N
Nianhua Xie
Researcher at Chinese Academy of Sciences
Publications - 16
Citations - 941
Nianhua Xie is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Contextual image classification & Histogram. The author has an hindex of 8, co-authored 16 publications receiving 857 citations. Previous affiliations of Nianhua Xie include Temple University.
Papers
More filters
Journal ArticleDOI
A Survey on Visual Content-Based Video Indexing and Retrieval
TL;DR: Methods for video structure analysis, including shot boundary detection, key frame extraction and scene segmentation, extraction of features including static key frame features, object features and motion features, video data mining, video annotation, and video retrieval including query interfaces are analyzed.
Journal ArticleDOI
A Robust Tracking System for Low Frame Rate Video
TL;DR: Experimental results demonstrate that the proposed tracking system can effectively tackle the difficulties caused by LFR, and an integral image based parameter calculation is constructed, which greatly reduces the computational load.
Proceedings ArticleDOI
Use bin-ratio information for category and scene classification
TL;DR: It is shown that bin-ratio information, which is collected from the ratios between bin values of histograms, provides several attractive advantages for category and scene classification tasks: first, BRD is robust to cluttering, partial occlusion and histogram normalization, and second,BRD captures rich co-occurrence information while enjoying a linear computational complexity.
Journal ArticleDOI
Unsupervised Active Learning Based on Hierarchical Graph-Theoretic Clustering
TL;DR: Evaluations on data sets for network intrusion detection, image classification, and video classification have demonstrated that the proposed unsupervised active learning framework can effectively reduce the workload of manual classification while maintaining a high accuracy of automatic classification.
Journal ArticleDOI
Image Classification Using Multiscale Information Fusion Based on Saliency Driven Nonlinear Diffusion Filtering
TL;DR: The algorithm emphasizes the foreground features, which are important for image classification, and preserves or even enhances semantically important structures in the foreground, and inhibits and smoothes clutter in the background.