The visual cues from multiple support regions of different sizes and resolutions are complementary in classifying a candidate box in object detection. Effective integration of local and contextual visual cues from these regions has become a fundamental problem in object detection. In this paper, we...
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 40(2018), 9 vom: 20. Sept., Seite 2109-2123
|
|---|
| 1. Verfasser: |
Zeng, Xingyu
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Ouyang, Wanli,
Yan, Junjie,
Li, Hongsheng,
Xiao, Tong,
Wang, Kun,
Liu, Yu,
Zhou, Yucong,
Yang, Bin,
Wang, Zhe,
Zhou, Hui,
Wang, Xiaogang |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2018
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article
Research Support, Non-U.S. Gov't |
|---|