Home /
Research
Showing 523 - 528 / 897
Prototypical Contrast and Reverse Prediction: Unsupervised Skeleton Based Action Recognition
ShihaoXu, HaocongRao, XipingHu....
Published date-11/14/2020
ActionRecognition, Clustering, RepresentationLearning, SemanticSimilarity, SemanticTextualSimilarity, SkeletonBasedActionRecognition, UnsupervisedRepresentationLearning
In this paper, we focus on unsupervised representation learning for skeleton-based action recognition. Existing approaches usually learn action representations by sequential prediction but they suffer from the inability to fully …
Reinforced Molecular Optimization with Neighborhood-Controlled Grammars
ChenchengXu, QiaoLiu, MinlieHuang....
Published date-11/14/2020
GraphGeneration, MolecularGraphGeneration
A major challenge in the pharmaceutical industry is to design novel molecules with specific desired properties, especially when the property evaluation is costly. Here, we propose MNCE-RL, a graph convolutional …
Classification based on invisible features and thereby finding the effect of tuberculosis vaccine on COVID-19
NihalAcharyaAdde, ThiloMoshagen....
Published date-11/14/2020
In the case of clustered data, an artificial neural network with logcosh loss function learns the bigger cluster rather than the mean of the two. Even more so, the ANN …
Factorized Gaussian Process Variational Autoencoders
MetodJazbec, MichaelPearce, VincentFortuin....
Published date-11/14/2020
Variational autoencoders often assume isotropic Gaussian priors and mean-field posteriors, hence do not exploit structure in scenarios where we may expect similarity or consistency across latent variables. Gaussian process variational …
Utilizing Bidirectional Encoder Representations from Transformers for Answer Selection
MdTahmidRahmanLaskar, EnamulHoque, JimmyXiangjiHuang....
Published date-11/14/2020
AnswerSelection, CommunityQuestionAnswering, LanguageModelling, QuestionAnswering
Pre-training a transformer-based model for the language modeling task in a large dataset and then fine-tuning it for downstream tasks has been found very useful in recent years. One major …
GENNI: Visualising the Geometry of Equivalences for Neural Network Identifiability
DanielLengyel, JanithPetangoda, IsakFalk....
Published date-11/14/2020
We propose an efficient algorithm to visualise symmetries in neural networks. Typically, models are defined with respect to a parameter space, where non-equal parameters can produce the same input-output map. …