Home /
Research
Showing 649 - 654 / 904
Deep Multimodal Fusion by Channel Exchanging
YikaiWang, WenbingHuang, FuchunSun....
Published date-11/10/2020
Image-to-ImageTranslation, SemanticSegmentation
Deep multimodal fusion by using multiple sources of data for classification or regression has exhibited a clear advantage over the unimodal counterpart on various applications. Yet, current methods including aggregation-based …
MotePy: A domain specific language for low-overhead machine learning and data processing
JayarajPoroor....
Published date-11/10/2020
A domain specific language (DSL), named MotePy is presented. The DSL offers a high level syntax with low overheads for ML/data processing in time constrained or memory constrained systems. The …
A step towards neural genome assembly
LovroVrček, PetarVeličković, MileŠikić....
Published date-11/10/2020
GraphRepresentationLearning, RepresentationLearning
De novo genome assembly focuses on finding connections between a vast amount of short sequences in order to reconstruct the original genome. The central problem of genome assembly could be …
When Do You Need Billions of Words of Pretraining Data?
YianZhang, AlexWarstadt, Haau-SingLi....
Published date-11/10/2020
NLP is currently dominated by general-purpose pretrained language models like RoBERTa, which achieve strong performance on NLU tasks through pretraining on billions of words. But what exact knowledge or skills …
SeasonDepth: Cross-Season Monocular Depth Prediction Dataset and Benchmark under Multiple Environments
HanjiangHu, BaoquanYang, WeiangShi....
Published date-11/09/2020
DepthEstimation, StructurefromMotion, VisualLocalization
Monocular depth prediction has been well studied recently, while there are few works focused on the depth prediction across multiple environments, e.g. changing illumination and seasons, owing to the lack …
Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAE
DingZhou, Xue-XinWei....
Published date-11/09/2020
LatentVariableModels
The ability to record activities from hundreds of neurons simultaneously in the brain has placed an increasing demand for developing appropriate statistical techniques to analyze such data. Recently, deep generative …