search

weirme / FCSN

A PyTorch reimplementation of FCSN in paper "Video Summarization Using Fully Convolutional Sequence Networks"
115 stars 33 forks source link

Any ideas about the structure of unsupervised SUM-FCN #9

Open chenbohua3 opened 5 years ago

chenbohua3 commented 5 years ago

After reading chapter 3.3 in FCSN several times, I can not figure out what exactly structure of the unsupervised part. Is that mean:

  1. select Y frames: choose the top Y socres features with dimension: batch * 2 * Y
  2. apply a 11 conv to decode features above to reconstruct their orginal feature representations: `batch 2 Y -> batch 10 * Y (shape of the output of conv8)`
  3. merge the input frame-level feature vectors of thess selected Y frames using skip connection: batch * 1024 * Y -> batch * 10 * Y and then added by the output of step 2
  4. obtain final reconstructed features of the Y frames: batch * 10 * Y -> batch * 1024 * Y
jiaweichuang commented 4 years ago

Hello,have you implemented this unsupervised part?Can you tell me?