4 papers · 1 filter
SSeg: Active Sparse Point-Label Augmentation for Semantic Segmentation
Cesar Borja, Carlos Plou, Ruben Martinez-Cantin +1
Semantic segmentation is essential for automating remote sensing analysis in fields like ecology. However, fine-grained analysis of complex aerial or underwater imagery remains an…
FALCONEye: Finding Answers and Localizing Content in ONE-hour-long videos with multi-modal LLMs
Carlos Plou, Cesar Borja, Ruben Martinez-Cantin +1
Finding information in hour-long videos is a challenging task even for top-performing Vision Language Models (VLMs), as encoding visual content quickly exceeds available context wi…
CARLOR @ Ego4D Step Grounding Challenge: Bayesian temporal-order priors for test time refinement
Carlos Plou, Lorenzo Mur-Labadia, Ruben Martinez-Cantin +1
The goal of the Step Grounding task is to locate temporal boundaries of activities based on natural language descriptions. This technical report introduces a Bayesian-VSLNet to add…
EventSleep: Sleep Activity Recognition with Event Cameras
Carlos Plou, Nerea Gallego, Alberto Sabater +5
Event cameras are a promising technology for activity recognition in dark environments due to their unique properties. However, real event camera datasets under low-lighting condit…