Emotion Understanding in Videos Through Body, Context, and Visual-Semantic Embedding Loss

Autor:	Niki Efthymiou, Gerasimos Potamianos, Panagiotis Paraskevas Filntisis, Petros Maragos
Rok vydání:	2020
Předmět:	Computer science business.industry Context (language use) computer.software_genre Body language Test set Embedding Expressed emotion Artificial intelligence Set (psychology) business computer Word (computer architecture) Natural language processing Meaning (linguistics)
Zdroj:	Computer Vision – ECCV 2020 Workshops ISBN: 9783030664145 ECCV Workshops (1)
Popis:	We present our winning submission to the First International Workshop on Bodily Expressed Emotion Understanding (BEEU) challenge. Based on recent literature on the effect of context/environment on emotion, as well as visual representations with semantic meaning using word embeddings, we extend the framework of Temporal Segment Network to accommodate these. Our method is verified on the validation set of the Body Language Dataset (BoLD) and achieves 0.26235 Emotion Recognition Score on the test set, surpassing the previous best result of 0.2530.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::7d1ded03ed27989ef47cf8af8eff8bb7 https://doi.org/10.1007/978-3-030-66415-2_52 Zobrazit plný text záznamu