OVMR: Open-Vocabulary Recognition with Multi-Modal References.

Zehong Ma Shiliang Zhang Longhui Wei Qi Tian

Published in: CoRR (2024)

Keyphrases

multi modal
multi modality
object recognition
audio visual
visual recognition
cross modal
feature extraction
high dimensional
action recognition
metadata
low level
markov random field
image annotation
video search
uni modal