4 papers
Rethinking Online Action Detection in Untrimmed Videos: A Novel Online Evaluation Protocol
Marcos Baptista Rios, Roberto J. López-Sastre, Fabian Caba Heilbron +3
The Online Action Detection (OAD) problem needs to be revisited. Unlike traditional offline action detection approaches, where the evaluation metrics are clear and well established…
The Instantaneous Accuracy: a Novel Metric for the Problem of Online Human Behaviour Recognition in Untrimmed Videos
Marcos Baptista Rios, Roberto J. López-Sastre, Fabian Caba Heilbron +3
The problem of Online Human Behaviour Recognition in untrimmed videos, aka Online Action Detection (OAD), needs to be revisited. Unlike traditional offline action detection approac…
Embarrassingly Simple Model for Early Action Proposal
Marcos Baptista-Ríos, Roberto J. López-Sastre, Franciso Javier Acevedo-Rodríguez +1
Early action proposal consists in generating high quality candidate temporal segments that are likely to contain an action in a video stream, as soon as they happen. Many sophistic…
Learning to Exploit the Prior Network Knowledge for Weakly-Supervised Semantic Segmentation
Carolina Redondo-Cabrera, Marcos Baptista-Ríos, Roberto J. López-Sastre
Training a Convolutional Neural Network (CNN) for semantic segmentation typically requires to collect a large amount of accurate pixel-level annotations, a hard and expensive task.…