BMT icon indicating copy to clipboard operation
BMT copied to clipboard

Source code for "Bi-modal Transformer for Dense Video Captioning" (BMVC 2020)

Results 8 BMT issues
Sort by recently updated
recently updated
newest added

Thank you for your excellent work **Describe the bug** when I bash ./download_data.sh Checking for correctness of the downloaded files md5sum: ./data/i3d_25fps_stack64step64_2stream_npy.zip: No such file or directory ERROR: .zip file...

Hello, Thanks for this amazing work. Error opening './tmp/test.wav': System error. Above error on executing python main.py --feature_type vggish --on_extraction save_numpy --device_ids 0 --video_paths ../../sample/v__N1MWv9bW6Q.mp4 --output_path ../../sample/ comand Please help...

Hi, Thanks for this amazing work. I'm wondering if it's better to create one general virtualenv (and one requirements.txt file) instead of 3 conda environment and their yml files ?...

Do you have a way to visualize the attention mechanism?I want to know what exactly does the attention mechanism focus on?

Hello, Vladimir. First of all congratulations for such a fantastic project. I was introduced to this work from many other papers who cited it and used it as a base...

I am facing the above error while running the training script. Can someone let me know how to solve it? My GPU specifications are- ![image](https://github.com/v-iashin/BMT/assets/116613755/ab89e3ce-368d-44ad-a599-9bfd67d07ded) And the packages in conda...

I want to fine tune this pre-trained model for learning purpose on a small set of videos, but not able to proceed. If anyone can help me then it would...

Hello Iashin, I have trained the proposal generation module for 5 epochs and I have got a new 'best_prop_model.pt' and 5 files 'prop_results_val_1_e*_maxprop100.json' for epoch 0 to 4 , but...