27 citations · 86 across the 37 of their papers we have counts for
37 papers
RoHOI: Robustness Benchmark for Human-Object Interaction Detection
Di Wen, Kunyu Peng, Kailun Yang +7
Human-Object Interaction (HOI) detection is crucial for robot-human assistance, enabling context-aware support. However, models trained on clean datasets degrade in real-world cond…
Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization
Kunyu Peng, Di Wen, M. Saquib Sarfraz +7
Open-Set Domain Generalization (OSDG) is a challenging task requiring models to accurately predict familiar categories while minimizing confidence for unknown categories to effecti…
Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler
Kunyu Peng, Di Wen, Kailun Yang +6
In Open-Set Domain Generalization (OSDG), the model is exposed to both new variations of data appearance (domains) and open-set conditions, where both known and novel categories ar…
Towards Synthetic Data Generation for Improved Pain Recognition in Videos under Patient Constraints
Jonas Nasimzada, Jens Kleesiek, Ken Herrmann +2
Recognizing pain in video is crucial for improving patient-computer interaction systems, yet traditional data collection in this domain raises significant ethical and logistical ch…
Probing Fine-Grained Action Understanding and Cross-View Generalization of Foundation Models
Thinesh Thiyakesan Ponbagavathi, Kunyu Peng, Alina Roitberg
Foundation models (FMs) are large neural networks trained on broad datasets, excelling in downstream tasks with minimal fine-tuning. Human activity recognition in video has advance…
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…
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…
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…
Navigating Open Set Scenarios for Skeleton-based Action Recognition
Kunyu Peng, Cheng Yin, Junwei Zheng +7
In real-world scenarios, human actions often fall outside the distribution of training data, making it crucial for models to recognize known actions and reject unknown ones. Howeve…
Quantized Distillation: Optimizing Driver Activity Recognition Models for Resource-Constrained Environments
Calvin Tanama, Kunyu Peng, Zdravko Marinov +2
Deep learning-based models are at the forefront of most driver observation benchmarks due to their remarkable accuracies but are also associated with high computational costs. This…
Exploring Self-supervised Skeleton-based Action Recognition in Occluded Environments
Yifei Chen, Kunyu Peng, Alina Roitberg +7
To integrate action recognition into autonomous robotic systems, it is essential to address challenges such as person occlusions-a common yet often overlooked scenario in existing…
Elevating Skeleton-Based Action Recognition with Efficient Multi-Modality Self-Supervision
Yiping Wei, Kunyu Peng, Alina Roitberg +6
Self-supervised representation learning for human action recognition has developed rapidly in recent years. Most of the existing works are based on skeleton data while using a mult…
Towards Privacy-Supporting Fall Detection via Deep Unsupervised RGB2Depth Adaptation
Hejun Xiao, Kunyu Peng, Xiangsheng Huang +4
Fall detection is a vital task in health monitoring, as it allows the system to trigger an alert and therefore enabling faster interventions when a person experiences a fall. Altho…
On Transferability of Driver Observation Models from Simulated to Real Environments in Autonomous Cars
Walter Morales-Alvarez, Novel Certad, Alina Roitberg +2
For driver observation frameworks, clean datasets collected in controlled simulated environments often serve as the initial training ground. Yet, when deployed under real driving c…
Line Graphics Digitization: A Step Towards Full Automation
Omar Moured, Jiaming Zhang, Alina Roitberg +2
The digitization of documents allows for wider accessibility and reproducibility. While automatic digitization of document layout and text content has been a long-standing focus of…
Exploring Few-Shot Adaptation for Activity Recognition on Diverse Domains
Kunyu Peng, Di Wen, David Schneider +5
Domain adaptation is essential for activity recognition to ensure accurate and robust performance across diverse environments, sensor types, and data sources. Unsupervised domain a…
AdaptiveClick: Clicks-aware Transformer with Adaptive Focal Loss for Interactive Image Segmentation
Jiacheng Lin, Jiajun Chen, Kailun Yang +4
Interactive Image Segmentation (IIS) has emerged as a promising technique for decreasing annotation time. Substantial progress has been made in pre- and post-processing for IIS, bu…
FishDreamer: Towards Fisheye Semantic Completion via Unified Image Outpainting and Segmentation
Hao Shi, Yu Li, Kailun Yang +7
This paper raises the new task of Fisheye Semantic Completion (FSC), where dense texture, structure, and semantics of a fisheye image are inferred even beyond the sensor field-of-v…
Towards Activated Muscle Group Estimation in the Wild
Kunyu Peng, David Schneider, Alina Roitberg +6
In this paper, we tackle the new task of video-based Activated Muscle Group Estimation (AMGE) aiming at identifying active muscle regions during physical activity in the wild. To t…
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…
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…