PMID-sentid	Pub_year	Sent_text		comp_official_name	comp_offsetprotein_name	organism	prot_offset
29994168-7	2018	The EAC-Net integrates three important elements, i.e., learning transfer, attention coding, and regions of interest processing, making our AU detection approach more efficient and more robust to facial position and orientation changes.	Gold	139-141	ETS transcription factor ELK3	Homo sapiens	8-11	
29994168-9	2018	The EAC-Net with a slight modification also shows its potentials in estimating accurate AU intensities.	Gold	88-90	ETS transcription factor ELK3	Homo sapiens	8-11	
29994168-12	2018	It further shows that the EAC-Net works much better without a face frontalization than with face frontalization through image warping as pre-processing, in terms of computational efficiency and AU detection accuracy.	Gold	194-196	ETS transcription factor ELK3	Homo sapiens	30-33