conftrace_

video speaking style recognition

1 paper

Explore in graph

Also known as

VSSR

Co-occurring keywords · papers mentioning both

text-guided nonverbal enhancement (1) modality-invariant representation (1) modality-specific representation (1) long-form video understanding (1) speaking style recognition (1) cross-modal attention (1) video understanding (1) multimodal learning (1)

Papers

Text-Guided Nonverbal Enhancement Based on Modality-Invariant and -Specific Representations for Video Speaking Style Recognition AAAI 2025