X
Xi Zhou
Researcher at Chinese Academy of Sciences
Publications - 51
Citations - 2248
Xi Zhou is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Facial recognition system & Mixture model. The author has an hindex of 19, co-authored 51 publications receiving 2067 citations. Previous affiliations of Xi Zhou include University of Illinois at Urbana–Champaign & Rochester Institute of Technology.
Papers
More filters
Book ChapterDOI
Image classification using super-vector coding of local image descriptors
TL;DR: In this article, the authors proposed a new framework for image classification using local visual descriptors, which performs a nonlinear feature transformation on descriptors and aggregates the results together to form image-level representations, and finally applies a classification model.
Proceedings ArticleDOI
A Deep Regression Architecture with Two-Stage Re-initialization for High Performance Facial Landmark Detection
TL;DR: This paper presents a deep regression architecture with two-stage re-initialization to explicitly deal with the initialization problem and obtains promising results using different kinds of unstable initialization.
Journal ArticleDOI
Real-world acoustic event detection
TL;DR: This work proposes extracting discriminative features for AED using a boosting approach, which outperform classical speech perceptual features, such as Mel-frequency Cepstral Coefficients and log frequency filterbank parameters, and leverages statistical models better fitting the task.
Proceedings ArticleDOI
Hierarchical Gaussianization for image classification
TL;DR: A new image representation to capture both the appearance and spatial information for image classification applications is proposed and it is justified that the traditional histogram representation and the spatial pyramid matching are special cases of the hierarchical Gaussianization.
Proceedings ArticleDOI
Regression from patch-kernel
TL;DR: A patch-based regression framework for addressing the human age and head pose estimation problems by characterizing the Kullback-Leibler divergence between the derived models for any two images, and its discriminating power is further enhanced by a weak learning process, called inter-modality similarity synchronization.