Unified open-vocabulary dense visual prediction

H Shi, M Hayat, J Cai - IEEE Transactions on Multimedia, 2024 - ieeexplore.ieee.org
In recent years, open-vocabulary (OV) dense visual prediction (such as OV object detection,
semantic, instance and panoptic segmentations) has attracted increasing research attention …

Ugains: Uncertainty guided anomaly instance segmentation

A Nekrasov, A Hermans, L Kuhnert, B Leibe - DAGM German Conference …, 2023 - Springer
A single unexpected object on the road can cause an accident or may lead to injuries. To
prevent this, we need a reliable mechanism for finding anomalous objects on the road. This …

[PDF][PDF] Imaging with Confidence: Uncertainty Quantification for High-dimensional Undersampled MR Images

F Hoppe, CM Verdun, H Laus, S Endt… - … on Computer Vision …, 2024 - fq.pkwyx.com
Establishing certified uncertainty quantification (UQ) in imaging processing applications
continues to pose a significant challenge. In particular, such a goal is crucial for accurate …

Object detection as probabilistic set prediction

G Hess, C Petersson, L Svensson - European Conference on Computer …, 2022 - Springer
Accurate uncertainty estimates are essential for deploying deep object detectors in safety-
critical systems. The development and evaluation of probabilistic object detectors have been …

High accurate and explainable multi-pill detection framework with graph neural network-assisted multimodal data fusion

AD Nguyen, HH Pham, HT Trung, QVH Nguyen… - Plos one, 2023 - journals.plos.org
Due to the significant resemblance in visual appearance, pill misuse is prevalent and has
become a critical issue, responsible for one-third of all deaths worldwide. Pill identification …

CoBaIR: A python library for context-based intention recognition in human-robot-interaction

A Lubitz, L Gutzeit, F Kirchner - 2023 32nd IEEE International …, 2023 - ieeexplore.ieee.org
Human-Robot Interaction (HRI) becomes more and more important in a world where robots
integrate fast in all aspects of our lives but HRI applications depend massively on the utilized …

Digital Semantic Communications: An Alternating Multi-Phase Training Strategy with Mask Attack

M Gong, S Wang, S Bi, Y Wu, L Qian - arXiv preprint arXiv:2408.04972, 2024 - arxiv.org
Semantic communication (SemComm) has emerged as new paradigm shifts. Most existing
SemComm systems transmit continuously distributed signals in analog fashion. However …

Comparison of uncertainty quantification with deep learning in time series regression

L Foldesi, M Valdenegro-Toro - arXiv preprint arXiv:2211.06233, 2022 - arxiv.org
Increasingly high-stakes decisions are made using neural networks in order to make
predictions. Specifically, meteorologists and hedge funds apply these techniques to time …

Towards robust uncertainty estimation in the presence of noisy labels

C Pan, B Yuan, W Zhou, X Yao - International Conference on Artificial …, 2022 - Springer
In security-critical applications, it is essential to know how confident the model is in its
predictions. Many uncertainty estimation methods have been proposed recently, and these …

Sensor Fusion using Probabilistic Object Detection for State Estimation

S Subedi, L Höhndorf, R Kulaga, Z Hodaie… - AIAA AVIATION 2023 …, 2023 - arc.aiaa.org
View Video Presentation: https://doi. org/10.2514/6.2023-3561. vid Kalman filtering for
global navigation satellite systems (GNSS)-aided inertial navigation has been widely used …