Classifier learning with hidden information

58 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Learning and Refining of Privileged Information-Based RNNs for Action Recognition from Depth Sequences (2017, background): “This knowledge, also referred to as PI [41], hidden information [50] or side information [54], which can help to provide more explanations in training but will not be available at testing.”
Information Bottleneck Learning Using Privileged Information for Visual Recognition (2016, methodology): “This approach relates more to multiview learning, but only the main view pipeline is used for testing, without considering the intrinsic asymmetry of the LUPI framework, as pointed out in [42].”
Information Bottleneck Domain Adaptation with Privileged Information for Visual Recognition (2016, methodology): “Other implementations of the LUPI paradigm include [6] for boosting, [17] for object localization in a structured prediction framework, and [47].”
Graph Distillation for Action Detection with Privileged Modalities (2017, background): “Several work employed privileged information (PI) on SVM classifiers [53,56].”