With the increase in massive digitized datasets of cultural artefacts, social and cultural scientists have an unprecedented opportunity for the discovery and expansion of cultural theory. The WikiArt dataset is one such example, with over 250,000 high qual ...
Training convolutional neural networks (CNNs) for very high-resolution images requires a large quantity of high-quality pixel-level annotations, which is extremely labor-intensive and time-consuming to produce. Moreover, professional photograph interpreter ...
Optimizing resource utilization in target platforms is key to achieving high performance during DNN inference. While optimizations have been proposed for inference latency, memory footprint, and energy consumption, prior hardware-aware neural architecture ...
The objective of meta-learning is to exploit knowledge obtained from observed tasks to improve adaptation to unseen tasks. Meta-learners are able to generalize better when they are trained with a larger number of observed tasks and with a larger amount of ...
Phonological-based features (articulatory features, AFs) describe the movements of the vocal organ which are shared across languages. This paper investigates a domain-adversarial neural network (DANN) to extract reliable AFs, and different multi-stream tec ...
The massive amounts of digitized historical documents acquired over the last decades naturally lend themselves to automatic processing and exploration. Research work seeking to automatically process facsimiles and extract information thereby are multiplyin ...
