arXiv subjects

Xuan Shi

Publications and source records attributed to Xuan Shi.

22 records · Page 2Linked to original sources

arXiv2020

Taming Near Repeat Calculation for Crime Analysis via Cohesive Subgraph Computing

Near repeat (NR) is a well known phenomenon in crime analysis assuming that crime events exhibit correlations within a given time and space frame. Traditional NR calculation generates 2 event pairs if 2 events happened within a given space and time limit. When the number of events is large, however, NR calculation is time consuming and how these pairs are organized are not yet explored. In this paper, we designed a new approach to calculate clusters of NR events efficiently. To begin with, R-tree is utilized to index crime events, a single event is represented by a vertex whereas edges are constructed by range querying the vertex in R-tree, and a graph is formed. Cohesive subgraph approaches are applied to identify the event chains. k-clique, k-truss, k-core plus DBSCAN algorithms are implemented in sequence with respect to their varied range of ability to find cohesive subgraphs. Real world crime data in Chicago, New York and Washington DC are utilized to conduct experiments. The experiment confirmed that near repeat is a solid effect in real big crime data by conducting Mapreduce empowered knox tests. The performance of 4 different algorithms are validated, while the quality of the algorithms are gauged by the distribution of number of cohesive subgraphs and their clustering coefficients. The proposed framework is the first to process the real crime data of million record scale, and is the first to detect NR events with size of more than 2.

cs.DS↗

arXiv2019

RepGN:Object Detection with Relational Proposal Graph Network

Region based object detectors achieve the state-of-the-art performance, but few consider to model the relation of proposals. In this paper, we explore the idea of modeling the relationships among the proposals for object detection from the graph learning perspective. Specifically, we present relational proposal graph network (RepGN) which is defined on object proposals and the semantic and spatial relation modeled as the edge. By integrating our RepGN module into object detectors, the relation and context constraints will be introduced to the feature extraction of regions and bounding boxes regression and classification. Besides, we propose a novel graph-cut based pooling layer for hierarchical coarsening of the graph, which empowers the RepGN module to exploit the inter-regional correlation and scene description in a hierarchical manner. We perform extensive experiments on COCO object detection dataset and show promising results.

cs.CV↗

arXiv2019

End-to-End Model for Speech Enhancement by Consistent Spectrogram Masking

Recently, phase processing is attracting increasinginterest in speech enhancement community. Some researchersintegrate phase estimations module into speech enhancementmodels by using complex-valued short-time Fourier transform(STFT) spectrogram based training targets, e.g. Complex RatioMask (cRM) [1]. However, masking on spectrogram would violentits consistency constraints. In this work, we prove that theinconsistent problem enlarges the solution space of the speechenhancement model and causes unintended artifacts. ConsistencySpectrogram Masking (CSM) is proposed to estimate the complexspectrogram of a signal with the consistency constraint in asimple but not trivial way. The experiments comparing ourCSM based end-to-end model with other methods are conductedto confirm that the CSM accelerate the model training andhave significant improvements in speech quality. From ourexperimental results, we assured that our method could enha

cs.SD↗

arXiv2018

End-to-End Residual CNN with L-GM Loss Speaker Verification System

We propose an end-to-end speaker verification system based on the neural network and trained by a loss function with less computational complexity. The end-to-end speaker verification system in this paper consists of a ResNet architecture to extract features from utterance, then produces utterance-level speaker embeddings, and train using the large-margin Gaussian Mixture loss function. Influenced by the large-margin and likelihood regularization, large-margin Gaussian Mixture loss function benefits the speaker verification performance. Experimental results demonstrate that the Residual CNN with large-margin Gaussian Mixture loss outperforms DNN-based i-vector baseline by more than 10% improvement in accuracy rate.

cs.SD↗