2 papers
cs.CV2026
CEZSAR: A Contrastive Embedding Method for Zero-Shot Action Recognition
Valter Estevam, Rayson Laroca, Helio Pedrini +1
This paper proposes a novel Zero-Shot Action Recognition~(ZSAR) method based on contrastive learning. In ZSAR, we aim to classify examples from classes that were missing during tra…
cs.CV2025
Self-Organizing Visual Prototypes for Non-Parametric Representation Learning
Thalles Silva, Helio Pedrini, AdÃn RamÃrez Rivera
We present Self-Organizing Visual Prototypes (SOP), a new training technique for unsupervised visual feature learning. Unlike existing prototypical self-supervised learning (SSL) m…