Author name cluster

Zhan Gao

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.

5 papers

2 author rows

EAAI Journal 2026 Journal Article

A cosmetic packaging design method based on online reviews

Zhan Gao
Zhenyu Li

To address the transformation of user experience and packaging iteration in cosmetics due to the diversification of usage scenarios and demands, this study capitalizes on the advancements in artificial intelligence across user analysis, data analysis, and generative design domains, and proposes a cosmetic packaging design approach centered around online reviews. In this study, 124, 879 pieces of user review data were collected from JingDong (JD), a Chinese e-commerce platform, using Python programming technology. Five topics are clustered through the application of the Latent Dirichlet Allocation (LDA) topic model. By integrating the coding of Grounded Theory, 18 demand elements within six core categories are summarized. The Kano model and the Analytic Hierarchy Process (AHP) are employed to classify and rank these demands. Notably, aspects such as strong brand recognition (M1, 0. 2182), strong brand value perception (M5, 0. 1129), and visually appealing and refined aesthetics (A5, 0. 0983) exhibit relatively high weights. Subsequently, six lipstick packaging design schemes are developed by combining traditional software with the MidJourney generative artificial intelligence tool. Through comprehensive evaluation using the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) method, the optimal Scheme c is identified and further optimized. This study constructs a comprehensive design strategy with user online reviews at its core, encompassing data collection, analysis, scheme design, artificial intelligence (AI)-assisted design, and evaluation. It is recommended that the application of artificial intelligence (AI)-assisted design be significantly enhanced throughout the entire design process, enabling precise and rapid generation of design schemes, streamlining the process, and shortening the development cycle.

Details DOI

JBHI Journal 2026 Journal Article

Automated Screening Network for Fetal Closed Spina Bifida With Semantic Enhancement and Projected Attention

Zhan Gao
Yan Ding
Ningbo Zhu
Hongjie Zhang
Chunlian Wang
Shengli Li
Kenli Li

Closed spina bifida is a high-incidence developmental disorder among rare fetal diseases. Its signs in ultrasound imaging are subtle, making it prone to misdiagnosis and heavily reliant on sonographers' experience. Therefore, we propose a novel semantic enhancement framework incorporating projected attention for the automated screening of closed spina bifida through precise landmark detection. In this method, we utilize a multi-granularity deep supervision and voting mechanism to generate point-specific features and reconstruct saliency maps for each landmark, effectively reducing interference from homogeneous high-echogenic noise in ultrasound images while preserving rich semantic information. Additionally, a coordinate attention projection module is designed to convert the 2D landmark probability maps into one-dimensional vectors, ensuring low computational complexity along with precise coordinate regression. The clinical application potential of this intelligent system is significant, as it facilitates automated fetal spine counting and anatomical measurement, enabling early warnings of diseases based on identified anomalies. Extensive experiments comparing our method with advanced baselines on an in-house dataset and two public datasets demonstrate its clear advantage in computational complexity and accuracy.

Details DOI

AAAI Conference 2026 Conference Paper

MPA: Multimodal Prototype Augmentation for Few-Shot Learning

Liwen Wu
Wei Wang
Lei Zhao
Zhan Gao
Qika Lin
Shaowen Yao
Zuozhu Liu
Bin Pu

Recently, Few-shot Learning (FSL) has become a popular task that aims to recognize new classes from only a few labeled examples and has been widely applied in fields such as natural science, remote sensing, and medical images. However, most existing methods focus only on the visual modality and compute prototypes directly from raw support images, which lack comprehensive and rich multimodal information. To address these limitations, we propose a novel Multimodal Prototype Augmentation FSL framework called MPA, including LLM-based Multi-Variant Semantic Enhancement (LMSE), Hierarchical Multi-View Augmentation (HMA), and an Adaptive Uncertain Class Absorber (AUCA). LMSE leverages large language models to generate diverse paraphrased category descriptions, enriching the support set with additional semantic cues. HMA exploits both natural and multi-view augmentations to enhance feature diversity (e.g., changes in viewing distance, camera angles, and lighting conditions). AUCA models uncertainty by introducing uncertain classes via interpolation and Gaussian sampling, effectively absorbing uncertain samples. Extensive experiments on four single-domain and six cross-domain FSL benchmarks demonstrate that MPA achieves superior performance compared to existing state-of-the-art methods across most settings. Notably, MPA surpasses the second-best method by 12.29% and 24.56% in the single-domain and cross-domain setting, respectively, in the 5-way 1-shot setting.

PDF Details DOI

EAAI Journal 2024 Journal Article

Graph-enhanced ensembles of multi-scale structure perception deep architecture for fetal ultrasound plane recognition

Zhan Gao
Guanghua Tan
Chunlian Wang
Jianxin Lin
Bin Pu
Shengli Li
Kenli Li

Ultrasound imaging plays a pivotal role in assessing fetal health and diagnosing diseases. However, the inherent challenges posed by the high similarity of certain fetal anatomical structures and noise in ultrasound images hinder the accurate identification of ultrasound planes. To address this challenge, we present a graph-enhanced ensembles of multi-scale structure perception architecture for more precise identification of standard ultrasound planes. Specifically, we introduce a local-to-global multi-granularity ensemble module for feature enhancement and noise suppression, coupled with a graph-based multi-view refinement module to perceive relationships within fetal anatomical structures. Additionally, we employ multiple classifiers with branch subnets to capture fine-grained structure representations and integrate a confidence evaluation loss to ensure alignment with the true distribution. Finally, the collaborative decision-making among classifiers is achieved through confidence matching. Extensive experiments demonstrate that our innovative framework achieves state-of-the-art classification performance on multiple datasets, and verify that the improvements benefit from the proposed modules. We also show that our method has outstanding capabilities in evaluating the quality of fetal ultrasound planes, a distinctive attribute absent in current methods. Code is available at: https: //github. com/201610006/graph-ensemble-net. git.

Details DOI

ICRA Conference 2023 Conference Paper

Environment Optimization for Multi-Agent Navigation

Zhan Gao
Amanda Prorok

Traditional approaches to the design of multiagent navigation algorithms consider the environment as a fixed constraint, despite the obvious influence of spatial constraints on agents' performance. Yet hand-designing improved environment layouts and structures is inefficient and potentially expensive. The goal of this paper is to consider the environment as a decision variable in a system-level optimization problem, where both agent performance and environment cost can be accounted for. We begin by proposing a novel environment optimization problem. We show, through formal proofs, under which conditions the environment can change while guaranteeing completeness (i. e. , all agents reach their navigation goals). Our solution leverages a model-free reinforcement learning approach. In order to accommodate a broad range of implementation scenarios, we include both online and offline optimization, and both discrete and continuous environment representations. Numerical results corroborate our theoretical findings and validate our approach.

Details