Fudong Nian
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Fudong Nian has a total of 63 co-authors. Here are the top co-authors by number of shared publications:
Teng Li
4 shared publicationsGang Lv
Chizhou University
3 shared publications- Teng Li
School of Artificial Intelligence, Anhui University, Hefei, China
3 shared publications Yanhong Gu
The School of Electronic Information and Automation Hefei University Hefei China
3 shared publications- Gang Lv
Hefei University
2 shared publications Jingjing Zhang
School of Electrical Engineering and Automation Anhui University Hefei Anhui China
2 shared publications
Latest Publications
- 21 September 2026
- Published by Springer Nature in Multimedia Systems
- Vol. 32 (9) , 598
Evidence-grounded multimodal mining of fine-grained research problems and methods from computer vision papers
- 21 September 2026
- Published by Springer Nature in Multimedia Systems
- Vol. 32 (9) , 598
Evidence-grounded multimodal mining of fine-grained research problems and methods from computer vision papers
- 29 October 2025
- Published by Royal Society of Chemistry (RSC) in Journal of Analytical Atomic Spectrometry
- Vol. 40 (11) , 3280-3293
Semi-supervised graph learning for spatial mapping of heavy metal concentrations in smelter-adjacent soils using a mobile LIBS device
This study employs a multi-task deep learning model based on GraphSAGE within a teacher–student semi-supervised framework to predict heavy metal concentrations in soils around smelters, reducing the demand for labeled data and enhancing accuracy.
- 29 October 2025
- Published by Royal Society of Chemistry (RSC) in Journal of Analytical Atomic Spectrometry
- Vol. 40 (11) , 3280-3293
Semi-supervised graph learning for spatial mapping of heavy metal concentrations in smelter-adjacent soils using a mobile LIBS device
This study employs a multi-task deep learning model based on GraphSAGE within a teacher–student semi-supervised framework to predict heavy metal concentrations in soils around smelters, reducing the demand for labeled data and enhancing accuracy.
- 17 February 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 172
Domain Adaptation via Feature Disentanglement for cross-domain image classification
- 17 February 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 172
Domain Adaptation via Feature Disentanglement for cross-domain image classification
- Open Access
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 19 (1)
DCMCF: Dynamic Cross‐Modal Context Fusion for Image‐Based Person Search
Image‐based person search, which locates and identifies a query person from uncropped gallery images, remains challenging due to occlusions, viewpoint changes, and ambiguous appearances. While existing methods increasingly leverage visual context, they are fundamentally limited by static fusion strategies for multi‐view features and their neglect of semantic context from other modalities. To overcome these limitations, we propose the dynamic cross‐modal context fusion (DCMCF) framework, which establishes a core multi‐modal fusion architecture by explicitly leveraging self‐generated textual descriptions to provide semantics‐driven matching guidance. DCMCF consists of three core components: (1) multi‐modal feature extraction, which employs an enhanced multi‐view visual encoder with dynamic gating and a zero‐shot pipeline using pre‐trained VLMs to generate multi‐level textual descriptions from images; (2) a dynamic cross‐modal fusion (DCMF) module, which hierarchically and adaptively fuses the visual and textual features through cross‐modal attention and input‐dependent gating; and (3) a text‐guided inter‐image group context ranking (T‐IGCR) algorithm, which refines retrieval results by measuring holistic image consistency in both visual and textual spaces. Experiments on CUHK‐SYSU and PRW datasets demonstrate state‐of‐the‐art performance, achieving 96.9%/97.3% (mAP/top‐1) and 56.1%/91.2% , respectively. This work demonstrates the significant potential of dynamic cross‐modal context fusion for advancing image‐based person search.
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 19 (1)
Open AccessDCMCF: Dynamic Cross‐Modal Context Fusion for Image‐Based Person Search
Image‐based person search, which locates and identifies a query person from uncropped gallery images, remains challenging due to occlusions, viewpoint changes, and ambiguous appearances. While existing methods increasingly leverage visual context, they are fundamentally limited by static fusion strategies for multi‐view features and their neglect of semantic context from other modalities. To overcome these limitations, we propose the dynamic cross‐modal context fusion (DCMCF) framework, which establishes a core multi‐modal fusion architecture by explicitly leveraging self‐generated textual descriptions to provide semantics‐driven matching guidance. DCMCF consists of three core components: (1) multi‐modal feature extraction, which employs an enhanced multi‐view visual encoder with dynamic gating and a zero‐shot pipeline using pre‐trained VLMs to generate multi‐level textual descriptions from images; (2) a dynamic cross‐modal fusion (DCMF) module, which hierarchically and adaptively fuses the visual and textual features through cross‐modal attention and input‐dependent gating; and (3) a text‐guided inter‐image group context ranking (T‐IGCR) algorithm, which refines retrieval results by measuring holistic image consistency in both visual and textual spaces. Experiments on CUHK‐SYSU and PRW datasets demonstrate state‐of‐the‐art performance, achieving 96.9%/97.3% (mAP/top‐1) and 56.1%/91.2% , respectively. This work demonstrates the significant potential of dynamic cross‐modal context fusion for advancing image‐based person search.
- Open Access
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 19 (1)
Dual‐Branch Enhancement and Multi‐Modal Fusion for Low‐Light Visible Polarization Image Object Detection in Dense Smog Environments
In scenarios with heavy smog, the accuracy of object detection in low‐light visible polarization images significantly decreases. To address this issue, we propose a dual‐branch enhancement and multi‐modal fusion network for object detection in low‐light visible polarization images in dense smog environments. Specifically, the network consists of an image enhancement stage and an object detection stage. In the image enhancement stage, a dual‐branch enhancement structure comprising greyscale feature map prediction and atmospheric light transmission network is proposed to remove noise from the images and enhance texture information, jointly generating enhanced visible polarization images. In the object detection stage, feature maps of the enhanced visible polarization images and the degree of visible polarization images are fused, and their fused texture‐enhanced feature maps are fed into the detection module for object detection. Additionally, we have collected a dataset of low‐light visible polarization images under real smog conditions. Extensive experiments demonstrate that our method can generate visually improved enhanced images and significantly increase detection accuracy and the number of detected objects in low‐light and dense smog environments.
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 19 (1)
Open AccessDual‐Branch Enhancement and Multi‐Modal Fusion for Low‐Light Visible Polarization Image Object Detection in Dense Smog Environments
In scenarios with heavy smog, the accuracy of object detection in low‐light visible polarization images significantly decreases. To address this issue, we propose a dual‐branch enhancement and multi‐modal fusion network for object detection in low‐light visible polarization images in dense smog environments. Specifically, the network consists of an image enhancement stage and an object detection stage. In the image enhancement stage, a dual‐branch enhancement structure comprising greyscale feature map prediction and atmospheric light transmission network is proposed to remove noise from the images and enhance texture information, jointly generating enhanced visible polarization images. In the object detection stage, feature maps of the enhanced visible polarization images and the degree of visible polarization images are fused, and their fused texture‐enhanced feature maps are fed into the detection module for object detection. Additionally, we have collected a dataset of low‐light visible polarization images under real smog conditions. Extensive experiments demonstrate that our method can generate visually improved enhanced images and significantly increase detection accuracy and the number of detected objects in low‐light and dense smog environments.
- 7 November 2024
- Published by Springer Nature
- p. 32-46
Swelling-ViT: Rethink Data-Efficient Vision Transformer from Locality
- 7 November 2024
- Published by Springer Nature
- p. 32-46
Swelling-ViT: Rethink Data-Efficient Vision Transformer from Locality
- 1 November 2024
- Published by Elsevier in Pattern Recognition
- Vol. 159
Local and global self-attention enhanced graph convolutional network for skeleton-based action recognition
- 1 November 2024
- Published by Elsevier in Pattern Recognition
- Vol. 159
Local and global self-attention enhanced graph convolutional network for skeleton-based action recognition
- 14 August 2024
- Published by Springer Nature
- p. 298-310
Fine-Grained Cross-Modal Contrast Learning for Video-Text Retrieval
- 14 August 2024
- Published by Springer Nature
- p. 298-310
Fine-Grained Cross-Modal Contrast Learning for Video-Text Retrieval
- 1 July 2024
- Published by Elsevier in Digital Signal Processing
- Vol. 153
Ingredient-guided multi-modal interaction and refinement network for RGB-D food nutrition assessment
- 1 July 2024
- Published by Elsevier in Digital Signal Processing
- Vol. 153
Ingredient-guided multi-modal interaction and refinement network for RGB-D food nutrition assessment
- Open Access
- 17 May 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (10) , 1562
CC-DETR: DETR with Hybrid Context and Multi-Scale Coordinate Convolution for Crowd Counting
Prevailing crowd counting approaches primarily rely on density map regression methods. Despite wonderful progress, significant scale variations and complex background interference within the same image remain challenges. To address these issues, in this paper we propose a novel DETR-based crowd counting framework called Crowd Counting DETR (CC-DETR), which aims to extend the state-of-the-art DETR object detection framework to the crowd counting task. In CC-DETR, a DETR-like encoder–decoder structure (Hybrid Context DETR, i.e., HCDETR) is proposed to tackle complex visual information by fusing features from hybrid semantic levels through a transformer. In addition, we design a Coordinate Dilated Convolution Module (CDCM) to effectively employ position-sensitive context information in different scales. Extensive experiments on three challenging crowd counting datasets (ShanghaiTech, UCF-QNRF, and NWPU) demonstrate that our model is effective and competitive when compared against SOTA crowd counting models.
- 17 May 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (10) , 1562
Open AccessCC-DETR: DETR with Hybrid Context and Multi-Scale Coordinate Convolution for Crowd Counting
Prevailing crowd counting approaches primarily rely on density map regression methods. Despite wonderful progress, significant scale variations and complex background interference within the same image remain challenges. To address these issues, in this paper we propose a novel DETR-based crowd counting framework called Crowd Counting DETR (CC-DETR), which aims to extend the state-of-the-art DETR object detection framework to the crowd counting task. In CC-DETR, a DETR-like encoder–decoder structure (Hybrid Context DETR, i.e., HCDETR) is proposed to tackle complex visual information by fusing features from hybrid semantic levels through a transformer. In addition, we design a Coordinate Dilated Convolution Module (CDCM) to effectively employ position-sensitive context information in different scales. Extensive experiments on three challenging crowd counting datasets (ShanghaiTech, UCF-QNRF, and NWPU) demonstrate that our model is effective and competitive when compared against SOTA crowd counting models.