Ding Yuan

Dr. Ding Yuan


Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
13 July 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
YLYixuan Lyu
Yixuan Lyu
HZHong Zhang
Hong Zhang
YLYan Li
Yan Li
HLHanyang Liu
Hanyang Liu
YYYifan Yang
Yifan Yang
DYDing Yuan
Ding Yuan
According to Darwinian evolutionary theory, numerous species in the wild have developed remarkable adaptive mechanisms, involving pattern rearrangement and environmental assimilation, to evade predators. These obfuscation strategies pose significant challenges for both individuals and algorithms when performing the Camouflage Object Detection (COD) task in complex and intricate scenarios. Inspired by human strategies in the COD task, which involve assigning uncertainties to the entire input and then focusing on highly uncertain areas with the aid of prior knowledge such as boundary information, we propose the Uncertainty-Edge Dual Guide (UEDG) architecture. UEDG effectively combines probabilistic-derived uncertainty and deterministic-derived edge information to accurately detect concealed objects. The architecture consists of two independent branches dedicated to uncertainty reasoning and edge inference, which are subsequently integrated into a feature fusion module utilizing recursion feedback and feature-reuse techniques. This novel COD framework leverages the benefits of Bayesian learning and convolution-based learning, resulting in a powerful multi-task guided approach. Extensive experiments conducted on four widely employed datasets demonstrate the superior performance of UEDG compared to 12 state-of-the-art approaches, while maintaining an acceptable level of computational complexity. Overall, UEDG presents a promising solution for addressing the challenges of COD in complex environments by combining evolutionary-inspired strategies with advanced computer vision techniques. The code will be available at: https://github.com/lyu-yx/UEDG.git

1 February 2016 in Neurocomputing
Verified
Journal Article
Closed access
MXMiao Xin
Miao Xin
HZHong Zhang
Hong Zhang
HWHelong Wang
Helong Wang
MSMingui Sun
Mingui Sun
DYDing Yuan
Ding Yuan

31 January 2023 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
CYChaoqi Yan
Chaoqi Yan
HZHong Zhang
Hong Zhang
XLXuliang Li
Xuliang Li
YYYifan Yang
Yifan Yang
DYDing Yuan
Ding Yuan

1 July 2015 in Pattern Recognition
Verified
Journal Article
Closed access
FCFeiyang Cheng
Feiyang Cheng
HZHong Zhang
Hong Zhang
MSMingui Sun
Mingui Sun
DYDing Yuan
Ding Yuan

14 January 2022 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
CYChaoqi Yan
Chaoqi Yan
HZHong Zhang
Hong Zhang
XLXuliang Li
Xuliang Li
DYDing Yuan
Ding Yuan

18 November 2020 in IEEE Access
Verified
Journal Article
Open access
YWYujie Wu
Yujie Wu
HZHong Zhang
Hong Zhang
YLYawei Li
Yawei Li
YYYifan Yang
Yifan Yang
DYDing Yuan
Ding Yuan
In recent years, the excellent image-based object detection algorithms are transferred to the video object detection directly. These frame-by-frame processing methods are suboptimal owing to the degenerate object appearance such as motion blur, defocus and rare poses. The existing works for video object detection mostly focus on the feature aggregation at pixel level and instance level, but the blur impact in the aggregation process has not been exploited well so far. In this paper, we propose an end-to-end blur-aid feature aggregation network (BFAN) for video object detection. The proposed BFAN focuses on the aggregation process influenced by the blur including motion blur and defocus with high accuracy and little increased computation. In BFAN, we evaluate the object blur degree of each frame as the weight for aggregation. Noteworthy, the background is usually flat which has a negative impact on the object blur degree evaluation. Therefore, we introduce a light saliency detection network to alleviate the background interference. The experiments conducted on the ImageNet VID dataset show that BFAN achieves the state-of-the-art detection performance, exactly 79.1% mAP, with 3 points improvement compared to the video object detection baseline.