Sign in
Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detection.
Jiashuo Yu
Jinyu Liu
Ying Cheng
Rui Feng
Yuejie Zhang
Published in:
CoRR (2022)
Keyphrases
</>
weakly supervised
audio visual
multi modal
object class
active learning
relation extraction
object detection
data sets
image database
named entities
superpixels
object detectors
feature selection
d objects
topic models
visual data