79 citations · 608 across the 98 of their papers we have counts for
25 papers · 2 filters
Uncertainty-aware Vision-based Metric Cross-view Geolocalization
Florian Fervers, Sebastian Bullinger, Christoph Bodensteiner +2
This paper proposes a novel method for vision-based metric cross-view geolocalization (CVGL) that matches the camera images captured from a ground-based vehicle with an aerial imag…
Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation
Zeyun Zhong, David Schneider, Michael Voit +2
Although human action anticipation is a task which is inherently multi-modal, state-of-the-art methods on well known action anticipation datasets leverage this data by applying ens…
Detailed Annotations of Chest X-Rays via CT Projection for Report Understanding
Constantin Seibold, Simon Reiß, Saquib Sarfraz +7
In clinical radiology reports, doctors capture important information about the patient's health status. They convey their observations from raw medical imaging data about the inner…
ModSelect: Automatic Modality Selection for Synthetic-to-Real Domain Generalization
Zdravko Marinov, Alina Roitberg, David Schneider +1
Modality selection is an important step when designing multimodal systems, especially in the case of cross-domain activity recognition as certain modalities are more robust to doma…
Multi-modal Depression Estimation based on Sub-attentional Fusion
Ping-Cheng Wei, Kunyu Peng, Alina Roitberg +3
Failure to timely diagnose and effectively treat depression leads to over 280 million people suffering from this psychological disorder worldwide. The information cues of depressio…
Multimodal Generation of Novel Action Appearances for Synthetic-to-Real Recognition of Activities of Daily Living
Zdravko Marinov, David Schneider, Alina Roitberg +1
Domain shifts, such as appearance changes, are a key challenge in real-world applications of activity recognition models, which range from assistive robotics and smart homes to dri…
Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation
Jiaming Zhang, Kailun Yang, Hao Shi +7
In this paper, we address panoramic semantic segmentation which is under-explored due to two critical challenges: (1) image distortions and object deformations on panoramas; (2) la…
Trans4Map: Revisiting Holistic Bird's-Eye-View Mapping from Egocentric Images to Allocentric Semantics with Vision Transformers
Chang Chen, Jiaming Zhang, Kailun Yang +2
Humans have an innate ability to sense their surroundings, as they can extract the spatial representation from the egocentric perception and form an allocentric semantic map via sp…
Panoramic Panoptic Segmentation: Insights Into Surrounding Parsing for Mobile Agents via Unsupervised Contrastive Learning
Alexander Jaus, Kailun Yang, Rainer Stiefelhagen
In this work, we introduce panoramic panoptic segmentation, as the most holistic scene understanding, both in terms of Field of View (FoV) and image-level understanding for standar…
Breaking with Fixed Set Pathology Recognition through Report-Guided Contrastive Training
Constantin Seibold, Simon Reiß, M. Saquib Sarfraz +2
When reading images, radiologists generate text reports describing the findings therein. Current state-of-the-art computer-aided diagnosis tools utilize a fixed set of predefined c…
Towards Automatic Parsing of Structured Visual Content through the Use of Synthetic Data
Lukas Scholch, Jonas Steinhauser, Maximilian Beichter +6
Structured Visual Content (SVC) such as graphs, flow charts, or the like are used by authors to illustrate various concepts. While such depictions allow the average reader to bette…
A Comparative Analysis of Decision-Level Fusion for Multimodal Driver Behaviour Understanding
Alina Roitberg, Kunyu Peng, Zdravko Marinov +3
Visual recognition inside the vehicle cabin leads to safer driving and more intuitive human-vehicle interaction but such systems face substantial obstacles as they need to capture…
Is my Driver Observation Model Overconfident? Input-guided Calibration Networks for Reliable and Interpretable Confidence Estimates
Alina Roitberg, Kunyu Peng, David Schneider +4
Driver observation models are rarely deployed under perfect conditions. In practice, illumination, camera placement and type differ from the ones present during training and unfore…
Indoor Navigation Assistance for Visually Impaired People via Dynamic SLAM and Panoptic Segmentation with an RGB-D Sensor
Wenyan Ou, Jiaming Zhang, Kunyu Peng +4
Exploring an unfamiliar indoor environment and avoiding obstacles is challenging for visually impaired people. Currently, several approaches achieve the avoidance of static obstacl…
Towards Robust Semantic Segmentation of Accident Scenes via Multi-Source Mixed Sampling and Meta-Learning
Xinyu Luo, Jiaming Zhang, Kailun Yang +3
Autonomous vehicles utilize urban scene segmentation to understand the real world like a human and react accordingly. Semantic segmentation of normal scenes has experienced a remar…
Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation
Jiaming Zhang, Kailun Yang, Chaoxiang Ma +3
Panoramic images with their 360-degree directional view encompass exhaustive information about the surrounding space, providing a rich foundation for scene understanding. To unfold…
Hierarchical Nearest Neighbor Graph Embedding for Efficient Dimensionality Reduction
M. Saquib Sarfraz, Marios Koulakis, Constantin Seibold +1
Dimensionality reduction is crucial both for visualization and preprocessing high dimensional data for machine learning. We introduce a novel method based on a hierarchy built on 1…
MatchFormer: Interleaving Attention in Transformers for Feature Matching
Qing Wang, Jiaming Zhang, Kailun Yang +2
Local feature matching is a computationally intensive task at the subpixel level. While detector-based methods coupled with feature descriptors struggle in low-texture scenes, CNN-…
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers
Jiaming Zhang, Huayao Liu, Kailun Yang +3
Scene understanding based on image segmentation is a crucial component of autonomous vehicles. Pixel-wise semantic segmentation of RGB images can be advanced by exploiting compleme…
Continuous Self-Localization on Aerial Images Using Visual and Lidar Sensors
Florian Fervers, Sebastian Bullinger, Christoph Bodensteiner +2
This paper proposes a novel method for geo-tracking, i.e. continuous metric self-localization in outdoor environments by registering a vehicle's sensor information with aerial imag…
Revisiting Click-based Interactive Video Object Segmentation
Stephane Vujasinovic, Sebastian Bullinger, Stefan Becker +3
While current methods for interactive Video Object Segmentation (iVOS) rely on scribble-based interactions to generate precise object masks, we propose a Click-based interactive Vi…
TransDARC: Transformer-based Driver Activity Recognition with Latent Space Feature Calibration
Kunyu Peng, Alina Roitberg, Kailun Yang +2
Traditional video-based human activity recognition has experienced remarkable progress linked to the rise of deep learning, but this effect was slower as it comes to the downstream…
TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation
Ruiping Liu, Kailun Yang, Alina Roitberg +5
Semantic segmentation benchmarks in the realm of autonomous driving are dominated by large pre-trained transformers, yet their widespread adoption is impeded by substantial computa…
Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions
Kunyu Peng, Alina Roitberg, Kailun Yang +2
Occlusions are universal disruptions constantly present in the real world. Especially for sparse representations, such as human skeletons, a few occluded points might destroy the g…