Abstract | ||
---|---|---|
We present Convolutional Oriented Boundaries (COB), which produces multiscale oriented contours and region hierarchies starting from generic image classification Convolutional Neural Networks (CNNs). COB is computationally efficient, because it requires a single CNN forward pass for multi-scale contour detection and it uses a novel sparse boundary representation for hierarchical segmentation; it g... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TPAMI.2017.2700300 | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Keywords | DocType | Volume |
Image segmentation,Feature extraction,Semantics,Detectors,Machine learning,Proposals,Benchmark testing | Journal | 40 |
Issue | ISSN | Citations |
4 | 0162-8828 | 31 |
PageRank | References | Authors |
0.90 | 30 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kevis-Kokitsi Maninis | 1 | 179 | 7.67 |
Jordi Pont-Tuset | 2 | 656 | 32.22 |
Pablo Arbelaez | 3 | 3626 | 173.00 |
Luc Van Gool | 4 | 27566 | 1819.51 |