Abstract | ||
---|---|---|
Finding a template in a search image is one of the core problems many computer vision, such as semantic image semantic, image-to-GPS verification etc. We propose a novel quality-aware template matching method, QATM, which is not only used as a standalone template matching algorithm, but also a trainable layer that can be easily embedded into any deep neural network. Here, our quality can be interpreted as the distinctiveness of matching pairs. Specifically, we assess the quality of a matching pair using soft-ranking among all matching pairs, and thus different matching scenarios such as 1-to-1, I-to-many, and many-to-many will be all reflected to different values. Our extensive evaluation on classic template matching benchmarks and deep learning tasks demonstrate the effectiveness of QATM. It not only outperforms state-of-the-art template matching methods when used alone, but also largely improves existing deep network solutions. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/CVPR.2019.01182 | 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) |
Field | DocType | Volume |
Template matching,Computer vision,Computer science,Artificial intelligence,Deep learning | Journal | abs/1903.07254 |
ISSN | Citations | PageRank |
1063-6919 | 2 | 0.37 |
References | Authors | |
17 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiaxin Cheng | 1 | 3 | 1.40 |
Yue Wu | 2 | 331 | 31.69 |
Wael Abd-Almageed | 3 | 248 | 24.52 |
Premkumar Natarajan | 4 | 874 | 79.46 |