Fatemeh Ziaeetabar
PulseAugur coverage of Fatemeh Ziaeetabar — every cluster mentioning Fatemeh Ziaeetabar across labs, papers, and developer communities, ranked by signal.
-
Survey explores vision-language models for egocentric video understanding
A new survey paper published on arXiv examines the application of vision-language models (VLMs) to egocentric video understanding. The paper, authored by Fatemeh Ziaeetabar, reviews existing research on VLMs for tasks s…
-
New LACA method improves dual-hand action segmentation with temporal alignment
Researchers have developed a novel method called Lag-Aware Cross-Hand Alignment (LACA) to improve dual-hand action segmentation. LACA explicitly estimates temporal offsets between left and right-hand feature streams, al…
-
New hypergraph framework enhances human activity recognition
Researchers have developed a novel dynamic manipulation hypergraph framework to improve human activity recognition in videos. This approach moves beyond traditional pairwise relationships by modeling multi-entity config…
-
New framework assesses visual predicate reliability in robotic manipulation
Researchers have developed a new framework to assess the reliability of visual predicates used in understanding robotic manipulation. This framework evaluates how well predicates like contact, support, and grasp perform…