Open Access
Table 6
Paper titles and citation frequencies for Tsungyi Lin
| Title | Citation |
|---|---|
| Learning deep representations for ground-to-aerial geolocalization | 48 |
| Cross-view image geolocalization | 32 |
| Feature pyramid networks for object detection | 1 097 |
| Focal loss for dense object detection | 56 |
| Bottleneck transformers for visual recognition | 18 |
| SpineNet: Learning scale-permuted backbone for recognition and localization | 5 |
| NAS-FPN: Learning scalable feature pyramid architecture for object detection | 46 |
| A multipath network for object detection | 19 |
| Class-balanced loss based on effective number of samples | 91 |
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.