Delta Sampling R-BERT for limited data and low-light action recognition

Abstract

We present an approach to perform supervised action recognition in the dark. In this work, we present our results on the ARID dataset. Most previous works only evaluate performance on large, well illuminated datasets like Kinetics and HMDB51. We demonstrate that our work is able to achieve a very low error rate while being trained on a much smaller dataset of dark videos. We also explore a variety of training and inference strategies including domain transfer methodologies and also propose a simple but useful frame selection strategy. Our empirical results demonstrate that we beat previously published baseline models by 11%.

References in corpus (5)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
• The Kinetics Human Action Video Dataset
• Deep Bilateral Learning for Real-Time Image Enhancement
• Gradient Centralization: A New Optimization Technique for Deep Neural Networks