This paper studies the problem of learning the conditional distribution of a high-dimensional output given an input, where the output and input may belong to two different domains, e.g., the output…
This paper examines the information content of insider silence, periods of no insider trading. We hypothesize that, to avoid litigation risk, rational insiders do not sell own-company shares when t…
Feature Extraction, Image Motion Analysis, Image Representation, Learning Artificial Intelligence, Matrix Algebra, Supervised Dimensionality Reduction, Sequence Data, Low Dimensional Subspace, Conv…
Heterogeneous integration of electro-optic (EO) crystal thin film on insulator has become an attractive platform to achieve high-performance and compact modulators. While there has been some impres…
3D data that contains rich geometry information of objects and scenes is valuable for understanding 3D physical world. With the recent emergence of large-scale 3D datasets, it becomes increasingly …
In this paper, we present a method to mine object-part patterns from conv-layers of a pre-trained convolutional neural network (CNN). The mined object-part patterns are organized by an And-Or graph…
This paper proposes a generic method to learn interpretable convolutional filters in a deep convolutional neural network (CNN) for object classification, where each interpretable filter encodes fea…
This paper introduces an explanatory graph representation to reveal object parts encoded inside convolutional layers of a CNN. Given a pre-trained CNN, each filter 1 in a conv-layer usually represe…
The Vernier effect can amplify the sensitivity of the sensor, but its effective spectral range is usually limited to one free spectral range (FSR). Once the envelope shifts beyond one FSR, it will …