3 citations · 12 across the 18 of their papers we have counts for
19 papers
FlowNar: Scalable Streaming Narration for Long-Form Videos
Zeyun Zhong, Manuel Martin, Chengzhi Wu +4
Recent Large Multimodal Models (LMMs), primarily designed for offline settings, are ill-suited for the dynamic requirements of streaming video. While recent online adaptations impr…
IMPACT-Scribe: Interactive Temporal Action Segmentation with Boundary Scribbles and Query Planning
Qian Yin, Di Wen, Kunyu Peng +11
Dense temporal annotation of procedural activity videos is vital for action understanding and embodied intelligence but remains labor-intensive due to reactive tools. Each correcti…
IMPACT-HOI: Supervisory Control for Onset-Anchored Partial HOI Event Construction
Haoshen Zhang, Di Wen, Kunyu Peng +12
We present IMPACT-HOI, a mixed-initiative framework for annotating egocentric procedural video by constructing structured event graphs for Human-Object Interactions (HOI), motivate…
IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory
Weitong Kong, Di Wen, Kunyu Peng +10
Correcting errors in long-video understanding is disproportionately costly: existing multimodal pipelines produce opaque, end-to-end outputs that expose no intermediate state for i…
IMPACT: A Dataset for Multi-Granularity Human Procedural Action Understanding in Industrial Assembly
Di Wen, Zeyun Zhong, David Schneider +18
We introduce IMPACT, a synchronized five-view RGB-D dataset for deployment-oriented industrial procedural understanding, built around real assembly and disassembly of a commercial…
OmniFall: From Staged Through Synthetic to Wild, A Unified Multi-Domain Dataset for Robust Fall Detection
David Schneider, Zdravko Marinov, Moritz Mistol +6
Visual fall detection models are usually trained on small, staged datasets. Their real-world utility remains unclear; such data lacks diversity and evaluation protocols differ from…
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…
Muscles in Time: Learning to Understand Human Motion by Simulating Muscle Activations
David Schneider, Simon Reiß, Marco Kugler +6
Exploring the intricate dynamics between muscular and skeletal structures is pivotal for understanding human motion. This domain presents substantial challenges, primarily attribut…
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…
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…
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…
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…
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…
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…
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…
Affect-DML: Context-Aware One-Shot Recognition of Human Affect using Deep Metric Learning
Kunyu Peng, Alina Roitberg, David Schneider +3
Human affect recognition is a well-established research area with numerous applications, e.g., in psychological care, but existing methods assume that all emotions-of-interest are…
Let's Play for Action: Recognizing Activities of Daily Living by Learning from Life Simulation Video Games
Alina Roitberg, David Schneider, Aulia Djamal +3
Recognizing Activities of Daily Living (ADL) is a vital process for intelligent assistive robots, but collecting large annotated datasets requires time-consuming temporal labeling…