

Encoding based saliency detection for videos and images by Mauthner, Thomas, Possegger, Horst, Waltner, Georg, Bischof, Horst

“…We present a novel video saliency detection method to support human activity recognition and weakly supervised training of activity detection algorithms…”
Get full text

Occlusion Geodesics for Online Multi-object Tracking by Possegger, Horst, Mauthner, Thomas, Roth, Peter M., Bischof, Horst

“…Robust multi-object tracking-by-detection requires the correct assignment of noisy detection results to object trajectories. We address this problem by…”
Get full text

Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions by Leitner, Stefan, Mirza, M. Jehanzeb, Lin, Wei, Micorek, Jakub, Masana, Marc, Kozinski, Mateusz, Possegger, Horst, Bischof, Horst

“…In autonomous driving scenarios, current object detection models show strong performance when tested in clear weather. However, their performance deteriorates…”
Get full text

Semi-Supervised Learning Of Monocular 3D Hand Pose Estimation From Multi-View Images by Muller, Markus, Poier, Georg, Possegger, Horst, Bischof, Horst

“…Most modern hand pose estimation methods rely on Convolutional Neural Networks (CNNs), which typically require a large training dataset to perform well…”
Get full text

Efficient Motion Prediction: A Lightweight & Accurate Trajectory Prediction Model With Fast Training and Inference Speed by Prutsch, Alexander, Bischof, Horst, Possegger, Horst

“…For efficient and safe autonomous driving, it is essential that autonomous vehicles can predict the motion of other traffic agents. While highly accurate,…”
Get full text

An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions by Jehanzeb Mirza, M., Masana, Marc, Possegger, Horst, Bischof, Horst

“…Although deep neural networks enable impressive visual perception performance for autonomous driving, their robustness to varying weather conditions still…”
Get full text