L-DYNO: Framework to Learn Consistent Visual Features Using Robot's Motion.

Kartikeya Singh Charuvahan Adhivarahan Karthik Dantu

Published in: ICRA (2024)

Keyphrases

visual features
image classification
visual information
visual content
image retrieval
key frames
visual data
labeled images
motion features
visual appearance
image search
low level
semantic concepts
image collections
semantic gap
human actions
image sequences
wordnet
motion estimation
keywords