Author name cluster

Shanshan Li

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.

6 papers

1 author row

JBHI Journal 2026 Journal Article

MBE-UNet: Multi-Branch Boundary Enhanced U-Net for Ultrasound Segmentation

Qing Qin
Ziwei Lin
Guangyuan Gao
Chunxiao Han
Ruofan Wang
Yingmei Qin
Shanshan Li
Shan An

Accurately capturing object areas in medical images is crucial for the clinical diagnosis and treatment of diseases. Due to the inherent low contrast and blurry edges in ultrasound images, most existing CNN-based methods often yield unsatisfactory segmentation results, making ultrasound image segmentation a challenging task. This paper introduces a novel multi-branch boundary enhanced network (MBE-UNet) for automatic ultrasound image segmentation. This method can accurately segment targets and delineate boundaries simultaneously using a multi-branch network. First, a global pyramid attention module (GPAM) is designed to capture multi-scale contextual information. Second, we embed a boundary cascade module (BCM) in the main branch to ensure the network focuses on edge information flow and generates relatively desirable boundaries. Finally, a boundary feature fusion module (BFM) is used to integrate boundary and region information, obtaining a boundary enhanced region map. The visual results and quantitative analysis demonstrate that the proposed MBE-UNet outperforms classical segmentation networks on three publicly available ultrasound datasets.

Details DOI

AAAI Conference 2025 Conference Paper

Debiased Active Learning with Variational Gradient Rectifier

Weiguo Chen
Changjian Wang
Shijun Li
Kele Xu
Yanru Bai
Wei Chen
Shanshan Li

The strategy of selecting ``most informative'' hard samples in active learning has proven a boon for alleviating the challenges of few-shot learning and costly data annotation in deep learning. However, this very preference towards hard samples engenders bias issues, thereby impeding the full potential of active learning. It has witnessed an increasing trend to mitigate this stubborn problem, yet most neglect the quantification of bias itself and the direct rectification of dynamically evolving biases. Revisiting the bias issue, this paper presents an active learning approach based on the Variational Gradient Rectifier (VaGeRy). First, we employ variational methods to quantify bias at the level of latent state representations. Then, harnessing historical training dynamics, we introduce Uncertainty Consistency Regularization and Fluctuation Restriction, which asynchronously iterate to rectify gradient backpropagation. Extensive experiments demonstrate that our proposed methodology effectively counteracts bias phenomena in a majority of active learning scenarios

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

TP-MDDN: Task-Preferenced Multi-Demand-Driven Navigation with Autonomous Decision-Making

Shanshan Li
Da Huang
Yu He
Yanwei Fu
Yu-Gang Jiang
Xiangyang Xue

In daily life, people often move through spaces to find objects that meet their needs, posing a key challenge in embodied AI. Traditional Demand-Driven Navigation (DDN) handles one need at a time but does not reflect the complexity of real-world tasks involving multiple needs and personal choices. To bridge this gap, we introduce Task-Preferenced Multi-Demand-Driven Navigation (TP-MDDN), a new benchmark for long-horizon navigation involving multiple sub-demands with explicit task preferences. To solve TP-MDDN, we propose AWMSystem, an autonomous decision-making system composed of three key modules: BreakLLM (instruction decomposition), LocateLLM (goal selection), and StatusMLLM (task monitoring). For spatial memory, we design MASMap, which combines 3D point cloud accumulation with 2D semantic mapping for accurate and efficient environmental understanding. Our Dual-Tempo action generation framework integrates zero-shot planning with policy-based fine control, and is further supported by an Adaptive Error Corrector that handles failure cases in real time. Experiments demonstrate that our approach outperforms state-of-the-art baselines in both perception accuracy and navigation robustness.

PDF Details

EAAI Journal 2025 Journal Article

Weakly supervised temporal action localization via a multimodal feature map diffusion process

Yuanbing Zou
Qingjie Zhao
Shanshan Li

With the continuous growth of massive video data, understanding video content has become increasingly important. Weakly supervised temporal action localization (WTAL), as a critical task, has received significant attention. The goal of WTAL is to learn temporal class activation maps (TCAMs) using only video-level annotations and perform temporal action localization via post-processing steps. However, due to the lack of detailed behavioral information in video-level annotations, the separability between foreground and background in the learned TCAM is poor, leading to incomplete action predictions. To this end, we leverage the inherent advantages of the Contrastive Language-Image Pre-training (CLIP) model in generating high-semantic visual features. By integrating CLIP-based visual information, we further enhance the representational capability of action features. We propose a novel multimodal feature map generation method based on diffusion models to fully exploit the complementary relationships between modalities. Specifically, we design a hard masking strategy to generate hard masks, which are then used as frame-level pseudo-ground truth inputs for the diffusion model. These masks are used to convey human behavior knowledge, enhancing the model’s generative capacity. Subsequently, the concatenated multimodal feature maps are employed as conditional inputs to guide the generation of diffusion feature maps. This design enables the model to extract rich action cues from diverse modalities. Experimental results demonstrate that our approach achieves state-of-the-art performance on two popular benchmarks. These results highlight the proposed method’s capability to achieve precise and efficient temporal action detection under weak supervision, making a significant contribution to the advancement in large-scale video data analysis.

Details DOI

EAAI Journal 2022 Journal Article

Risk evaluation of information technology outsourcing project: An integrated approach considering risk interactions and hierarchies

Wenyan Song
Yue Zhu
Shanshan Li
Li Wang
Hui Zhang

Effective risk evaluation is necessary to guarantee the successful completion of an IT outsourcing (ITO) process. However, previous methods of ITO risk assessment omit the interrelationships between the risk factors and ignore the vagueness of the evaluations. Additionally, most of the approaches fail to show the complex interactions among the risk factors with an intuitive and clear structure diagram. Thus, a new method for ITO risk assessment and visualization is developed in this paper. The proposed method integrates the advantages of improved decision-making and trial evaluation laboratories (DEMATEL) method, to incorporate the vagueness of the evaluations flexibly and evaluate the interactions and internal strengths of risk factors, and the merits of interpretative structural modeling (ISM), to clarify the risk factor structure. To illustrate the practicality and validity of this approach, an ITO case study of a mineral company is used in the implementation section to demonstrate the method.

Details DOI

TCS Journal 2018 Journal Article

Formalization of fractional order PD control systems in HOL4

Chunna Zhao
Shanshan Li

Higher-order logic theorem proving method is applied to analyze fractional order PD control systems in this paper. Theorem proving is based on rigorous logic and correct mathematics theory. Firstly, existent conditions and formal model of fractional calculus Caputo definition is established in higher order logic theorem prover. Then some properties are verified, including homogeneity, linearity property, fractional differential of constant and relationship between integer order differential and fractional differential. And formalization of Laplace transform based on fractional calculus Caputo definition is given and we apply it to illustrate advantages of fractional calculus Caputo definition. Initial values based on fractional calculus Caputo definition have exact physical meanings. And then formal modeling of fractional order PD controller is verified based on the above properties. We also verify the stability and other properties of fractional order PD controller by theorem proving method. Lastly, steady-state error is analyzed based on formalization of fractional calculus Caputo definition. It shows that fractional order PD controller can achieve a better control performance than integer order PD controller.

Details DOI