Lei Wang

Dr. Lei Wang

orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 August 2021 in Expert Systems
Verified
Journal Article
Closed access
PDF file
ZLZefeng Lai
Zefeng Lai
LWLei Wang
Lei Wang
QLQiang Ling
Qiang Ling

29 August 2024 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
YJYu Jun
Yu Jun
ZCZhongpeng Cai
Zhongpeng Cai
YLYihao Li
Yihao Li
LWLei Wang
Lei Wang
Fang GaoFang Gao
Fang Gao
YYYe Yu
Ye Yu
This paper focuses on the advancement of single object tracking technologies in computer vision, which have broad applications including robotic vision, video surveillance, and sports video analysis. Current methods relying solely on the target's initial visual information encounter performance bottlenecks and limited applications, due to the scarcity of target semantics in appearance features and the continuous change in the target's appearance. To address these issues, we propose a novel approach, combining visual-language dual-modal single object tracking, that leverages natural language descriptions to enrich the semantic information of the moving target. We introduce a dual-modal single-object tracking algorithm based on local correspondence modeling. The algorithm decomposes visual features into multiple local visual semantic features and pairs them with local language features extracted from natural language descriptions. In addition, we also propose a new global relocalization method that utilizes visual language bimodal information to perceive target disappearance and misalignment and adaptively reposition the target in the entire image. This improves the tracker's ability to adapt to changes in target appearance over long periods of time, enabling long-term single target tracking based on bimodal semantic and motion information. Experimental results show that our model outperforms stateof-the-art methods, which demonstrates the effectiveness and efficiency of our approach


17 December 2022
Verified
Book Chapter
Closed access
PDF file
ZLZhiwei Liang
Zhiwei Liang
LLLei Li
Lei Li
LWLei Wang
Lei Wang


13 March 2025 in arXiv
Verified
Preprint
Open access
PDF file
JYJun Yu
Jun Yu
YWYongqi Wang
Yongqi Wang
LWLei Wang
Lei Wang
YZYang Zheng
Yang Zheng
SXShengfan Xu
Shengfan Xu
This paper presents our method for the estimation of valence-arousal (VA) in the 8th Affective Behavior Analysis in-the-Wild (ABAW) competition. Our approach integrates visual and audio information through a multimodal framework. The visual branch uses a pre-trained ResNet model to extract spatial features from facial images. The audio branches employ pre-trained VGG models to extract VGGish and LogMel features from speech signals. These features undergo temporal modeling using Temporal Convolutional Networks (TCNs). We then apply cross-modal attention mechanisms, where visual features interact with audio features through query-key-value attention structures. Finally, the features are concatenated and passed through a regression layer to predict valence and arousal. Our method achieves competitive performance on the Aff-Wild2 dataset, demonstrating effective multimodal fusion for VA estimation in-the-wild.