Robust image matching via local graph structure consensus

X Jiang, Y **a, XP Zhang, J Ma - Pattern Recognition, 2022 - Elsevier
Image matching plays a vital role in many computer vision tasks, and this paper focuses on
the mismatch removal problem of feature-based matching. We formulate the problem into a …

SSL-Net: Sparse semantic learning for identifying reliable correspondences

S Chen, G **ao, Z Shi, J Guo, J Ma - Pattern Recognition, 2024 - Elsevier
Feature matching aims to identify reliable correspondences between two sets of given initial
feature points, which is of considerable importance to photogrammetry and computer vision …

JRA-Net: Joint representation attention network for correspondence learning

Z Shi, G **ao, L Zheng, J Ma, R Chen - Pattern Recognition, 2023 - Elsevier
In this paper, we propose a Joint Representation Attention Network (JRA-Net), an end-to-
end network, to establish reliable correspondences for image pairs. The initial …

Diversification-Agentsourcing-Conversification theory: Insights into a universal problem-solving strategy with an informative review

A Taimori, JR Hopgood - Authorea Preprints, 2024 - techrxiv.org
Proficiency in problem-solving techniques is essential for engineers across various
disciplines. Achieving a successful answer to a specific problem in sciences often …

Guided neighborhood affine subspace embedding for feature matching

Z Li, Y Ma, X Mei, J Huang, J Ma - Pattern Recognition, 2022 - Elsevier
Feature matching, which refers to determining reliable correspondences between two sets of
feature points, is a fundamental component of numerous visual tasks. This paper proposes a …

Hypergraph matching via game-theoretic hypergraph clustering

J Hou, M Pelillo, H Yuan - Pattern Recognition, 2022 - Elsevier
Feature matching is used to build correspondences between features in the model and test
images. As the extension of graph matching, hypergraph matching is able to encode rich …

Multi-neighborhood guided Kendall rank correlation coefficient for feature matching

J Chen, M Yang, W Gong, Y Yu - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Seeking feature correspondences among two or more images is an important problem in
computer vision and image processing. The putative matches constructed by the similarity of …

Does cross-validation work in telling rankings apart?

BR Sziklai, M Baranyi, K Héberger - Central European Journal of …, 2024 - Springer
Although cross-validation (CV) is a standard technique in machine learning and data
science, its efficacy remains largely unexplored in ranking environments. When evaluating …

On learning discriminative embeddings for optimized top-k matching

S Ghosh, M Vatsa, R Singh, N Ratha - Pattern Recognition, 2025 - Elsevier
Optimizing overall classification accuracy in neural networks does not always yield the best
top-k accuracy, a critical metric in many real-world applications. This discrepancy is …

DF3Net: Dual frequency feature fusion network with hierarchical transformer for image inpainting

M Huang, W Yu, L Zhang - Information Fusion, 2024 - Elsevier
In recent years, researchers have made significant strides in computer vision by leveraging
transformers, achieving remarkable breakthroughs in low-level vision tasks. The inherent …