3 papers
eess.SP2025
Cross-Channel Unlabeled Sensing over a Union of Signal Subspaces
Taulant Koka, Manolis C. Tsakiris, Benjamín Béjar Haro +1
Cross-channel unlabeled sensing addresses the problem of recovering a multi-channel signal from measurements that were shuffled across channels. This work expands the cross-channel…
cs.LG2025
Diffusion Active Learning: Towards Data-Driven Experimental Design in Computed Tomography
Luis Barba, Johannes Kirschner, Tomas Aidukas +2
We introduce Diffusion Active Learning, a novel approach that combines generative diffusion modeling with data-driven sequential experimental design to adaptively acquire data for…
cs.CV2023
Semantic-aware Video Representation for Few-shot Action Recognition
Yutao Tang, Benjamin Bejar, Rene Vidal
Recent work on action recognition leverages 3D features and textual information to achieve state-of-the-art performance. However, most of the current few-shot action recognition me…