24 citations · 35 across the 32 of their papers we have counts for
32 papers
Hand-centric Human-to-Robot Trajectory Transfer from Video Demonstrations via Object Category-agnostic Temporal Localization
Yitian Shi, Di Wen, Zhengqi Han +6
Human videos provide a scalable source of demonstrations for robot imitation learning. However, converting them into executable and semantically aligned robot trajectories requires…
Multi-modal Video Representation Alignment for Robust Self-supervised Driver Distraction Detection
David J. Lerch, Livien Majer, Zeyun Zhong +3
Robust self-supervised learning of multi-modal video representations is critical for real-world applications such as driver distraction detection, where multiple sensors provide co…
Vision-language Models for Driver Monitoring Systems: A Driver Activity Description Dataset
David J. Lerch, Sarath Mulugurthi, Manuel Martin +2
Understanding subtle driver actions is essential for building reliable driver monitoring systems. Existing visionlanguage models (VLMs) are trained on general datasets and struggle…
CHAOS: Chart Analysis with Outlier Samples
Omar Moured, Yufan Chen, Ruiping Liu +4
Charts play a critical role in data analysis and visualization, yet real-world applications often present charts with challenging or noisy features. However, "outlier charts" pose…
Scene-agnostic Pose Regression for Visual Localization
Junwei Zheng, Ruiping Liu, Yufan Chen +4
Absolute Pose Regression (APR) predicts 6D camera poses but lacks the adaptability to unknown environments without retraining, while Relative Pose Regression (RPR) generalizes bett…
RefChartQA: Grounding Visual Answer on Chart Images through Instruction Tuning
Alexander Vogel, Omar Moured, Yufan Chen +2
Recently, Vision Language Models (VLMs) have increasingly emphasized document visual grounding to achieve better human-computer interaction, accessibility, and detailed understandi…
SFDLA: Source-Free Document Layout Analysis
Sebastian Tewes, Yufan Chen, Omar Moured +2
Document Layout Analysis (DLA) is a fundamental task in document understanding. However, existing DLA and adaptation methods often require access to large-scale source data and tar…
ObjectFinder: An Open-Vocabulary Assistive System for Interactive Object Search by Blind People
Ruiping Liu, Jiaming Zhang, Angela Schön +6
Searching for objects in unfamiliar scenarios is a challenging task for blind people. It involves specifying the target object, detecting it, and then gathering detailed informatio…
Deformable Mamba for Wide Field of View Segmentation
Jie Hu, Junwei Zheng, Jiale Wei +2
Recent advancements in the Mamba architecture, with its linear computational complexity, being a promising alternative to transformer architectures suffering from quadratic complex…
Solving Zero-Shot 3D Visual Grounding as Constraint Satisfaction Problems
Qihao Yuan, Kailai Li, Jiaming Zhang
3D visual grounding (3DVG) aims to locate objects in a 3D scene with natural language descriptions. Supervised methods have achieved decent accuracy, but have a closed vocabulary a…
OneBEV: Using One Panoramic Image for Bird's-Eye-View Semantic Mapping
Jiale Wei, Junwei Zheng, Ruiping Liu +3
In the field of autonomous driving, Bird's-Eye-View (BEV) perception has attracted increasing attention in the community since it provides more comprehensive information compared w…
@Bench: Benchmarking Vision-Language Models for Human-centered Assistive Technology
Xin Jiang, Junwei Zheng, Ruiping Liu +4
As Vision-Language Models (VLMs) advance, human-centered Assistive Technologies (ATs) for helping People with Visual Impairments (PVIs) are evolving into generalists, capable of pe…
Comb, Prune, Distill: Towards Unified Pruning for Vision Model Compression
Jonas Schmitt, Ruiping Liu, Junwei Zheng +2
Lightweight and effective models are essential for devices with limited resources, such as intelligent vehicles. Structured pruning offers a promising approach to model compression…
Open Panoramic Segmentation
Junwei Zheng, Ruiping Liu, Yufan Chen +5
Panoramic images, capturing a 360° field of view (FoV), encompass omnidirectional spatial information crucial for scene understanding. However, it is not only costly to obtain trai…
Referring Atomic Video Action Recognition
Kunyu Peng, Jia Fu, Kailun Yang +8
We introduce a new task called Referring Atomic Video Action Recognition (RAVAR), aimed at identifying atomic actions of a particular person based on a textual description and the…
Occlusion-Aware Seamless Segmentation
Yihong Cao, Jiaming Zhang, Hao Shi +5
Panoramic images can broaden the Field of View (FoV), occlusion-aware prediction can deepen the understanding of the scene, and domain adaptation can transfer across viewing domain…
ACCSAMS: Automatic Conversion of Exam Documents to Accessible Learning Material for Blind and Visually Impaired
David Wilkening, Omar Moured, Thorsten Schwarz +2
Exam documents are essential educational materials for exam preparation. However, they pose a significant academic barrier for blind and visually impaired students, as they are oft…
ChartFormer: A Large Vision Language Model for Converting Chart Images into Tactile Accessible SVGs
Omar Moured, Sara Alzalabny, Anas Osman +3
Visualizations, such as charts, are crucial for interpreting complex data. However, they are often provided as raster images, which are not compatible with assistive technologies f…
Alt4Blind: A User Interface to Simplify Charts Alt-Text Creation
Omar Moured, Shahid Ali Farooqui, Karin Muller +4
Alternative Texts (Alt-Text) for chart images are essential for making graphics accessible to people with blindness and visual impairments. Traditionally, Alt-Text is manually writ…
AltChart: Enhancing VLM-based Chart Summarization Through Multi-Pretext Tasks
Omar Moured, Jiaming Zhang, M. Saquib Sarfraz +1
Chart summarization is a crucial task for blind and visually impaired individuals as it is their primary means of accessing and interpreting graphical data. Crafting high-quality d…
Rethinking Annotator Simulation: Realistic Evaluation of Whole-Body PET Lesion Interactive Segmentation Methods
Zdravko Marinov, Moon Kim, Jens Kleesiek +1
Interactive segmentation plays a crucial role in accelerating the annotation, particularly in domains requiring specialized expertise such as nuclear medicine. For example, annotat…
Chart4Blind: An Intelligent Interface for Chart Accessibility Conversion
Omar Moured, Morris Baumgarten-Egemole, Alina Roitberg +3
In a world driven by data visualization, ensuring the inclusive accessibility of charts for Blind and Visually Impaired (BVI) individuals remains a significant challenge. Charts ar…
RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
Yufan Chen, Jiaming Zhang, Kunyu Peng +4
Before developing a Document Layout Analysis (DLA) model in real-world applications, conducting comprehensive robustness testing is essential. However, the robustness of DLA models…
Skeleton-Based Human Action Recognition with Noisy Labels
Yi Xu, Kunyu Peng, Di Wen +7
Understanding human actions from body poses is critical for assistive robots sharing space with humans in order to make informed and safe decisions about the next interaction. Howe…