5 papers
An End-to-End Framework for Video Multi-Person Pose Estimation
Zhihong Wei
Video-based human pose estimation models aim to address scenarios that cannot be effectively solved by static image models such as motion blur, out-of-focus and occlusion. Most exi…
AUD-TGN: Advancing Action Unit Detection with Temporal Convolution and GPT-2 in Wild Audiovisual Contexts
Jun Yu, Zerui Zhang, Zhihong Wei +6
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 in…
Multimodal Fusion Method with Spatiotemporal Sequences and Relationship Learning for Valence-Arousal Estimation
Jun Yu, Gongpeng Zhao, Yongqi Wang +7
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 seg…
Exploring Facial Expression Recognition through Semi-Supervised Pretraining and Temporal Modeling
Jun Yu, Zhihong Wei, Zhongpeng Cai +6
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…
Efficient Feature Extraction and Late Fusion Strategy for Audiovisual Emotional Mimicry Intensity Estimation
Jun Yu, Wangyuan Zhu, Jichao Zhu
In this paper, we present the solution to the Emotional Mimicry Intensity (EMI) Estimation challenge, which is part of 6th Affective Behavior Analysis in-the-wild (ABAW) Competitio…