H
Hui Wei
Researcher at Fudan University
Publications - 50
Citations - 532
Hui Wei is an academic researcher from Fudan University. The author has contributed to research in topics: Cognitive neuroscience of visual object recognition & Object detection. The author has an hindex of 11, co-authored 45 publications receiving 334 citations.
Papers
More filters
Journal ArticleDOI
Contour detection model with multi-scale integration based on non-classical receptive field
Hui Wei,Bo Lang,Qingsong Zuo +2 more
TL;DR: A multi-scale integration based contour extraction model, inspired by the inhibitory and disinhibitory interactions between the CRF and the nCRF is presented and provides a better understanding of the role of thenCRF and a novel approach for computer vision and pattern recognition.
Journal ArticleDOI
A novel method for 2D nonrigid partial shape matching
Chengzhuan Yang,Hui Wei,Qian Yu +2 more
TL;DR: A novel shape descriptor, triangular centroid distances (TCDs) is proposed, for shape representation; the TCDs shape descriptor is invariant to translation, rotation, scaling, and considerable shape deformations and outperforms existing methods in 2D nonrigid partial shape matching.
Journal ArticleDOI
A Genetic-Algorithm-Based Explicit Description of Object Contour and its Ability to Facilitate Recognition
Hui Wei,Xue-song Tang +1 more
TL;DR: This paper shows that the explicit representation of the shape contour contributes significantly to shape representation and object recognition.
Journal ArticleDOI
Visual Navigation Using Projection of Spatial Right-Angle In Indoor Environment
Hui Wei,Luping Wang +1 more
TL;DR: This paper presented a method to efficiently understand indoor scenes from a single image, without training or any knowledge of the camera's internal calibration, and estimated not only room layout, but also details of the indoor scene.
Journal ArticleDOI
DERF: Distinctive Efficient Robust Features From the Biological Modeling of the P Ganglion Cells
TL;DR: Extensive experiments conducted in the image matching task on the multiview stereo correspondence data set demonstrate that DERF outperforms state of the art methods for both hand-crafted and learned descriptors, while remaining robust and being much faster to compute.