ictnlp DSTC8-AVSD issues

ictnlp / DSTC8-AVSD

We rank the 1st in DSTC8 Audio-Visual Scene-Aware Dialog competition. This is the source code for our IEEE/ACM TASLP (AAAI2020-DSTC8-AVSD) paper "Bridging Text and Video: A Universal Multimodal Transformer for Video-Audio Scene-Aware Dialog".

MIT License

55 stars 14 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Bump transformers from 2.1.1 to 4.30.0

#6 dependabot[bot] opened 1 year ago
0
'VideoGPT2Model' object has no attribute 'output_hidden_states'

#5 avinashsai opened 2 years ago
2
it seems hard to reproduce your results in paper.

#4 patrick-tssn closed 3 years ago
5
The evaluation results i get are lower than reported in the paper

#3 yukaroman closed 3 years ago
2
Question on reproduction

#2 cshanjiewu closed 4 years ago
15
Model Weights

#1 vibhavagarwal5 opened 4 years ago
2

ictnlp / DSTC8-AVSD

issues

Bump transformers from 2.1.1 to 4.30.0

'VideoGPT2Model' object has no attribute 'output_hidden_states'

it seems hard to reproduce your results in paper.

The evaluation results i get are lower than reported in the paper

Question on reproduction

Model Weights