Salvato in:
Dettagli Bibliografici
Autori principali: Ge, Mengying, Tang, Dongkai, Li, Mingyang
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2408.11286
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916365320847360
author Ge, Mengying
Tang, Dongkai
Li, Mingyang
author_facet Ge, Mengying
Tang, Dongkai
Li, Mingyang
contents Multimodal emotion recognition is a task of great concern. However, traditional data sets are based on fixed labels, resulting in models that often focus on main emotions and ignore detailed emotional changes in complex scenes. This report introduces the solution of using MLLMs technology to generate open-vocabulary emotion labels from a video. The solution includes the use of framework, data generation and processing, training methods, results generation and multi-model co-judgment. In the MER-OV (Open-Word Emotion Recognition) of the MER2024 challenge, our method achieved significant advantages, leading to its superior capabilities in complex emotion computation.
format Preprint
id arxiv_https___arxiv_org_abs_2408_11286
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Video Emotion Open-vocabulary Recognition Based on Multimodal Large Language Model
Ge, Mengying
Tang, Dongkai
Li, Mingyang
Computer Vision and Pattern Recognition
Multimodal emotion recognition is a task of great concern. However, traditional data sets are based on fixed labels, resulting in models that often focus on main emotions and ignore detailed emotional changes in complex scenes. This report introduces the solution of using MLLMs technology to generate open-vocabulary emotion labels from a video. The solution includes the use of framework, data generation and processing, training methods, results generation and multi-model co-judgment. In the MER-OV (Open-Word Emotion Recognition) of the MER2024 challenge, our method achieved significant advantages, leading to its superior capabilities in complex emotion computation.
title Video Emotion Open-vocabulary Recognition Based on Multimodal Large Language Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.11286