Vonderland
Vonderland
Thank you for your nice code! It is quite novel to consider sequantial relationships for knowledge selection. I have used your code and pretrained models for WoW seen/unseen inference (under...
Thanks for this open-source codes! In your paper, you said that the re-collected Holl-E contains 7,228 dialogues for training, 930 dialogues for validation and 913 dialogues for test, but I...
thank you for providing this implementation of segmentation! from the rfcn implementation of the original paper, the key frame interval is set under the config. how to set the interval...