CLIP-Count: Towards Text-Guided Zero-Shot Object Counting.

Ruixiang Jiang Lingbo Liu Changwen Chen

Published in: ACM Multimedia (2023)

Keyphrases

text retrieval
d objects
object model
deformable objects
partial occlusion
neural network
text mining
semantic information
complex objects
text data
object models
text information
text documents
free text
object segmentation
text graphics