md-mohaiminul/VideoRecap

Issues

• GPT2LMHeadModel does not support an attention implementation through torch.nn.functional.scaled_dot_product_attention yet

  #14 opened 2 months ago by hanjidani
  0

• Ego4D dataset

  #13 opened 3 months ago by YingYellow
  0

• How can I know the time corresponding to the segment description

  #12 opened 3 months ago by Wiselnn570
  0

• About training dataset

  #11 opened 5 months ago by lwpyh
  0

• About VQA task

  #10 opened 7 months ago by shuyansy
  0

• Question about captions

  #9 opened 7 months ago by tiangeluo
  0

• About the CIDEr metric

  #8 opened 7 months ago by AlbertHuyb
  0

• Question about the training cost

  #6 opened 7 months ago by Richar-Du
  2

• Question about the clip captions generated by the model for my video.

  #7 opened 7 months ago by Xuchen-Li
  2

• Evaluate error

  #3 opened 7 months ago by shuyansy
  1

• Hierarchical captions of raw video data

  #1 opened 7 months ago by G-U-N
  3

• Usage of Pre-Trained Models

  #5 opened 7 months ago by fakerybakery
  2

• License

  #4 opened 8 months ago by fakerybakery
  2

• Model repositories on Hugging Face

  #2 opened 8 months ago by merveenoyan
  2