Shuyong Gao

Shuyong Gao

Auto-generated profile, based on publicly available information

Shuyong Gao

Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
10 March 2023 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
HXHaozhe Xing
Haozhe Xing
SGShuyong Gao
Shuyong Gao
YWYan Wang
Yan Wang
XWXujun Wei
Xujun Wei
HTHao Tang
Hao Tang
WZWenqiang Zhang
Wenqiang Zhang
Camouflaged Object Detection (COD) aims to detect objects well hidden in the environment. The main challenges of COD come from the high degree of texture and color overlapping between the objects and their surroundings. Inspired by that humans tend to go closer to the object and magnify it to recognize ambiguous objects more clearly, we propose a novel three-stage architecture called Search-Amplify-Recognize and design a network SARNet to address the challenges. Specifically, In the Search part, we utilize an attention-based backbone to locate the object. In the Amplify part, to obtain rich searched features and fine segmentation, we design Object Area Amplification modules (OAA) to perform cross-level and adjacent-level feature fusion and amplifying operations on feature maps. Besides, the OAA can be regarded as a simple and effective plug-in module to integrate and amplify the feature maps. The main components of the Recognize part are the Figure-Ground Conversion modules (FGC). The FGC modules alternately pay attention to the foreground and background to precisely separate the highly similar foreground and background. Extensive experiments on benchmark datasets show that our model outperforms other SOTA methods not only on COD tasks but also in COD downstream tasks, such as polyp segmentation and video camouflaged object detection. Source codes will be available at https://github.com/Haozhe-Xing/SARNet.

17 September 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
LHLingyi Hong
Lingyi Hong
ZLZhongying Liu
Zhongying Liu
WCWenchao Chen
Wenchao Chen
CTChenzhi Tan
Chenzhi Tan
YFYuang Feng
Yuang Feng
WZWenqiang Zhang
Wenqiang Zhang
Video object segmentation (VOS) aims to distinguish and track target objects in a video. Despite the excellent performance achieved by off-the-shelf VOS models, part of the existing VOS benchmarks mainly focuses on short-term videos, where objects remain visible most of the time. However, these benchmarks may not fully capture challenges encountered in practical applications, and the absence of long-term datasets restricts further investigation of VOS in realistic scenarios. Thus, we propose a novel benchmark named LVOS, comprising 720 videos with 296,401 frames and 407,945 high-quality annotations. Videos in LVOS last 1.14 minutes on average. Each video includes various attributes, especially challenges encountered in the wild, such as long-term reappearing and cross-temporal similar objects. Compared to previous benchmarks, our LVOS better reflects VOS models’ performance in real scenarios. Based on LVOS, we evaluate 15 existing VOS models under 3 different settings and conduct a comprehensive analysis. On LVOS, these models suffer a large performance drop, highlighting the challenge of achieving precise tracking and segmentation in real-world scenarios. Attribute-based analysis indicates that one of the significant factors contributing to accuracy decline is the increased video length, interacting with complex challenges such as long-term reappearance, cross-temporal confusion, and occlusion, which emphasize LVOS’s crucial role. We hope our LVOS can advance development of VOS in real scenes.

2 February 2024 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
YWYan Wang
Yan Wang
SYShaoqi Yan
Shaoqi Yan
WSWei Song
Wei Song
ALAntonio Liotta
Antonio Liotta
JLJing Liu
Jing Liu
WZWenqiang Zhang
Wenqiang Zhang
Automatic facial expression recognition (FER) based on face images is essential for affective robots, which are designed for interactive companions and intelligent healthcare. Although existing DL-based FERs have made significant progress, an accurate FER model in robots is challenging due to the subtle differences in facial expressions across various scenarios. To address this issue, we propose a multigranularity region relation representation network (MGR 3 Net) to improve the robustness and generalization of FER via attention-guided global-local fusion. The MGR 3 Net is composed of three modules: multigranularity attention (MGA), holistic-regional feature extractor (HRFE), and hybrid feature fusion. In the MGA module, we first process each holistic cropped face image into three granularity of face regions from coarse to fine, which are four region-cropped faces, $2^{2}$ face partitions, and $4^{2}$ face partitions. Then, we propose the region attention relation cell to model the relationship between each region and the aggregated representation while preserving the spatial information of the local features. In the HRFE module, we align multigranularity features from the coarse space to the finer space and extract one holistic embedding and multiple region embeddings for each granularity. Finally, we use a hybrid-level fusion strategy to combine global-local features from the three granularities for final classification. Extensive experiments demonstrate that the MGR 3 Net outperforms the state-of-the-art methods evaluated on the in-the-lab datasets, in-the-wild datasets, and occlusion/pose-based sets.

29 December 2023 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
QZQing Zhao
Qing Zhao
YWYan Wang
Yan Wang
BWBoyang Wang
Boyang Wang
JLJunxiong Lin
Junxiong Lin
SYShaoqi Yan
Shaoqi Yan
WZWenqiang Zhang
Wenqiang Zhang
Intelligent detection of product surface defects in the industrial scene is the key to ensuring product quality. On general benchmarks, current unsupervised anomaly detection techniques have achieved significant success. When used in complex industrial environments (e.g., large industrial components with small defects), the model needs to be able to adapt to different imaging scenarios (e.g., illumination and resolution) and accurately detect and localize anomalies, but its performance is still far from satisfactory. Besides, the complex and unstable optical lighting environment for collecting such data poses major challenges in establishing unified benchmarks for optical lighting and imaging resolution in defect detection. To fill this gap, we build a standard imaging system-based multiscene unsupervised anomaly detection dataset, coined as MSC-AD. In particular, it provides 12 imaging scenes, i.e., a cross combination of low-to-high three illuminations and 150 × 150 to 600 × 600 four resolutions, in which six types of large casting surfaces with different structures include five kinds of small defects with sample-level and pixel-level precise ground truth. We systematically investigate representative baseline methods and empirical analysis on this dataset to obtain a number of interesting findings, e.g., how to detach from distinctly different imaging scenes, and how to distinguish between subtly normal–anomaly classes. To the best of our knowledge, MSC-AD is the first multi-illumination, multiresolution, multisurface, and multidefect dataset built in a standard imaging system.

16 April 2024 in IEEE Sensors Journal
Verified
Journal Article
Closed access
QWQiShan Wang
QiShan Wang
SGShuyong Gao
Shuyong Gao
LXLi Xiong
Li Xiong
ALAili Liang
Aili Liang
KJKaidong Jiang
Kaidong Jiang
WZWenqiang Zhang
Wenqiang Zhang
Industrial anomaly detection (IAD) algorithms are essential for implementing automated quality inspection. Dataset diversity serves as the foundation for developing comprehensive detection algorithms. Existing IAD datasets focus on the diversity of objects and defects, overlooking the diversity of domains within the real data. To bridge this gap, this study proposes the Casting Surface Defect Detection (CSDD) dataset, containing 12,647 high-resolution gray images and pixel-precise ground truth labels for all defect samples. Compared to existing datasets, CSDD has the following two characteristics: 1.) The target samples are unaligned and have complex and variable context information. 2.) The defects in the CSDD dataset samples are subtle and confusable by factors such as oil contamination, processing features, and machining marks, illustrating the challenge of detecting real casting defects in an industrial context. Based on this dataset, we observe that current state-of-the-art (SOTA) IAD methods face challenges when there is considerable variation in sample context information. Furthermore, these methods encounter difficulties when abnormal samples are scarce, particularly those samples with subtle and confusable defects. To address this issue, we propose a novel method called Realistic Synthetic Anomalies (RSA), which enhances the model’s capacity to construct a normal sample distribution by generating a large number of realistic synthetic anomalies. Experimental results demonstrate that the model trained to classify synthetic anomalies from normal samples achieves the highest accuracy for casting surface defect detection and significantly improves detection accuracy for subtle and confusable defects. The CSDD dataset and code of RSA are available at https://github.com/18894269590/RSA.