Výsledky vyhledávání

Report

AUD-TGN: Advancing Action Unit Detection with Temporal Convolution and GPT-2 in Wild Audiovisual Contexts

Autor: Yu, Jun, Zhang, Zerui, Wei, Zhihong, Zhao, Gongpeng, Cai, Zhongpeng, Wang, Yongqi, Xie, Guochen, Zhu, Jichao, Zhu, Wangyuan

Leveraging the synergy of both audio data and visual data is essential for understanding human emotions and behaviors, especially in in-the-wild setting. Traditional methods for integrating such multimodal information often stumble, leading to less-t

Externí odkaz: http://arxiv.org/abs/2403.13678

Zobrazit plný text záznamu

Report

Multimodal Fusion Method with Spatiotemporal Sequences and Relationship Learning for Valence-Arousal Estimation

Autor: Yu, Jun, Zhao, Gongpeng, Wang, Yongqi, Wei, Zhihong, Zheng, Yang, Zhang, Zerui, Cai, Zhongpeng, Xie, Guochen, Zhu, Jichao, Zhu, Wangyuan

This paper presents our approach for the VA (Valence-Arousal) estimation task in the ABAW6 competition. We devised a comprehensive model by preprocessing video frames and audio segments to extract visual and audio features. Through the utilization of

Externí odkaz: http://arxiv.org/abs/2403.12425

Zobrazit plný text záznamu

Report

Exploring Facial Expression Recognition through Semi-Supervised Pretraining and Temporal Modeling

Autor: Yu, Jun, Wei, Zhihong, Cai, Zhongpeng, Zhao, Gongpeng, Zhang, Zerui, Wang, Yongqi, Xie, Guochen, Zhu, Jichao, Zhu, Wangyuan

Facial Expression Recognition (FER) plays a crucial role in computer vision and finds extensive applications across various fields. This paper aims to present our approach for the upcoming 6th Affective Behavior Analysis in-the-Wild (ABAW) competitio

Externí odkaz: http://arxiv.org/abs/2403.11942

Zobrazit plný text záznamu

Report

Efficient Dynamic Allocation Policy for Robust Ranking and Selection under Stochastic Control Framework

Autor: Xiao, Hui, Wei, Zhihong

This research considers the ranking and selection with input uncertainty. The objective is to maximize the posterior probability of correctly selecting the best alternative under a fixed simulation budget, where each alternative is measured by its wo

Externí odkaz: http://arxiv.org/abs/2305.07603

Zobrazit plný text záznamu