In this paper we investigate a time delay neural network (TDNN) for a keyword spotting task
that requires low CPU, memory and latency. The TDNN is trained with transfer learning and …

While many multiple graph inference methodologies operate under the implicit assumption
that an explicit vertex correspondence is known across the vertex sets of the graphs, in …

Given a vertex of interest in a network G 1, the vertex nomination problem seeks to find the
corresponding vertex of interest (if it exists) in a second network G 2. A vertex nomination …

Universum, a set of examples that do not belong to any class of interest for a classification
problem, has been playing an important role in improving the performance of many machine …

Matching datasets of multiple modalities has become an important task in data analysis.
Existing methods often rely on the embedding and transformation of each single modality …

This paper presents our work on building a small-footprint keyword spotting system for a
resource-limited language, which requires low CPU, memory and latency. Our keyword …

Given a network and a subset of interesting vertices whose identities are only partially
known, the vertex nomination problem seeks to rank the remaining vertices in such a way …

首先, 对空间分布不均匀且无序的三维点云构造其二维主流形, 并以与球面同胚的封闭曲面网格
形式给出其二维主流形的二次优化逼近, 以主流形网格有序均匀的结点分布表示三维点云空间 …

The joint optimization of fidelity and commensurability (JOFC) manifold matching
methodology embeds an omnibus dissimilarity matrix consisting of multiple dissimilarities on …

Graphs are widely used in modeling data in the modern statistics. Although a great deal of
research has been done on the single graph, inference for multiple networks is still a …