2 papers
cs.CV2025
Class Prototypes based Contrastive Learning for Classifying Multi-Label and Fine-Grained Educational Videos
Rohit Gupta, Anirban Roy, Claire Christensen +6
The recent growth in the consumption of online media by children during early childhood necessitates data-driven tools enabling educators to filter out appropriate educational cont…
cs.LG2022
Learning Invariant World State Representations with Predictive Coding
Avi Ziskind, Sujeong Kim, Giedrius T. Burachas
Self-supervised learning methods overcome the key bottleneck for building more capable AI: limited availability of labeled data. However, one of the drawbacks of self-supervised ar…