Introduces TALKIN dataset and deep Siamese fusion network showing audio-visual combination outperforms uni-modal baselines for kinship verification.
Multi-modal factorized bilinear pooling with co-attention learning for visual question answering,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Audio-Visual Kinship Verification
Introduces TALKIN dataset and deep Siamese fusion network showing audio-visual combination outperforms uni-modal baselines for kinship verification.