From the 1 of 4 linked papers with an AI index.
4 papers
FORGE: Frame Orthogonality in Relevance Geometry for Long-Form Video Understanding
Ghazal Kaviani, Ghassan AlRegib
The paper introduces FORGE, a training-free method that selects a diverse set of query-relevant video frames at inference by shaping a query‑conditioned geometry in a pretrained mu…
Hierarchical and Multimodal Data for Daily Activity Understanding
Ghazal Kaviani, Yavuz Yarici, Seulgi Kim +4
Daily Activity Recordings for Artificial Intelligence (DARai, pronounced "Dahr-ree") is a multimodal, hierarchically annotated dataset constructed to understand human activities in…
Evaluating BM3D and NBNet: A Comprehensive Study of Image Denoising Across Multiple Datasets
Ghazal Kaviani, Reza Marzban, Ghassan AlRegib
This paper investigates image denoising, comparing traditional non-learning-based techniques, represented by Block-Matching 3D (BM3D), with modern learning-based methods, exemplifi…
Multi-level and Multi-modal Action Anticipation
Seulgi Kim, Ghazal Kaviani, Mohit Prabhushankar +1
Action anticipation, the task of predicting future actions from partially observed videos, is crucial for advancing intelligent systems. Unlike action recognition, which operates o…