Výsledky vyhledávání - "Ge, Mengying"

Report

Early Joint Learning of Emotion Information Makes MultiModal Model Understand You Better

Autor: Ge, Mengying, Li, Mingyang, Tang, Dongkai, Li, Pengbo, Liu, Kuo, Deng, Shuhao, Pu, Songbai, Liu, Long, Song, Yang, Zhang, Tao

In this paper, we present our solutions for emotion recognition in the sub-challenges of Multimodal Emotion Recognition Challenge (MER2024). To mitigate the modal competition issue between audio and text, we adopt an early fusion strategy based on a

Externí odkaz: http://arxiv.org/abs/2409.18971

Zobrazit plný text záznamu

Report

Video Emotion Open-vocabulary Recognition Based on Multimodal Large Language Model

Autor: Ge, Mengying, Tang, Dongkai, Li, Mingyang

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

Externí odkaz: http://arxiv.org/abs/2408.11286

Zobrazit plný text záznamu

Akademický článek

Analysis of microstructure and compressive properties of full coral concrete under fiber reinforcement

Autor: Dai, Junyan, Yin, Shiping, Wang, Fei, Ge, Mengying

Publikováno v: In Journal of Building Engineering 15 September 2024 93

Zobrazit plný text záznamu

Report

DAF-NET: a saliency based weakly supervised method of dual attention fusion for fine-grained image classification

Autor: Dong, ZiChao, Wu, JiLong, Ren, TingTing, Wang, Yue, Ge, MengYing

Fine-grained image classification is a challenging problem, since the difficulty of finding discriminative features. To handle this circumstance, basically, there are two ways to go. One is use attention based method to focus on informative areas, wh

Externí odkaz: http://arxiv.org/abs/2001.02219

Zobrazit plný text záznamu