C
Cunzhao Shi
Researcher at Chinese Academy of Sciences
Publications - 60
Citations - 1297
Cunzhao Shi is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Convolutional neural network & Image retrieval. The author has an hindex of 16, co-authored 60 publications receiving 1047 citations.
Papers
More filters
Journal ArticleDOI
Scene text detection using graph model built upon maximally stable extremal regions
TL;DR: A novel scene text detection approach using graph model built upon Maximally Stable Extremal Regions (MSERs) to incorporate various information sources into one framework that outperforms state-of-the-art methods both in recall and precision.
Proceedings ArticleDOI
Scene Text Recognition Using Part-Based Tree-Structured Character Detection
TL;DR: A novel scene text recognition method using part-based tree-structured character detection that outperforms state-of-the-art methods significantly both for character detection and word recognition.
Proceedings ArticleDOI
Cross-View Action Recognition via a Continuous Virtual Path
TL;DR: A virtual view kernel is proposed to compute the value of similarity between two infinite-dimensional features, which can be readily used to construct any kernelized classifiers to improve the performance of classifiers.
Journal ArticleDOI
Degraded document image binarization using structural symmetry of strokes
TL;DR: The structural symmetric pixels (SSPs) are utilized to calculate the local threshold in neighborhood and the voting result of multiple thresholds will determine whether one pixel belongs to the foreground or not and an adaptive global threshold selection algorithm is proposed.
Journal ArticleDOI
Deep Convolutional Activations-Based Features for Ground-Based Cloud Classification
TL;DR: It is believed the local rich texture information might be more important than the global layout information and, thus, a comprehensive evaluation of using both shallow convolutional layers-based features and DCAFs for ground-based cloud classification is given.