Haoxiang Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Haoxiang Zhang has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Deqiang Cheng
School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China
7 shared publications - He Jiang
School of Mines, China University of Mining and Technology, Xuzhou 221116, China
7 shared publications - Qiqi Kou
School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China
6 shared publications - Ping Zheng
China University of Mining and Technology
2 shared publications - Feixiang Xu
China University of Mining and Technology
1 shared publication - Gaoting Cao
Beijing Institute of Technology
1 shared publication
Latest Publications
- 5 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (4) , 4419-4432
Triple-Way Visual Modulation for Zero-Shot Sketch-Based Image Retrieval
Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) seeks to correlate unseen hand-drawn sketches with unseen real images by leveraging trained models on visible categories. Recent CLIP-based models, which primarily focus on visual-textual interaction, have demonstrated strong competitiveness in ZS-SBIR. However, they still fall short in the exploration of cross-modal visual representations, especially in terms of cross-modal visual shared and specific information. Differing from the aforementioned researches, we start with class-level, prompt-level, and patch-level visual information, committed to unlocking the potential of visual feature representation. On this foundation, we introduce the vision-centric Triple-way visual modulATion (TAT) framework to enhance the model’s perception of visual shared and specific information. Specifically, we establish unified multi-modal perception by integrating visual-level modality prompter into the CLIP architecture. We then conduct triple-way modulation modeling on prompt, token, and patch levels to effectively mine shared and specific features. Lastly, we develop an enhanced calibration strategy incorporating prompt-aware, token-aware, and logit-aware alignment modules to amplify the model’s proficiency in probing shared-specific features. We thoroughly test our approach to confirm its excellence and the efficacy of individual components. The comparison results on the popular datasets Sketchy, Sketchyv2, Tuberlin, and QuickDraw show that the developed algorithm significantly surpasses the current state-of-the-art technologies.
- 5 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (4) , 4419-4432
Triple-Way Visual Modulation for Zero-Shot Sketch-Based Image Retrieval
Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) seeks to correlate unseen hand-drawn sketches with unseen real images by leveraging trained models on visible categories. Recent CLIP-based models, which primarily focus on visual-textual interaction, have demonstrated strong competitiveness in ZS-SBIR. However, they still fall short in the exploration of cross-modal visual representations, especially in terms of cross-modal visual shared and specific information. Differing from the aforementioned researches, we start with class-level, prompt-level, and patch-level visual information, committed to unlocking the potential of visual feature representation. On this foundation, we introduce the vision-centric Triple-way visual modulATion (TAT) framework to enhance the model’s perception of visual shared and specific information. Specifically, we establish unified multi-modal perception by integrating visual-level modality prompter into the CLIP architecture. We then conduct triple-way modulation modeling on prompt, token, and patch levels to effectively mine shared and specific features. Lastly, we develop an enhanced calibration strategy incorporating prompt-aware, token-aware, and logit-aware alignment modules to amplify the model’s proficiency in probing shared-specific features. We thoroughly test our approach to confirm its excellence and the efficacy of individual components. The comparison results on the popular datasets Sketchy, Sketchyv2, Tuberlin, and QuickDraw show that the developed algorithm significantly surpasses the current state-of-the-art technologies.
- 4 December 2025
- Published by Springer Nature in Multimedia Systems
- Vol. 32 (1) , 9
Dual-consistency framework for cross-domain zero-shot image retrieval via prompt reconstruction and semantic mining
- 4 December 2025
- Published by Springer Nature in Multimedia Systems
- Vol. 32 (1) , 9
Dual-consistency framework for cross-domain zero-shot image retrieval via prompt reconstruction and semantic mining
- 4 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
Zero-Shot Detection Based on Dual-Task Balancing
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.
- 4 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
Zero-Shot Detection Based on Dual-Task Balancing
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
- Published by Springer Nature
- p. 590-601
Single Image Super Resolution Based on Dual-Path Large Kernel Learning
- 26 April 2024
- Published by Springer Nature
- p. 590-601
Single Image Super Resolution Based on Dual-Path Large Kernel Learning
- 26 April 2024
- Published by Springer Nature
- p. 602-615
Denoising Real-World Low Light Surveillance Videos Based on Trilateral Filter
- 26 April 2024
- Published by Springer Nature
- p. 602-615
Denoising Real-World Low Light Surveillance Videos Based on Trilateral Filter
- 19 February 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (31) , 76905-76934
Intermediate-term memory mechanism inspired lightweight single image super resolution
- 19 February 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (31) , 76905-76934
Intermediate-term memory mechanism inspired lightweight single image super resolution
- 13 February 2024
- Published by Elsevier in Advanced Engineering Informatics
- Vol. 60
Indicative Vision Transformer for end-to-end zero-shot sketch-based image retrieval
- 13 February 2024
- Published by Elsevier in Advanced Engineering Informatics
- Vol. 60
Indicative Vision Transformer for end-to-end zero-shot sketch-based image retrieval
- 12 December 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (19) , 57811-57828
Task-like training paradigm in CLIP for zero-shot sketch-based image retrieval
- 12 December 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (19) , 57811-57828
Task-like training paradigm in CLIP for zero-shot sketch-based image retrieval