Name
Abstract | ||
|---|---|---|
Most existing object detection algorithms are trained based upon a set of fully annotated object regions or bounding boxes, which are typically labor-intensive. On the contrary, nowadays there is a significant amount of image-level annotations cheaply available on the Internet. It is hence a natural thought to explore such “weak” supervision to benefit the training of object detectors. In this pap... |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/TNNLS.2018.2816021 | IEEE Transactions on Neural Networks and Learning Systems |
Keywords | Field | DocType |
Detectors,Object detection,Proposals,Training,Convolutional neural networks,Visualization,Learning systems | Object detection,Pattern recognition,Visualization,Convolutional neural network,Computer science,Pooling,Pixel,Artificial intelligence,Detector,The Internet,Bounding overwatch | Journal |
Volume | Issue | ISSN |
29 | 12 | 2162-237X |
Citations | PageRank | References |
7 | 0.42 | 27 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yunhang Shen | 1 | 29 | 7.25 |
| Rongrong Ji | 2 | 3616 | 189.98 |
| Changhu Wang | 3 | 1296 | 70.36 |
| Xuelong Li | 4 | 15049 | 617.31 |
| Xuelong Li | 5 | 9 | 1.12 |