Neuron pruning for compressing deep networks using maxout architectures
This paper presents an efficient and robust approach for reducing the size of deep neural
networks by pruning entire neurons. It exploits maxout units for combining neurons into more …
networks by pruning entire neurons. It exploits maxout units for combining neurons into more …
Towards a framework for semi-automated annotation of human order picking activities using motion capturing
Data creation for Human Activity Recognition (HAR) requires an immense human effort and
contextual knowledge for manual annotation. This paper proposes a framework for semi …
contextual knowledge for manual annotation. This paper proposes a framework for semi …
Zero-shot object prediction using semantic scene knowledge
R Grzeszick, GA Fink - arXiv preprint arXiv:1604.07952, 2016 - arxiv.org
This work focuses on the semantic relations between scenes and objects for visual object
recognition. Semantic knowledge can be a powerful source of information especially in …
recognition. Semantic knowledge can be a powerful source of information especially in …
[PDF][PDF] Strategic Technical Insights
A Auger, E Wiseman - 2017 - cradpdf.drdc-rddc.gc.ca
In order to assist with long-term R&D planning and the prioritization of research topics, this
scientometric study was commissioned to provide a high level overview of worldwide …
scientometric study was commissioned to provide a high level overview of worldwide …