YuanGongND/cav-mae

Issues

• Can you share some visualization for your results of paper?

  #32 opened 4 months ago by DevKiHyun
  2

• traintest_ft.py 中缺少 calculate_stats 函数

  #31 opened 7 months ago by yt605155624
  1

• About the video part, could you release the experimental code?

  #30 opened 8 months ago by Cb1ock
  2

• Eval data not used in evaluation stage?

  #28 opened 9 months ago by ben2002chou
  0

• some problem about finetuning

  #27 opened 10 months ago by thirteen-bears
  1

• Question Regarding stat calculation of dataset

  #24 opened a year ago by ben2002chou
  3

• BOM Considerations When Extracting Your Video frames & Audio

  #25 opened a year ago by fujitte
  2

• Where is contrastive loss implemented? How are the positive and negative samples defined?

  #23 opened a year ago by ben2002chou
  2

• Not found the sample_video_extract_list.csv

  #22 opened a year ago by JackieWang9811
  4

• Could you release the checkpoints pretrained on Kinetics 400

  #21 opened a year ago by qiyue-liang
  1

• what is the validation set for finetuning?

  #19 opened a year ago by thirteen-bears
  6

• Question for contrastive loss weight in the paper

  #20 opened a year ago by sukun1045
  3

• retrieval evaluation

  #15 opened a year ago by sukun1045
  3

• installation

  #18 opened a year ago by chandlerbing65nm
  0

• Just suggesting a small change to Loading model for Finetuning Example

  #16 opened a year ago by ben2002chou
  2

• Some confuse about this paper and implement

  #17 opened a year ago by skyzjsx
  1

• How can i get the video and audio pairs of audioset?

  #10 opened a year ago by SteveTanggithub
  6

• Audio Event Classification resulting tensor has all negative values

  #14 opened a year ago by rehana-mahfuz
  5

• Acquiring checkpoints of VGGSound (audio), VGGSound (video)

  #13 opened a year ago by mouxingyang
  1

• Question about some irregular videos in AudioSet-20k

  #9 opened a year ago by mouxingyang
  6

• How to download MSR-VTT datatset?

  #11 opened a year ago by KyeonghaRho
  4

• Finetune CAVMAE on ESC50

  #8 opened a year ago by kaiw7
  6

• Pretraining cav-mae on K400

  #5 opened a year ago by kaiw7
  18

• Usage of audio-modality components for visual embeddings

  #7 opened 2 years ago by gchochla
  2

• Multi-gpu pre-training

  #6 opened 2 years ago by mtran14
  4

• Which epoch of pre-trained models should I use?

  #4 opened 2 years ago by GenjiB
  5

• Zero-shot Code

  #3 opened 2 years ago by zongzi3zz
  2

• Video Only results on AudioSet-20K

  #2 opened 2 years ago by GenjiB
  3

• Error when loading the CAV-MAE model

  #1 opened 2 years ago by pelegshilo
  2