RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder.

Cheng Chi Fangyun Wei Han Hu

Published in: CoRR (2020)

Keyphrases

visual representations
object detection
visual representation
visualization tools
object class
computer vision
object categories
object recognition
background subtraction
multi class
object models
database
visual analytics
range data
computer graphics
learning process
social networks