Xi Zhou

Xi Zhou

Auto-generated profile, based on publicly available information

Xi Zhou

School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
29 October 2024 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
JWJingjing Wu
Jingjing Wu
XZXi Zhou
Xi Zhou
XLXiaohong Li
Xiaohong Li
HLHao Liu
Hao Liu
MQMeibin Qi
Meibin Qi
RHRichang Hong
Richang Hong
The Infrared Object Tracking (IOT) task aims to locate objects in infrared sequences. Since color and texture information is unavailable in infrared modality, most existing infrared trackers merely rely on capturing spatial contexts from the image to enhance feature representation, where other complementary information is rarely deployed. To fill this gap, we in this article propose a novel Asymmetric Deformable Spatio-Temporal Framework (ADSF) to fully exploit collaborative shape and temporal clues in terms of the objects. Firstly, an asymmetric deformable cross-attention module is designed to extract shape information, which attends to the deformable correlations between distinct frames in an asymmetric manner. Secondly, a spatio-temporal tracking framework is coined to learn the temporal variance trend of the object during the training process and store the template information closest to the tracking frame when testing. Comprehensive experiments demonstrate that ADSF outperforms state-of-the-art methods on three public datasets. Extensive ablation experiments further confirm the effectiveness of each component in ADSF. Furthermore, we conduct generalization validation to demonstrate that the proposed method also achieves performance gains in RGB-based tracking scenarios.

10 June 2024
Verified
Conference Paper
Open access
JWJingjing Wu
Jingjing Wu
YZYunkai Zhang
Yunkai Zhang
XZXi Zhou
Xi Zhou
Shengeng TangShengeng Tang
Shengeng Tang
YWYanyan Wei
Yanyan Wei
Pedestrian recognition, which entails identifying and retrieving a specific pedestrian from an image gallery based on a query, is pivotal for applications such as urban surveillance and autonomous vehicle navigation. This survey provides a detailed overview of person identification, delineating two primary categories based on the query source: person identification with a prescriptive query, which utilizes actual captured images (e.g., RGB or infrared image), and person identification with a descriptive query, which employs non-visual descriptions such as text or sketches. Furthermore, we explore the datasets commonly employed in person re-identification research, which are critical for training and evaluating models under both single-modal and multi-modal scenarios. This comprehensive analysis aims to furnish a deeper understanding of the current state of visual-based person identification, thereby aiding in the advancement of research and development within this field.