OpenViDial 2.0
Introduced by Wang et al. in OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts
OpenViDial 2.0 is a larger-scale open-domain multi-modal dialogue dataset compared to the previous version OpenViDial 1.0. OpenViDial 2.0 contains a total number of 5.6 million dialogue turns extracted from either movies or TV series from different resources, and each dialogue turn is paired with its corresponding visual context.
Benchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
OpenViDial 2.0
|
FV
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
