2 papers
cs.CV2021
Human-like Relational Models for Activity Recognition in Video
Joseph Chrol-Cannon, Andrew Gilbert, Ranko Lazic +2
Video activity recognition by deep neural networks is impressive for many classes. However, it falls short of human performance, especially for challenging to discriminate activiti…
cs.NE2017
An Efficient Method for online Detection of Polychronous Patterns in Spiking Neural Network
Joseph Chrol-Cannon, Yaochu Jin, André Grüning
Polychronous neural groups are effective structures for the recognition of precise spike-timing patterns but the detection method is an inefficient multi-stage brute force process…