Wei Cui

EAAI Journal 2026 Journal Article

Automatic estimation of lactate threshold heart rate and pace in real-world running based on transfer learning

• Zheng Zhu
• Wei Cui
• Changda Lu
• Yanfei Shen
• Bingyu Pan

AAAI Conference 2026 Conference Paper

Light but Sharp: SlimSTAD for Real-Time Action Detection from Sensor Data

• Wei Cui
• Lukai Fan
• Zhenghua Chen
• Min Wu
• Shili Xiang
• Haixia Wang
• Bing Li

Sensory Temporal Action Detection (STAD) aims to localize and classify human actions within long, untrimmed sequences captured by non-visual sensors such as WiFi or inertial measurement units (IMUs). Unlike video-based TAD, STAD poses unique challenges due to the low-dimensional, noisy, and heterogeneous nature of sensory data, as well as the real-time and resource constraints on edge devices. While recent STAD models have improved detection performance, their high computational cost hampers practical deployment. In this paper, we propose SlimSTAD, a simple yet effective framework that achieves both high accuracy and low latency for STAD. SlimSTAD features a novel Decoupled Channel Modeling (DCM) encoder, which preserves modality-specific temporal features and enables efficient inter-channel aggregation via lightweight graph attention. An anchor-free cascade predictor then refines action boundaries and class predictions in a two-stage design without dense proposals. Experiments on two real-world datasets demonstrate that SlimSTAD outperforms strong video-derived and sensory baselines by an average of 2.1 mAP, while significantly reducing GFLOPs, parameters, and latency, validating its effectiveness for real-world, edge-aware STAD deployment.

YNICL Journal 2025 Journal Article

Abnormal myelin could be a mediator of childhood-trauma-induced depression: A quantitative synthetic MRI study

• Junyan Wen
• Shuqiong Zheng
• Zhimin Chen
• Xuecong Lin
• Shanshan Yang
• Wei Cui
• Liaoming Gao
• Ziqi Wu

JBHI Journal 2024 Journal Article

Unsupervised Domain Adaptation Fundus Image Segmentation via Multi-Scale Adaptive Adversarial Learning

• Wei Zhou
• Jianhang Ji
• Wei Cui
• Yingyuan Wang
• Yugen Yi

Segmentation of the Optic Disc (OD) and Optic Cup (OC) is crucial for the early detection and treatment of glaucoma. Despite the strides made in deep neural networks, incorporating trained segmentation models for clinical application remains challenging due to domain shifts arising from disparities in fundus images across different healthcare institutions. To tackle this challenge, this study introduces an innovative unsupervised domain adaptation technique called Multi-scale Adaptive Adversarial Learning (MAAL), which consists of three key components. The Multi-scale Wasserstein Patch Discriminator (MWPD) module is designed to extract domain-specific features at multiple scales, enhancing domain classification performance and offering valuable guidance for the segmentation network. To further enhance model generalizability and explore domain-invariant features, we introduce the Adaptive Weighted Domain Constraint (AWDC) module. During training, this module dynamically assigns varying weights to different scales, allowing the model to adaptively focus on informative features. Furthermore, the Pixel-level Feature Enhancement (PFE) module enhances low-level features extracted at shallow network layers by incorporating refined high-level features. This integration ensures the preservation of domain-invariant information, effectively addressing domain variation and mitigating the loss of global features. Two publicly accessible fundus image databases are employed to demonstrate the effectiveness of our MAAL method in mitigating model degradation and improving segmentation performance. The achieved results outperform current state-of-the-art (SOTA) methods in both OD and OC segmentation.

JBHI Journal 2021 Journal Article

An Attention Based CNN-LSTM Approach for Sleep-Wake Detection With Heterogeneous Sensors

• Zhenghua Chen
• Min Wu
• Wei Cui
• Chengyu Liu
• Xiaoli Li

In this article, we propose an attention based convolutional neural network long short-term memory (CNN-LSTM) approach for sleep-wake detection with heterogeneous sensor data, i. e. , acceleration and heart rate variability (HRV). Since the three-dimensional acceleration data was sampled with a high frequency, we firstly design a CNN-LSTM structure to effectively learn latent features from the acceleration. Meanwhile, considering the unique format of the HRV data, some effective features are extracted based on domain knowledge. Next, we design a unified architecture to efficiently merge the features learned by CNN-LSTM approach from the acceleration and the extracted features from the HRV, which enables us to make full use of all the available information from these two heterogeneous sources. Taking into consideration that these two heterogeneous sources may have distinct contributions for the sleep and wake states, we propose an attention network to dynamically adjust the importance of features from the two sources. Real-world experiments have been conducted to verify the effectiveness of the proposed approach for sleep-wake detection. The results demonstrate that the proposed method outperforms all existing approaches for sleep-wake classification. In the evaluation of leave-one-subject-out (LOSO) cross-validation which is more challenging and practical, the proposed method achieves remarkable improvements ranging from 5% to 46% over the benchmark approaches.

NeurIPS Conference 2021 Conference Paper

Linear Convergence of Gradient Methods for Estimating Structured Transition Matrices in High-dimensional Vector Autoregressive Models

• Xiao Lv
• Wei Cui
• Yulong Liu

In this paper, we present non-asymptotic optimization guarantees of gradient descent methods for estimating structured transition matrices in high-dimensional vector autoregressive (VAR) models. We adopt the projected gradient descent (PGD) for single-structured transition matrices and the alternating projected gradient descent (AltPGD) for superposition-structured ones. Our analysis demonstrates that both gradient algorithms converge linearly to the statistical error even though the strong convexity of the objective function is absent under the high-dimensional settings. Moreover our result is sharp (up to a constant factor) in the sense of matching the phase transition theory of the corresponding model with independent samples. To the best of our knowledge, this analysis constitutes first non-asymptotic optimization guarantees of the linear rate for regularized estimation in high-dimensional VAR models. Numerical results are provided to support our theoretical analysis.

AAAI Conference 2021 Conference Paper

OpEvo: An Evolutionary Method for Tensor Operator Optimization

• Xiaotian Gao
• Wei Cui
• Lintao Zhang
• Mao Yang

Training and inference efficiency of deep neural networks highly rely on the performance of tensor operators on hardware platforms. Manually optimizing tensor operators has limitations in terms of supporting new operators or hardware platforms. Therefore, automatically optimizing device code configurations of tensor operators is getting increasingly attractive. However, current methods for tensor operator optimization usually suffer from poor sample-efficiency due to the combinatorial search space. In this work, we propose a novel evolutionary method, OpEvo, which efficiently explores the search spaces of tensor operators by introducing a topology-aware mutation operation based on q-random walk to leverage the topological structures over the search spaces. Our comprehensive experiment results show that compared with state-of-the-art (SOTA) methods OpEvo can find the best configuration with the lowest variance and least efforts in the number of trials and wall-clock time. All code of this work is available online.

AAAI Conference 2021 Conference Paper

Two-Stream Convolution Augmented Transformer for Human Activity Recognition

• Bing Li
• Wei Cui
• Wei Wang
• Le Zhang
• Zhenghua Chen
• Min Wu

Recognition of human activities is an important task due to its far-reaching applications such as healthcare system, context-aware applications, and security monitoring. Recently, WiFi based human activity recognition (HAR) is becoming ubiquitous due to its non-invasiveness. Existing WiFibased HAR methods regard WiFi signals as a temporal sequence of channel state information (CSI), and employ deep sequential models (e. g. , RNN, LSTM) to automatically capture channel-over-time features. Although being remarkably effective, they suffer from two major drawbacks. Firstly, the granularity of a single temporal point is blindly elementary for representing meaningful CSI patterns. Secondly, the timeover-channel features are also important, and could be a natural data augmentation. To address the drawbacks, we propose a novel Two-stream Convolution Augmented Human Activity Transformer (THAT) model. Our model proposes to utilize a two-stream structure to capture both time-over-channel and channel-over-time features, and use the multi-scale convolution augmented transformer to capture range-based patterns. Extensive experiments on four real experiment datasets demonstrate that our model outperforms state-of-the-art models in terms of both effectiveness and efficiency 1.

IJCAI Conference 2018 Conference Paper

An Adaptive Hierarchical Compositional Model for Phrase Embedding

• Bing Li
• Xiaochun Yang
• Bin Wang
• Wei Wang
• Wei Cui
• Xianchao Zhang

Phrase embedding aims at representing phrases in a vector space and it is important for the performance of many NLP tasks. Existing models only regard a phrase as either full-compositional or non-compositional, while ignoring the hybrid-compositionality that widely exists, especially in long phrases. This drawback prevents them from having a deeper insight into the semantic structure for long phrases and as a consequence, weakens the accuracy of the embeddings. In this paper, we present a novel method for jointly learning compositionality and phrase embedding by adaptively weighting different compositions using an implicit hierarchical structure. Our model has the ability of adaptively adjusting among different compositions without entailing too much model complexity and time cost. To the best of our knowledge, our work is the first effort that considers hybrid-compositionality in phrase embedding. The experimental evaluation demonstrates that our model outperforms state-of-the-art methods in both similarity tasks and analogy tasks.

AAAI Conference 2017 Conference Paper

Efficiently Mining High Quality Phrases from Texts

• Bing Li
• Xiaochun Yang
• Bin Wang
• Wei Cui

Phrase mining is a key research problem for semantic analysis and text-based information retrieval. The existing approaches based on NLP, frequency, and statistics cannot extract high quality phrases and the processing is also time consuming, which are not suitable for dynamic on-line applications. In this paper, we propose an efficient high-quality phrase mining approach (EQPM). To the best of our knowledge, our work is the first effort that considers both intra-cohesion and inter-isolation in mining phrases, which is able to guarantee appropriateness. We also propose a strategy to eliminate order sensitiveness, and ensure the completeness of phrases. We further design efficient algorithms to make the proposed model and strategy feasible. The empirical evaluations on four real data sets demonstrate that our approach achieved a considerable quality improvement and the processing time was 2. 3× ∼ 29× faster than the state-of-the-art works.