Three Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding.

Ozan Unal Christos Sakaridis Suman Saha Fisher Yu Luc Van Gool

Published in: CoRR (2023)

Keyphrases

visual information
visual features
visual perception
visual appearance
object recognition
visual data
low level
thermal images
database
visual processing
visual analysis
visual cues
video data
optical flow
feature extraction
high level
case study
real world
data sets
real time