DICCAE dynamically weights a confusion loss using measured inter-class overlap and reports 65.5% audio-visual top-1 on VGGSound, but the evaluation protocol uses test data during training.
Scaling egocentric vision: The epic-kitchens dataset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Dynamic Inter-Class Confusion-Aware Encoder for Audio-Visual Fusion in Human Activity Recognition
DICCAE dynamically weights a confusion loss using measured inter-class overlap and reports 65.5% audio-visual top-1 on VGGSound, but the evaluation protocol uses test data during training.