Login / Signup

CNN-Based Encoder and Transformer-Based Decoder for Efficient Semantic Segmentation.

Seunghun MoonSuk-Ju Kang
Published in: ICEIC (2024)
Keyphrases
  • semantic segmentation
  • street scenes
  • label transfer
  • motion estimation
  • superpixels
  • image processing
  • higher order
  • conditional random fields
  • multiple objects
  • weakly supervised
  • video codec