Login / Signup

VioLET: Vision-Language Efficient Tuning with Collaborative Multi-modal Gradients.

Yaoming WangYuchen LiuXiaopeng ZhangJin LiBowen ShiChenglin LiWenrui DaiHongkai XiongQi Tian
Published in: ACM Multimedia (2023)
Keyphrases
  • multi modal
  • multi modality
  • cross modal
  • image annotation
  • computer vision
  • audio visual
  • high dimensional
  • semantic concepts
  • machine learning
  • xml documents