Paper Reading AI Learner

A Protocol for Emotions

2021-10-29 11:48:29
Gabriele Costa

Abstract

We tend to consider emotions a manifestation of our innermost nature of human beings. Emotions characterize our lives in many ways and they chaperon every rational activity we carry out. Despite their pervasiveness, there are still many things we ignore about emotions. Among them, our understanding of how living beings transfer emotions is limited. In particular, there are highly sophisticated interactions between human beings that we would like to comprehend. For instance, think of a movie director who knows in advance the strong emotional impact that a certain scene will have on the spectators. Although many artists rely on some emotional devices, their talent and vision are still the key factors. In this work we analyze high-level protocols for transferring emotions between two intelligent agents. To the best of our knowledge, this is the first attempt to use communication protocols for modeling the exchange of human emotions. By means of a number of examples, we show that our protocols adequately model the engagement of the two parties. Beyond the theoretical interest, our proposal can provide a stepping stone for several applications that we also discuss in this paper.

Abstract (translated)

URL

https://arxiv.org/abs/2110.15695

PDF

https://arxiv.org/pdf/2110.15695.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot