×
Oct 13, 2019 · By following multi-stage training strategy, our experiments show steady and significant improvement on the VATEX benchmark. This report presents ...
Oct 13, 2019 · By following multi-stage training strategy, our experiments show steady and significant improvement on the VATEX benchmark. This report presents ...
By following multi-stage training strategy, our experiments show steady and significant improvement on the VATEX benchmark. This report presents an overview and ...
By following multi-stage training strategy, our experiments show steady and significant improvement on the VATEX benchmark. This report presents an overview and ...
[RDF data]. VATEX Captioning Challenge 2019: Multi-modal Information Fusion and Multi-stage Training Strategy for Video Captioning. Resource URI: https ...
Ranked #9 on Video Captioning on VATEX (using extra training data) ... Multi-modal Information Fusion and Multi-stage Training Strategy for Video Captioning.
We propose a style-aware two-stage learning framework. In the first stage, the model is trained with captions of separate styles.
Ranked #9 on Video Captioning on VATEX (using extra training data) ... Multi-modal Information Fusion and Multi-stage Training Strategy for Video Captioning.
The 1st VATEX Captioning Challenge has ended! We plan to archive the competition results from CodaLab to the official VATEX website and further contribute to ...
Missing: Fusion Training
Oct 15, 2019 · This notebook paper presents our model in the VATEX video captioning challenge. In order to capture multi-level aspects in the video, ...
Missing: stage | Show results with:stage