Login / Signup

CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding.

Zhijian HouWanjun ZhongLei JiDifei GaoKun YanWing Kwong ChanChong-Wah NgoZheng ShouNan Duan
Published in: CoRR (2022)
Keyphrases
  • coarse to fine
  • multiresolution
  • multiscale
  • object detection
  • pattern recognition
  • pairwise
  • image segmentation
  • three dimensional
  • similarity measure
  • matching scheme
  • hierarchical representation