Publications by authors named "Kuan Zhu"

2 Publications

  • Page 1 of 1

Two-Level Attention Network With Multi-Grain Ranking Loss for Vehicle Re-Identification.

IEEE Trans Image Process 2019 Sep 16;28(9):4328-4338. Epub 2019 Apr 16.

Vehicle re-identification (re-ID) aims to identify the same vehicle across multiple non-overlapping cameras, which is rather a challenging task. On the one hand, subtle changes in viewpoint and illumination condition can make the same vehicle look much different. On the other hand, different vehicles, even different vehicle models, may look quite similar. In this paper, we propose a novel Two-level Attention network supervised by a Multi-grain Ranking loss (TAMR) to learn an efficient feature embedding for the vehicle re-ID task. The two-level attention network consisting of hard part-level attention and soft pixel-level attention can adaptively extract discriminative features from the visual appearance of vehicles. The former one is designed to localize the salient vehicle parts, such as windscreen and car head. The latter one gives an additional attention refinement at pixel level to focus on the distinctive characteristics within each part. In addition, we present a multi-grain ranking loss to further enhance the discriminative ability of learned features. We creatively take the multi-grain relationship between vehicles into consideration. Thus, not only the discrimination between different vehicles but also the distinction between different vehicle models is constrained. Finally, the proposed network can learn a feature space, where both intra-class compactness and inter-class discrimination are well guaranteed. Extensive experiments demonstrate the effectiveness of our approach and we achieve state-of-the-art results on two challenging datasets, including VehicleID and Vehicle-1M.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TIP.2019.2910408DOI Listing
September 2019

X-ray tomography study of the random packing structure of ellipsoids.

Soft Matter 2014 Feb;10(7):990-6

We present an X-ray tomography study for the random packing of ellipsoids. The local structure displays short-range correlations. In addition to the contact number Z, we introduce ρshell, the average contact radius of curvature for contacting neighbors, as an additional parameter to characterize the local orientational geometry. In general, the local free volume w is affected by both Z and ρshell. We believe that the particle asphericity induces a polydispersity effect to influence the packing properties. A model is introduced which explicitly maps the ellipsoid packing onto a polydispersed sphere one, and it reproduces most of the experimental observations.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1039/c3sm52841cDOI Listing
February 2014