Login / Signup

Make Acoustic and Visual Cues Matter: CH-SIMS v2.0 Dataset and AV-Mixup Consistent Module.

Yihe LiuZiqi YuanHuisheng MaoZhiyun LiangWanqiuyue YangYuanzhe QiuTie ChengXiaoteng LiHua XuKai Gao
Published in: CoRR (2022)
Keyphrases
  • visual cues
  • low level
  • visual information
  • mid level
  • audio visual
  • multiple visual cues
  • artificial intelligence
  • knowledge base
  • object detection
  • multiple cues
  • database
  • key frames
  • depth cues