id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_hscp7elrtfakfkfv4zzrbyj23q	Haoqi Li	Linking emotions to behaviors through deep transfer learning	2020	32	.pdf	application/pdf	14018	1591	52	from acoustic signals and then use information from the emotion recognition network Keywords Behavior quantification, Emotion, Affective computing, Neural networks, Couples behavior recognition from emotion-informed embeddings') and study how this affects the speech capture, emotion recognition and behavior understanding as shown in Fig. 1 (Soken 2. Context-dependent behavior from emotion-informed embeddings: Instead of 3. Reduced context-dependent behavior from emotion-informed embeddings: Similar Context-dependent behavior recognition from emotion labels Context-dependent behavior recognition from emotion-embeddings Context-dependent behavior recognition from emotion-embeddings Reduced context-dependent behavior recognition from emotion-informed Binarized Emotion-Vector Behavior Primitives are generated by applying the SingleEmotion Classification Network (EC) systems on the couple therapy data: For each session, Table 3 Behavior binary classification accuracy in percentage for context-dependent behavior recognition model from emotion labels. Table 4 Behavior binary classification accuracy in percentage for context-dependent behavior recognition model from emotion-embeddings. 2. Can emotion-informed embeddings be employed in the prediction of behaviors?	./cache/work_hscp7elrtfakfkfv4zzrbyj23q.pdf	./txt/work_hscp7elrtfakfkfv4zzrbyj23q.txt