Haoxiang Zhang

Haoxiang Zhang

Auto-generated profile, based on publicly available information

Haoxiang Zhang

School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
13 February 2024 in Advanced Engineering Informatics
Verified
Journal Article
Closed access
HZHaoxiang Zhang
Haoxiang Zhang
DCDeqiang Cheng
Deqiang Cheng
QKQiqi Kou
Qiqi Kou
MAMujtaba Asad
Mujtaba Asad
HJHe Jiang
He Jiang

12 December 2023 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
HZHaoxiang Zhang
Haoxiang Zhang
DCDeqiang Cheng
Deqiang Cheng
HJHe Jiang
He Jiang
JLJingjing Liu
Jingjing Liu
QKQiqi Kou
Qiqi Kou

19 February 2024 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
DCDeqiang Cheng
Deqiang Cheng
YWYuze Wang
Yuze Wang
HZHaoxiang Zhang
Haoxiang Zhang
LLLong Li
Long Li
QKQiqi Kou
Qiqi Kou
HJHe Jiang
He Jiang

4 April 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
DCDeqiang Cheng
Deqiang Cheng
XXXingchen Xu
Xingchen Xu
HZHaoxiang Zhang
Haoxiang Zhang
HJHe Jiang
He Jiang
JQJiansheng Qian
Jiansheng Qian
QKQiqi Kou
Qiqi Kou
Zero-shot object detection (ZSD), which aims to detect unseen objects, has garnered significant attention due to its potential for expanding the range of detectable classes via textual extensions. However, current methods often directly adapt techniques from Zero-Shot Learning (ZSL), overlooking the unique challenges of ZSD, particularly the need to simultaneously address classification and localization tasks. In this paper, we identify classification as the primary bottleneck in ZSD and propose two novel strategies to address it. First, from a visual instrumentation perspective, we introduce decoupled and dynamic detection heads to enhance classification performance, along with a novel adaptive branch learning network that selectively processes relevant information for classification. Second, to mitigate modality differences caused by data collection and measurement discrepancies, we integrate a cross-modal alignment module with a contrastive embedding loss, which improves the projection matrix of the classification branch and enables more robust adaptive learning. Extensive experiments on three standard datasets (COCO, ILSVRC, and Visual Genome) demonstrate that our approach significantly outperforms both vanilla and state-of-the-art zero-shot detectors in test accuracy.

26 April 2024
Verified
Book Chapter
Closed access
PDF file
HJHe Jiang
He Jiang
GLGui Liu
Gui Liu
GCGaoting Cao
Gaoting Cao
PZPing Zheng
Ping Zheng
HZHaoxiang Zhang
Haoxiang Zhang
DCDeqiang Cheng
Deqiang Cheng

4 December 2025 in Multimedia Systems
Verified
Journal Article
Closed access
PDF file
HZHaoxiang Zhang
Haoxiang Zhang
RZRui Zhang
Rui Zhang
HJHe Jiang
He Jiang
DCDeqiang Cheng
Deqiang Cheng
QKQiqi Kou
Qiqi Kou