RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
–Neural Information Processing Systems
Existing object detection frameworks are usually built on a single format of object/part representation, i.e., anchor/proposal rectangle boxes in RetinaNet and
Neural Information Processing Systems
Aug-15-2025, 10:06:30 GMT
- Country:
- Asia (0.04)
- North America > Canada (0.04)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning (1.00)
- Natural Language (0.68)
- Vision (1.00)
- Information Technology > Artificial Intelligence