-
"Hello, could you provide the original videos of the YouCook2 dataset? Some videos on YouTube are damaged and cannot be downloaded. "
-
Hi @yellow-binary-tree, thanks for your great project.
I am interested in reproducing the training & testing. Since "video downloading may take quite a while 🙃", could you please share how much sto…
-
Hi,
Is there a script to generate captions for videos other than ActivityNet or YouCook2?
Could you let me know what changes needs to be made to just generate captions for a video which does not hav…
-
I reproduced using Charades dataset based on the checkpoint given in the repo, and the result was **27.9 for R@1 (IoU = 0.5) and 12.3 for R@1 (IoU = 0.7).**
However, according to the results of the p…
-
Thank you for your excellent work!
Could you provide the original videos of the YouCook2 dataset? Some videos on YouTube are damaged and cannot be downloaded.
-
Hi @RenShuhuai-Andy, thanks for sharing this great work! For some videos in HiREST dataset, the filenames are "xxxx_35_79.mp4". Do we need to crop the original videos according to the timestamps in th…
-
Hello, the Univl didn't provide youcookii_data.no_transcript.pickle file. How did you do the experiments V+T part of youcook caption.
-
Hi,
I trained the model in the dataset YouCookII and used the same configuration you provided in GitHub; however, I got different scores. Especially my Cider score is much lower than your Cider sco…
-
Hi, thanks for sharing great work.
I tried to segment YouCook2 training videos and observed that actionformer gives much shorter segments. Do you have a clue about that? I tried this because I obs…
-
Great work Antoine! In your last paper Vid2Seq, you also tested the pre-trained model on the ActivityNet captions dataset, but in VidChapters you only show on ViTT and YouCook2. I am wondering if ther…