Author name cluster

Yan Gong

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

EAAI Journal 2026 Journal Article

Seismic fragility assessment of curved girder bridges under vehicle-induced risks: A specialized deep learning-based neural network approach

Wei-zuo Guo
Wei-you Guo
Yan Gong
Shu-mao Qiu

The special horizontal alignment of curved girder bridges often leads to higher seismic demands than those of straight bridges, resulting in greater seismic fragility. With the continuing growth in transportation and logistics demand, the likelihood of heavy vehicles being stranded on bridges during earthquakes further increases, amplifying the seismic risk of curved girder bridges. However, existing data-driven seismic fragility assessment methods generally neglect the additional risks introduced by vehicle loads. Therefore, this study develops a specialized deep learning model—the seismic fragility embedding neural network under vehicle-induced risks for curved girder bridges (SFENR)—to assess their seismic fragility under combined vehicle–earthquake effects. An automated parametric finite element (APFE) program is developed to efficiently simulate the vehicle–curved girder bridge system and batch-produce nonlinear dynamic responses, thereby providing essential data support for training the SFENR model. A case study is then conducted on a typical three-span continuous curved box girder bridge to systematically investigate how vehicles with different weights and positions affect the seismic fragility of bridge components. The results demonstrate that the proposed SFENR model substantially outperforms conventional neural networks in terms of both memory efficiency and prediction accuracy. Specifically, the SFENR achieves a nearly 50% reduction in memory usage while improving Accuracy by 2–10%, with both Precision and Recall consistently maintained above 70%. Furthermore, the fragility curves of structural components exhibit greater sensitivity to variations in the tangential rather than radial positions of vehicles on the bridge deck. The presence of vehicles induces a non-monotonic effect on the seismic fragility of curved girder bridges—meaning that vehicles increase fragility at lower ground motion intensities but reduce it at higher intensities. This highlights the importance of considering vehicle effects in seismic risk evaluation and advances the development of more reliable fragility assessment for highway bridges.

Details DOI

NeurIPS Conference 2025 Conference Paper

RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers

Yan Gong
Yiren Song
Yicheng Li
Chenglin Li
Yin Zhang

Inspired by the in-context learning mechanism of large language models (LLMs), a new paradigm of generalizable visual prompt-based image editing is emerging. Existing single-reference methods typically focus on style or appearance adjustments and struggle with non-rigid transformations. To address these limitations, we propose leveraging source-target image pairs to extract and transfer content-aware editing intent to novel query images. To this end, we introduce RelationAdapter, a lightweight module that enables Diffusion Transformer (DiT) based models to effectively capture and apply visual transformations from minimal examples. We also introduce Relation252K, a comprehensive dataset comprising 218 diverse editing tasks, to evaluate model generalization and adaptability in visual prompt-driven scenarios. Experiments on Relation252K show that RelationAdapter significantly improves the model’s ability to understand and transfer editing intent, leading to notable gains in generation quality and overall editing performance.

PDF Details

EAAI Journal 2024 Journal Article

GLMDriveNet: Global–local Multimodal Fusion Driving Behavior Classification Network

Wenzhuo Liu
Yan Gong
Guoying Zhang
Jianli Lu
Yunlai Zhou
Junbin Liao

Driving behavior classification plays an important role in many fields, such as Advanced Driving Assistance System (ADAS), traffic safety, and energy saving. In this paper, we propose a Global–local Multimodal Fusion Driving Behavior Classification Network (GLMDriveNet) which classifies driver behaviors into normal driving, aggressive driving, and drowsy driving. First of all, we design a Global–local Interaction Channel Attention Module (GLI-CAM) to extract effective features in both the roadside image and the spectrogram generated from the current prediction time and its previous four seconds of vehicle speeds. Furthermore, a learnable positional embedding is introduced to fuse the global and local information of the channels for better screening of the extracted features. Secondly, we propose a Multi-scale Feature Representation Fusion Module (MS-FRFM) to associate the high-scale and low-scale information of images and spectrograms and assign different importances for different modal information, making the network more inclined to useful modal information. Our model is evaluated on a public dataset UAH-DriveSet and achieves the best performance (98. 4% F1-score on all roads, 97. 4% F1-score on the motorway road, and 99. 8% F1-score on the secondary road) compared to other state-of-the-art methods. Our model has a very fast speed (142 FPS) and strong generalization which has been verified through extensive experiments on multiple datasets. The code is available on https: //github. com/liuwenzhuo1/GLMDrivenet.

Details DOI

AIIM Journal 2020 Journal Article

Speckle reduction of OCT via super resolution reconstruction and its application on retinal layer segmentation

Qifeng Yan
Bang Chen
Yan Hu
Jun Cheng
Yan Gong
Jianlong Yang
Jiang Liu
Yitian Zhao

Optical coherence tomography (OCT) is a rapidly developing non-invasive three dimensional imaging approach, and it has been widely used in examination and diagnosis of eye diseases. However, speckle noise are often inherited from image acquisition process, and may obscure the anatomical structure, such as the retinal layers. In this paper, we propose a novel method to reduce the speckle noise in 3D OCT scans, by introducing a new super-resolution approach. It uses a multi-frame fusion mechanism that merges multiple scans for the same scene, and utilizes the movements of sub-pixels to recover missing signals in one pixel, which significantly improves the image quality. To evaluate the effectiveness of the proposed speckle noise reduction method, we have applied it for the application of retinal layer segmentation. Results show that the proposed method has produced promising enhancement performance, and enable deep learning-based methods to obtain more accurate retinal layer segmentation results.

Details DOI