Yuxiang Xie

Dr. Yuxiang Xie


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
15 September 2022 in International Journal of Multimedia Information Retrieval
Verified
Journal Article
Closed access
PDF file
YXYuxiang Xie
Yuxiang Xie
JYJie Yan
Jie Yan
LKLai Kang
Lai Kang
YGYanming Guo
Yanming Guo
JZJiahui Zhang
Jiahui Zhang
XLXidao LUAN
Xidao LUAN

10 February 2024 in Complex & Intelligent Systems
Verified
Journal Article
Open access
PDF file
JYJie Yan
Jie Yan
YXYuxiang Xie
Yuxiang Xie
YGYanming Guo
Yanming Guo
YWYingmei Wei
Yingmei Wei
XLXidao LUAN
Xidao LUAN
Nowadays, Artificial Intelligence Generated Content (AIGC) has shown promising prospects in both computer vision and natural language processing communities. Meanwhile, as an essential aspect of AIGC, image to captions has received much more attention. Recent vision-language research is developing from the bulky region visual representations based on object detectors toward more convenient and flexible grid ones. However, this kind of research typically concentrates on image understanding tasks like image classification, with less attention paid to content generation tasks. In this paper, we explore how to capitalize on the expressive features embedded in the grid visual representations for better image captioning. To this end, we present a Transformer-based image captioning model, dubbed FeiM, with two straightforward yet effective designs. We first design the feature queries that consist of a limited set of learnable vectors, which act as the local signals to capture specific visual information from global grid features. Then, taking augmented global grid features and the local feature queries as inputs, we develop a feature interaction module to query relevant visual concepts from grid features, and to enable interaction between the local signal and overall context. Finally, the refined grid visual representations and the linguistic features pass through a Transformer architecture for multi-modal fusion. With the two novel and simple designs, FeiM can fully leverage meaningful visual knowledge to improve image captioning performance. Extensive experiments are performed on the competitive MSCOCO benchmark to confirm the effectiveness of the proposed approach, and the results show that FeiM yields more eminent results than existing advanced captioning models.

23 March 2022 in International Journal of Multimedia Information Retrieval
Verified
Journal Article
Closed access
PDF file
JYJie Yan
Jie Yan
YXYuxiang Xie
Yuxiang Xie
XLXidao LUAN
Xidao LUAN
YGYanming Guo
Yanming Guo
QGQuanzhi Gong
Quanzhi Gong
SFSuru Feng
Suru Feng

14 July 2025 in International Journal of Multimedia Information Retrieval
Verified
Journal Article
Closed access
PDF file
Shi wei ZouShi wei Zou
Shi wei Zou
YWYingmei Wei
Yingmei Wei
YXYuxiang Xie
Yuxiang Xie
MLMingrui Lao
Mingrui Lao
XLXidao LUAN
Xidao LUAN

23 August 2023 in International Journal of Multimedia Information Retrieval
Verified
Journal Article
Closed access
PDF file
JYJie Yan
Jie Yan
YXYuxiang Xie
Yuxiang Xie
YGYanming Guo
Yanming Guo
YWYingmei Wei
Yingmei Wei
XZXiaoping Zhang
Xiaoping Zhang
XLXidao LUAN
Xidao LUAN

28 May 2013 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
YXYuxiang Xie
Yuxiang Xie
XZXiao-Ping Zhang
Xiao-Ping Zhang
XLXidao Luan
Xidao Luan
LLLi Liu
Li Liu
XZXin Zhang
Xin Zhang