Multi-Modal Video Dialog State Tracking in the Wild.

Adnen Abdessaied Lei Shi Andreas Bulling

Published in: CoRR (2024)

Keyphrases

multi modal
semantic concepts
video search
audio visual
multi modality
cross modal

video sequences
multiple modalities
video data
face detection and tracking
video surveillance
multimedia

high dimensional
video analysis
video database
fusing multiple
uni modal
video clips

spatial and temporal
video streams
particle filter
relevance feedback
state space
image analysis