MultiBench issues

Models, data used in get_data.py for mmimdb missing

Hi, Is there any way to access the **VGGNet pretrained model** and data used to extract parameters/features in vgg.py and get_data.py ? The repo for this (**multibench**) seems to have...

abhinavnippani

Process mosei_senti_data.pkl to match the text id in mosei.hdf5

If you are using the **mosei_senti_data.pkl** and want to get the raw text by matching the id in mosei.hdf5, please consider to use the following script to process the data....

ZhuoZHI-UCL

Text data encoding

Hi, for MOSI and MOSEI, for the preprocessed data accessed via google drive, how do you get their embeddings? You don't mention this anywhere as far as I can find...

h-0-0

About accuracy on MOSI dataset in paper

1

Can someone tell me whether the parameter settings of these examples are very different from those in the paper? I tried to verify the performance on the MOSI dataset, but...

wangzx-tech

Audio Feature Extraction

I noticed that the length of audio features and visual features in the MOSI dataset are different from those in MOSEI, may I ask what tool was used to extract...

xiaoxinchaoren56

Question about the MUJOCO PUSH accuracy

Thanks for your excellent work! I have questions about the results in Table 17. Is there a scientific notation unit missed since my reproduction results are about 0.0023 in MSE?...

shentt67