Shang-You Zeng

Shang-You Zeng

Auto-generated profile, based on publicly available information

Shang-You Zeng

Guangxi Normal University, Guilin, Guangxi, China

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
1 January 2013 in Chinese Physics B
Verified
Journal Article
Open access
WNWei-Lian Ning
Wei-Lian Ning
ZZZheng-Zhen Zhang
Zheng-Zhen Zhang
SZShang-You Zeng
Shang-You Zeng
XLXiao-Shu Luo
Xiao-Shu Luo
JHJin-Lin Hu
Jin-Lin Hu
HWHuisi Wu
Huisi Wu

13 September 2024
Verified
Conference Paper
Open access
XLXianda Liang
Xianda Liang
SZShangyou Zeng
Shangyou Zeng
HQHongyu Qiu
Hongyu Qiu
In image captioning, methods that generate descriptions by extracting regional visual features often overlook the rich contextual information and details contained in grid features. Additionally, Transformer models have some limitations in distinguishing between visual and non-visual vocabulary. To address these issues, this paper proposes a Transformer-based multi-feature fusion approach for image captioning. The model employs a bidirectional encoder to extract intrinsic features from both grid and regional features, and constructs a multi-level perception enhancement module to leverage semantic information from different encoder levels. Furthermore, at the feature fusion stage, this paper introduces a multi-visual feature fusion module that effectively resolves the semantic noise problem arising from multi-feature fusion. Lastly, to differentiate between visual and non-visual words, the paper also establishes a Transformer-based language model to extract semantic features. Through a dynamic attention mechanism, it adaptively captures the correlations between visual and lexical elements, guiding the generation of image descriptions. The proposed method is trained on the MS-COCO dataset and quantitatively compared with existing approaches. Experimental results demonstrate that this method can generate more accurate and richer image descriptions.