kracwarlock/action-recognition-visual-attention

Issues

• Results reproducibility

  #13 opened 8 years ago by jacopocavazza
  3

• How to get the dataset?

  #15 opened 7 years ago by cumtwb
  2

• Can anyone share the code mentioned in the closed issue #6 which is used to combine features to h5 format?

  #20 opened 7 years ago by YinRui1991
  3

• I'm new to this task. Could I know that how many frame are feed in testing time?

  #21 opened 6 years ago by guotong1988
  0

• Can you elaborate how to do data preprocessing?

  #6 opened 8 years ago by YantianZha
  23

• Python Scripts for CNN Encoding Generation

  #19 opened 7 years ago by 345ishaan
  1

• Possible bug on data_handler : Reset()

  #18 opened 7 years ago by noky
  0

• How to get the h5 features file，how to create h5 features file

  #17 opened 7 years ago by arcxianzhang
  0

• Your time for one 128-batch?

  #16 opened 7 years ago by thanhnguyentang
  5

• Location softmax

  #12 opened 8 years ago by pmorerio
  4

• Multi-layer LSTM

  #14 opened 8 years ago by pmorerio
  0

• Initialization of LSTM layers

  #3 opened 8 years ago by xlliu7
  21

• ucf11 evaluation problem

  #11 opened 8 years ago by ae86208
  1

• some question about the input and output of the LSTM

  #10 opened 8 years ago by Ouya-Bytes
  2

• Possible redundant code in actrec_mAP.py

  #9 opened 8 years ago by nixingyang
  1

• Enquiries regarding Data Preprocessing

  #8 opened 8 years ago by nixingyang
  1

• How the soft attention model be implemented in this project?

  #7 opened 8 years ago by kyuusaku
  1

• Input data

  #2 opened 8 years ago by frajem
  10

• Best model selection

  #4 opened 8 years ago by frajem
  1

• 1

  #5 opened 8 years ago by YantianZha
  0

• How to get the h5 features file

  #1 opened 8 years ago by Yidann
  3