J
Jinglin Zhang
Researcher at Nanjing University of Information Science and Technology
Publications - 18
Citations - 270
Jinglin Zhang is an academic researcher from Nanjing University of Information Science and Technology. The author has contributed to research in topics: Matching (statistics) & Symmetric multiprocessor system. The author has an hindex of 6, co-authored 18 publications receiving 137 citations. Previous affiliations of Jinglin Zhang include European University of Brittany & Hebei University of Technology.
Papers
More filters
Journal ArticleDOI
Hyperspectral Image Classification Using Mixed Convolutions and Covariance Pooling
TL;DR: This work proposes a mixed CNN with covariance pooling for HSI classification that starts with spectral-spatial 3-D convolutions that followed by a spatial 2-D Convolution, which achieves better accuracy than other state-of-the-art methods.
Proceedings ArticleDOI
Deep Adversarial Discrete Hashing for Cross-Modal Retrieval
TL;DR: The proposed DADH improves the performance and outperforms several state-of-the-art hashing methods for cross-modal retrieval and introduces a weighted cosine triplet constraint which can make full use of semantic knowledge from the multi-label to ensure the precise ranking relevance of item pairs.
Proceedings Article
Implementation of motion estimation based on heterogeneous parallel computing system with openc
TL;DR: A parallel Motion Estimation(ME) algorithm implemented using OpenCL is proposed and several optimization strategies applied in the OpenCL implementation of the motion estimation are presented.
Proceedings ArticleDOI
Implementation of Motion Estimation Based on Heterogeneous Parallel Computing System with OpenCL
TL;DR: In this article, a parallel Motion Estimation (ME) algorithm implemented using OpenCL and presented several optimization strategies applied in the OpenCL implementation of the motion estimation, and implemented the proposed algorithm on a heterogeneous computing system which contains one CPU and one GPU, and proposed one method to determine the balance to distribute the workload in heterogeneous Computing system with OpenCL.
Proceedings Article
Real-time GPU-based local stereo matching method
TL;DR: A real-time stereo matching algorithm optimized for GPU platform is proposed using a high level compiler HMPP (Hybrid Multicore Parallel Programming) which greatly reduces the development time and make use of the parallel computing of GPU device with CUDA/OpenCL.