Two accurate backbones for object detection models in video-frames-based transfer learning: ConvNeXtBase, ConvNeXtXLarge
| Autor: | Wang, Zhaohui, Tian, Jindong, Mandal, Mrinal, Bouraya, Sara, Belangour, Abdessamad |
|---|---|
| Zdroj: | Proceedings of SPIE; October 2024, Vol. 13274 Issue: 1 p132741U-132741U-9, 1194679p |
| Databáze: | Supplemental Index |
| Externí odkaz: |
|