Login / Signup

InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generation.

Rongyao FangShilin YanZhaoyang HuangJingqiu ZhouHao TianJifeng DaiHongsheng Li
Published in: CoRR (2023)
Keyphrases
  • multi modal
  • high dimensional
  • multi modality
  • audio visual
  • cross modal
  • multimedia
  • computer vision
  • image processing
  • feature selection
  • semantic concepts