Normalization methods play an important role in enhancing the performance of deep learning while their theoretical understandings have been limited.

Neural Information Processing Systems http://nips.cc/

Open-vocabulary object detection via vision and language knowledge distillation.

Human actions in egocentric videos often feature hand-object interactions composed of a verb (performed by the hand) applied to an object.

An essential aspect of any machine learning system is understanding what the model does not know.

Our proposed method directly learns the missing values ina bidirectional recurrent dynamical system, without anyspecific assumption. The imputed values are treated as variables of RNN graph and can be effectively updated during backpropagation. BRITS hasthree advantages: (a)itcanhandle multiple correlated missing values intime series; (b) itgeneralizes totime series with nonlinear dynamics underlying; (c) it provides a data-driven imputation procedure and applies to general settings with missing data. We evaluate our model on three real-world datasets, including an air quality dataset, a healthcare dataset, and a localization dataset for human activity. Experiments show that our model outperforms the state-of-the-art methods in both imputation and classification/regression.

Neural Information Processing Systems http://nips.cc/