Towards Better Caption Supervision for Object Detection
As training high-performance object detectors requires expensive bounding box annotations, recent methods resort to free-available image captions. However, detectors trained on caption supervision perform poorly because captions are usually noisy and cannot provide precise location information. To t...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on visualization and computer graphics. - 1996. - 28(2022), 4 vom: 03. Apr., Seite 1941-1954
|
|---|
| 1. Verfasser: |
Chen, Changjian
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Wu, Jing,
Wang, Xiaohan,
Xiang, Shouxing,
Zhang, Song-Hai,
Tang, Qifeng,
Liu, Shixia |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2022
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on visualization and computer graphics
|
|---|
| Schlagworte: | Journal Article |
|---|