An end-to-end system that performs temporal recognition of gesture sequences using speech and skeletal input. The model combines three networks with a CTC output layer that recognises gestures from continuous stream.
Hello Alex,
The data downloaded here http://sunai.uoc.edu/chalearn/#tabs-2 contains the skeletal data in MAT files (each mat file contain video, depth and skeleton)
Please can you provide the skeletal data in cdv format or the python script used to convert mat files to acv files needed in your codes extract_activity_feats.py, gather_skeletal.py, skeletal_feature_extraction.py)?
Hello Alex, The data downloaded here http://sunai.uoc.edu/chalearn/#tabs-2 contains the skeletal data in MAT files (each mat file contain video, depth and skeleton) Please can you provide the skeletal data in cdv format or the python script used to convert mat files to acv files needed in your codes extract_activity_feats.py, gather_skeletal.py, skeletal_feature_extraction.py)?
Many thanks Hazem