J
Jiaqi Yang
Researcher at Northwestern Polytechnical University
Publications - 63
Citations - 996
Jiaqi Yang is an academic researcher from Northwestern Polytechnical University. The author has contributed to research in topics: Computer science & Feature (computer vision). The author has an hindex of 11, co-authored 49 publications receiving 516 citations. Previous affiliations of Jiaqi Yang include Huazhong University of Science and Technology & Industrial Technology Research Institute.
Papers
More filters
Journal ArticleDOI
VOID: 3D object recognition based on voxelization in invariant distance space
Posted Content
Non-linear and Selective Fusion of Cross-Modal Images
TL;DR: Wang et al. as discussed by the authors proposed a multi-source image fusion framework that combines illuminance factors and attention mechanisms, which effectively combines traditional image features and modern deep learning features and demonstrated the superiority of their fusion framework over state-of-the-art in visual quality, objective fusion metrics and robustness.
Posted Content
Comparative evaluation of 2D feature correspondence selection algorithms.
TL;DR: Evaluating eight 2D correspondence selection algorithms ranging from classical methods to the most recent ones on four standard datasets and measuring the quality of a correspondence selection algorithm from four perspectives, i.e., precision, recall, F-measure and efficiency.
Proceedings ArticleDOI
Matching User Accounts across Large-scale Social Networks based on Locality-sensitive Hashing
TL;DR: Wang et al. as mentioned in this paper proposed a locality-sensitive hashing-based user identification (LoSHui) method, which mainly consists of four components: first, they construct locality sensitive hash function families that are suitable for determining the user trajectory, and then they construct the candidate user pairs in each hash bucket.
Posted Content
3D Correspondence Grouping with Compatibility Features
TL;DR: Comparisons with nine state-of-the-art methods on four benchmarks demonstrate that: 1) CF is distinctive, robust, and rotation-invariant; 2) the CF-based method achieves the best overall performance and holds good generalization ability.