Login / Signup
FCC-MF: Detecting Violence in Audio-Visual Context with Frame-Wise Cluster Contrast and Modality-Stage Flooding.
Jiaqing He
Yanzhen Ren
Liming Zhai
Wuyang Liu
Published in:
ICASSP (2024)
Keyphrases
</>
visual context
semantic context
temporal context
multi modal
video annotation
audio visual
object detection
scene interpretation
visual information
multimedia
pairwise
visual words
visual scene
video frames
visual data
key frames
discriminative power
image classification
co occurrence
multiscale