Exploring Explainability in Video Action Recognition

arXiv:2404.09067v1 Announce Type: new
Abstract: Image Classification and Video Action Recognition are perhaps the two most foundational tasks in computer vision. Consequently, explaining the inner workings of trained deep neural networks is of prime importance. While numerous efforts focus on explaining the decisions of trained deep neural networks in image classification, exploration in the domain of its temporal version, video action recognition, has been scant. In this work, we take a deeper look at this problem. We begin by revisiting …

abstract action recognition arxiv classification computer computer vision cs.ai cs.cv decisions explainability exploration focus foundational image importance networks neural networks prime recognition tasks type video vision