As a fundamental and critical task in various visual applications, image matching can identify then correspond the same or similar structure/content from two or more images. Over the …
C Liu, C Lou, R Wang, AY Xi… - … on Machine Learning, 2022 - proceedings.mlr.press
Abstract Model fusion without accessing training data in machine learning has attracted increasing interest due to the practical resource-saving and data privacy issues. During the …
R Wang, J Yan, X Yang - IEEE Transactions on Pattern …, 2021 - ieeexplore.ieee.org
Graph matching involves combinatorial optimization based on edge-to-edge affinity matrix, which can be generally formulated as Lawler's quadratic assignment problem (QAP). This …
W Li, Y Peng, M Zhang, L Ding, H Hu… - arXiv preprint arXiv …, 2023 - arxiv.org
Deep model fusion/merging is an emerging technique that merges the parameters or predictions of multiple deep learning models into a single one. It combines the abilities of …
R Wang, J Yan, X Yang - IEEE Transactions on Pattern …, 2023 - ieeexplore.ieee.org
Graph matching (GM) has been a long-standing combinatorial problem due to its NP-hard nature. Recently (deep) learning-based approaches have shown their superiority over the …
R Wang, J Yan, X Yang - Advances in neural information …, 2020 - proceedings.neurips.cc
This paper considers the setting of jointly matching and clustering multiple graphs belonging to different groups, which naturally rises in many realistic problems. Both graph matching …
X Zhu, Z Li, J Lou, Q Shen - Pattern Recognition, 2021 - Elsevier
Deep spatio-temporal neural networks have shown promising performance for video super- resolution (VSR) in recent years. However, most of them heavily rely on accuracy motion …
Recovering camera pose from two-view images is a critical problem in photogrammetry and computer vision. For complex scenarios, point correspondences that are constructed by off …
X Chen, Y Li, R Wang, J Yan - The Twelfth International Conference …, 2024 - openreview.net
The Boolean satisfiability problem (SAT) stands as a canonical NP-complete task. In particular, the scarcity of real-world SAT instances and their usefulness for tuning SAT …