11 citations · 11 across the 13 of their papers we have counts for
14 papers
Vision-Language Models for Egocentric Video: From Hand-Object Interaction to Embodied AI
Mohammad Zamani, Fatemeh Ziaeetabar
Egocentric video captures activities from the wearer's perspective, providing a direct view of human attention, hand--object interaction, and goal-directed behavior. This perspecti…
Lag-aware cross-hand alignment for dual-hand action segmentation
Fatemeh Ziaeetabar
Dual-hand action segmentation commonly fuses left- and right-hand representations at identical temporal indices, although coordinated hand transitions may occur with nonzero and ti…
Beyond Pairwise Relations: Dynamic Manipulation Hypergraphs for Vision-Based Human Activity Recognition
Fatemeh Ziaeetabar
Fine-grained manipulation recognition requires modeling evolving relations among hands, objects, tools, and supporting surfaces. Conventional graph-based methods use pairwise edges…
Trustworthy Visual Predicates for Robust Manipulation Understanding under Degradation
Fatemeh Ziaeetabar
Manipulation understanding requires reliable relational evidence, such as contact, support, containment, motion coupling, grasp, release, and active-hand involvement. Although thes…
Neuro-Symbolic Manipulation Understanding with Enriched Semantic Event Chains
Fatemeh Ziaeetabar
Robotic systems operating in human environments must reason about how object interactions evolve over time, which actions are currently being performed, and what manipulation step…
Beyond Sequences: A Benchmark for Atomic Hand-Object Interaction Using a Static RNN Encoder
Yousef Azizi Movahed, Fatemeh Ziaeetabar
Reliably predicting human intent in hand-object interactions is an open challenge for computer vision. Our research concentrates on a fundamental sub-problem: the fine-grained clas…
DRL-Guided Neural Batch Sampling for Semi-Supervised Pixel-Level Anomaly Detection
Amirhossein Khadivi Noghredeh, Abdollah Safari, Fatemeh Ziaeetabar +1
Anomaly detection in industrial visual inspection is challenging due to the scarcity of defective samples. Most existing methods rely on unsupervised reconstruction using only norm…
Why Relational Graphs Will Save the Next Generation of Vision Foundation Models?
Fatemeh Ziaeetabar
Vision foundation models (FMs) have become the predominant architecture in computer vision, providing highly transferable representations learned from large-scale, multimodal corpo…
EfficientGFormer: Multimodal Brain Tumor Segmentation via Pruned Graph-Augmented Transformer
Fatemeh Ziaeetabar
Accurate and efficient brain tumor segmentation remains a critical challenge in neuroimaging due to the heterogeneous nature of tumor subregions and the high computational cost of…
Leveraging Foundation Models for Multimodal Graph-Based Action Recognition
Fatemeh Ziaeetabar, Florentin Wörgötter
Foundation models have ushered in a new era for multimodal video understanding by enabling the extraction of rich spatiotemporal and semantic representations. In this work, we intr…
Multi Sentence Description of Complex Manipulation Action Videos
Fatemeh Ziaeetabar, Reza Safabakhsh, Saeedeh Momtazi +2
Automatic video description requires the generation of natural language statements about the actions, events, and objects in the video. An important human trait, when we describe a…
A Hierarchical Graph-based Approach for Recognition and Description Generation of Bimanual Actions in Videos
Fatemeh Ziaeetabar, Reza Safabakhsh, Saeedeh Momtazi +2
Nuanced understanding and the generation of detailed descriptive content for (bimanual) manipulation actions in videos is important for disciplines such as robotics, human-computer…
Human and Machine Action Prediction Independent of Object Information
Fatemeh Ziaeetabar, Jennifer Pomp, Stefan Pfeiffer +4
Predicting other people's action is key to successful social interactions, enabling us to adjust our own behavior to the consequence of the others' future actions. Studies on actio…
Action Prediction in Humans and Robots
Florentin Wörgötter, Fatemeh Ziaeetabar, Stefan Pfeiffer +3
Efficient action prediction is of central importance for the fluent workflow between humans and equally so for human-robot interaction. To achieve prediction, actions can be encode…