X
Xinxiang Zhang
Researcher at Southern Methodist University
Publications - 11
Citations - 232
Xinxiang Zhang is an academic researcher from Southern Methodist University. The author has contributed to research in topics: Recurrent neural network & Deblurring. The author has an hindex of 5, co-authored 9 publications receiving 113 citations.
Papers
More filters
Journal ArticleDOI
Concrete crack detection using context‐aware deep semantic segmentation network
TL;DR: A novel context‐aware deep convolutional semantic segmentation network is presented to effectively detect cracks in structural infrastructure under various conditions to segment the cracks on images with arbitrary sizes without retraining the prediction network.
Journal ArticleDOI
Attention augmentation with multi-residual in bidirectional LSTM
TL;DR: An Attention-augmentation Bidirectional Multi-residual Recurrent Neural Network (ABMRNN) is proposed to overcome the deficiency of LSTM and outperforms the traditional statistical classifiers and other existing RNN architectures.
Proceedings ArticleDOI
Accurate Vehicle Detection Using Multi-camera Data Fusion and Machine Learning
TL;DR: A multi-camera vehicle detection system that significantly improves the detection performance under occlusion conditions and results in an approximately 31.2% increase in AP and 8.6% in MODP than the single-camera methods.
Proceedings ArticleDOI
Effective real-scenario Video Copy Detection
Yue Zhang,Xinxiang Zhang +1 more
TL;DR: This paper introduces an effective real-scenario video copy detection system which aims to effectively and efficiently detect complex real video copies and measures the trade-off between effectiveness and efficiency.
Proceedings ArticleDOI
An Attention-aware Bidirectional Multi-residual Recurrent Neural Network (Abmrnn): A Study about Better Short-term Text Classification
TL;DR: An Attention-aware Bidirectional Multi-residual Recurrent Neural Network (ABMRNN) is proposed to overcome the deficiency of LSTM and achieves state-of-the-art performance in classification tasks.