Learning Human Cognitive Appraisal Through Reinforcement Memory Unit
This addresses the challenge of estimating human affective experience in video evaluation tasks, representing an incremental improvement in domain-specific modeling.
The paper tackles the problem of modeling human cognitive appraisal in sequential assessment tasks by proposing a Reinforcement Memory Unit (RMU) mechanism for recurrent neural networks, which achieves superior performance in video quality assessment and quality of experience experiments.
We propose a novel memory-enhancing mechanism for recurrent neural networks that exploits the effect of human cognitive appraisal in sequential assessment tasks. We conceptualize the memory-enhancing mechanism as Reinforcement Memory Unit (RMU) that contains an appraisal state together with two positive and negative reinforcement memories. The two reinforcement memories are decayed or strengthened by stronger stimulus. Thereafter the appraisal state is updated through the competition of positive and negative reinforcement memories. Therefore, RMU can learn the appraisal variation under violent changing of the stimuli for estimating human affective experience. As shown in the experiments of video quality assessment and video quality of experience tasks, the proposed reinforcement memory unit achieves superior performance among recurrent neural networks, that demonstrates the effectiveness of RMU for modeling human cognitive appraisal.