TMD-FS: Improving Few-Shot Object Detection with Transformer Multi-modal Directing.

Ying Yuan Lijuan Duan Wenjian Wang Qing En

Published in: PRCV (4) (2021)

Keyphrases

feature vectors
multi modal
object detection
feature extraction
feature space
multi modality
feature selection
audio visual
computer vision
cross modal
object categories
fuzzy logic
video sequences
video search
fault diagnosis
image annotation
semantic concepts
uni modal
multi class
high dimensional
machine learning