Source code for "Bi-modal Transformer for Dense Video Captioning" (BMVC 2020)
Why do you think that https://github.com/v-iashin/SpecVQGAN is a good alternative to BMT
Source code for "Bi-modal Transformer for Dense Video Captioning" (BMVC 2020)
Why do you think that https://github.com/v-iashin/SpecVQGAN is a good alternative to BMT