Login / Signup
ViDT: An Efficient and Effective Fully Transformer-based Object Detector.
Hwanjun Song
Deqing Sun
Sanghyuk Chun
Varun Jampani
Dongyoon Han
Byeongho Heo
Wonjae Kim
Ming-Hsuan Yang
Published in:
ICLR (2022)
Keyphrases
</>
object detectors
three dimensional
object detection
feature space
object class
data sets
active learning
multi class
multi modal