CZChenghua Zhu
Chenghua Zhu
*This is an algorithmically generated author record based on publicly available information.
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chenghua Zhu has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Siyan Wu
Aberdeen Institute of Data Science and Artificial Intelligence, South China Normal University, Foshan, China
2 shared publications - Guangyuan Dong
National University of Singapore, Singapore, Singapore
1 shared publication - Guibo Luo
Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen Graduate School, Peking University, Shenzhen, China
1 shared publication - Kehan Jiang
Peking University, Beijing, China
1 shared publication - Lei Wei
Peking University, Beijing, China
1 shared publication - Lei Yang
School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, China
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16190-16198
COMET: Contrastive Motion-Enhanced Temporal Reasoning for Video Multimodal Large Language Models
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16190-16198
Open AccessCOMET: Contrastive Motion-Enhanced Temporal Reasoning for Video Multimodal Large Language Models
- Open Access
- 13 May 2026
- Published by MDPI AG in Agriculture
- Vol. 16 (10) , 1067
D2FNet: A Lightweight Dual-Driven Texture–Semantic Fusion Network for Fine-Grained Real-Time UAV Weed–Crop Detection
Weed–crop object detection in UAV field imagery faces several significant challenges, including a large proportion of small objects, dense occlusions, similar texture appearance, and strong background interference. These challenges often lead to missed detections, localization drift, and unstable training under edge-device budget constraints. To improve detection accuracy while maintaining a practical accuracy–efficiency trade-off in complex farmland scenes, we propose the Dual-Driven Texture–Semantic Fusion Network (D2FNet), consisting of a Texture–Semantic Backbone (TSB), an efficient operator MCF-A2C2f, a cross-scale adaptive fusion and feature redistribution module DSSA-Head, and a scale-aware reweighting block PSBL. TSB reduces discriminative ambiguity caused by similar weed–crop appearance and complex background textures; MCF-A2C2f controls the additional cost of the dual-driven design via lightweight operator substitution while largely preserving per-scale representations; DSSA-Head addresses multi-scale representation inconsistency induced by abundant small objects and large scale variation in field scenes; PSBL downweights low-quality positives by sample quality to stabilize box regression and training. Experimental results show that on the WeedCrop Image Dataset, D2FNet-n improves from 36.6% to 44.1% (+7.5%) over the baseline YOLOv12-n; on the auxiliary Sesame Crop & Weed Dataset, increases from 62.2% to 70.1% (+7.9%). These results indicate that D2FNet achieves stable accuracy gains under comparable parameter and computation budgets, rather than pursuing the smallest absolute model size, and shows promising cross-dataset robustness on the evaluated benchmarks.- 13 May 2026
- Published by MDPI AG in Agriculture
- Vol. 16 (10) , 1067
Open AccessD2FNet: A Lightweight Dual-Driven Texture–Semantic Fusion Network for Fine-Grained Real-Time UAV Weed–Crop Detection
Weed–crop object detection in UAV field imagery faces several significant challenges, including a large proportion of small objects, dense occlusions, similar texture appearance, and strong background interference. These challenges often lead to missed detections, localization drift, and unstable training under edge-device budget constraints. To improve detection accuracy while maintaining a practical accuracy–efficiency trade-off in complex farmland scenes, we propose the Dual-Driven Texture–Semantic Fusion Network (D2FNet), consisting of a Texture–Semantic Backbone (TSB), an efficient operator MCF-A2C2f, a cross-scale adaptive fusion and feature redistribution module DSSA-Head, and a scale-aware reweighting block PSBL. TSB reduces discriminative ambiguity caused by similar weed–crop appearance and complex background textures; MCF-A2C2f controls the additional cost of the dual-driven design via lightweight operator substitution while largely preserving per-scale representations; DSSA-Head addresses multi-scale representation inconsistency induced by abundant small objects and large scale variation in field scenes; PSBL downweights low-quality positives by sample quality to stabilize box regression and training. Experimental results show that on the WeedCrop Image Dataset, D2FNet-n improves from 36.6% to 44.1% (+7.5%) over the baseline YOLOv12-n; on the auxiliary Sesame Crop & Weed Dataset, increases from 62.2% to 70.1% (+7.9%). These results indicate that D2FNet achieves stable accuracy gains under comparable parameter and computation budgets, rather than pursuing the smallest absolute model size, and shows promising cross-dataset robustness on the evaluated benchmarks.