X
Xiangjian He
Researcher at University of Technology, Sydney
Publications - 421
Citations - 7397
Xiangjian He is an academic researcher from University of Technology, Sydney. The author has contributed to research in topics: Image segmentation & Computer science. The author has an hindex of 35, co-authored 401 publications receiving 5511 citations. Previous affiliations of Xiangjian He include Information Technology University & University of Sydney.
Papers
More filters
Proceedings ArticleDOI
Intrusion Detection Using Geometrical Structure
TL;DR: A statistical model, namely Geometrical Structure Anomaly Detection (GSAD), is proposed to detect intrusion using the packet payload in the network to establish and identify the correlation among packet payloads in a network.
Journal ArticleDOI
Time-Frequency Filter Bank: A Simple Approach for Audio and Music Separation
TL;DR: A generalized Short Time Fourier Transform (STFT)-based technique, combined with filter bank to extract vocals from background music, and shows that the proposed approach performs better than the other state-of-the-art approaches, in terms of Signal-to-Interference Ratio (SIR) and Signal- to-Distortion ratio (SDR), respectively.
Proceedings ArticleDOI
A-CCNN: Adaptive CCNN for Density Estimation and Crowd Counting
TL;DR: Wang et al. as mentioned in this paper proposed an Adaptive Counting Convolutional Neural Network (A-CCNN) and considered the scale variation of objects in a frame adaptively so as to improve the accuracy of counting.
Journal ArticleDOI
An easy-to-use deep-learning model for highly accurate diagnosis of Parkinson's disease using SPECT images.
TL;DR: A CNN-based network model highly capable of discriminating PD patients based on Single Photon Emission Computed Tomography (SPECT) images from healthy controls is developed, which has the potential to revolutionize the diagnosis of PD and its management.
Journal ArticleDOI
Visual Tracking via Nonnegative Multiple Coding
TL;DR: This paper proposes a novel appearance model named as “nonnegative multiple coding” (NMC) to accurately represent a target, which involves a series of local dictionaries created with different predefined numbers of nearest neighbors, and then the contributions of these dictionaries are automatically learned.