Multifaceted Evaluation of Audio-Visual Capability for MLLMs: Effectiveness, Efficiency, Generalizability and Robustness

Documenti analoghi

• Robust LLM-based Audio-Visual Speech Recognition with Sparse Modality Alignment and Visual Unit-Guided Refinement
  di: Su, Fei, et al.
  Pubblicazione: (2026)
• Robust Wake Word Spotting With Frame-Level Cross-Modal Attention Based Audio-Visual Conformer
  di: Wang, Haoxu, et al.
  Pubblicazione: (2024)
• Rhythmic Foley: A Framework For Seamless Audio-Visual Alignment In Video-to-Audio Synthesis
  di: Huang, Zhiqi, et al.
  Pubblicazione: (2024)
• Efficient Video to Audio Mapper with Visual Scene Detection
  di: Yi, Mingjing, et al.
  Pubblicazione: (2024)
• Human-Inspired Computing for Robust and Efficient Audio-Visual Speech Recognition
  di: Liu, Qianhui, et al.
  Pubblicazione: (2024)