This data stores the preprocessed data for paper:
SignLLM: Sign Languages Production Large Language Models.
This data stores the preprocessed data for paper:
SignDiff: Learning Diffusion Models for American Sign Language Production.
After preprocessing How2Sign dataset, the condensed data set obtained is as follows:
It can be used for the diffusion model training of pose2video in sign language. (Based on ControlNet)
After preprocessing How2Sign dataset, the condensed data set obtained is as follows:
It can be used for the diffusion model training of pose2video in sign language. (Based on Vid2Vid)
Our pre-processing tools: the data cleansing tool and the three-step 2Dto3D tool.
Stay tuned. The data above should be sufficient for the time being.