MXMian Xiang

Mian Xiang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Mian Xiang has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    MDRAN: a multi-source dual-refining adaptation network for source-free domain adaptation guided by vision-language-model

    by Bingtao Zhou, Mian Xiang, Qian Ning

    Source-Free Domain Adaptation (SFDA) adapts a pre-trained source model to an unlabeled target domain without accessing source data, alleviating the need for direct access to source data during adaptation, which reduces the risk of data transmission. Existing methods leverage pre-trained Vision-Language (ViL) models to provide supervisory signals, but their predictions are often noisy, limiting adaptation performance. Moreover, current approaches refine ViL predictions only within individual source domains, overlooking the complementary discriminative evidence available across multiple sources. To better select the most decisive refinement signal from each source model, we propose a novel criterion, termed M aximum R efinement D ecision score ( MRD-score ), which replaces softmax with median centering to normalize source models’ predictions along both positive and negative axes, thereby harnessing both affirmative and complementary guidance. Building upon MRD-score, we present M ulti-source D ual- R efining A daptation N etwork ( MDRAN ), which, to the best of our knowledge, is among the first attempts to exploit ViL-based guidance for multi-source-free domain adaptation (MSFDA). MDRAN first aggregates the MRD-score-based predictions from multiple source models to construct S elected Source- L ogit S et ( SLS ), which is then used to customize a collective ViL model via prompt learning. To mitigate noise in the collective ViL models’ outputs, we design a D ual- V iew R efinement ( DVR ) module that refines ViL model’s predictions using source model predictions. Extensive experiments on four benchmarks demonstrate that our method achieves state-of-the-art performance on the more challenging Office-Home, VisDA-C, and DomainNet-126, while remaining highly competitive on the comparatively easy Office-31. The code can be found in https://anonymous.4open.science/r/MDRAN-098E/ .

  • Open Access

    STMS-Net: Spatial Temporal Multi-Spectral Network for sEMG Gesture Recognition

    by Wang Sijin, Tan Jianjun, Zhou Bingtao, Hu Tao, Zhu Li, Xiang Mian

    Accurate gestures recognition of sEMG plays an important role in the field of human-robot interaction. Currently, researchers commonly extracted feature from sEMG signals though spatial or temporal views. This paper introduces a novel Spatial Temporal Multi-Spectral Network (STMS-Net) to improve the recognition capability by leveraging the spatial, temporal and spectral features of sEMG signals. First of all, sEMG signal is filtered by a filter bank to obtain a multi-spectral data, then it is segmented into several fragments. Afterwards, for each fragment, a Multilayer Perceptron(MLP) Combining Max Pooling Network (MCMP-Net) is employed to extract the local spatial features. After that, the spatial features undergo two self-attention based modules to aware both the temporal and spectral interdependence within them, in those two modules, the spatial features are regarded as tokens of attention layer from spatial or spectral views, and dimension rearrangement is employed to streamline the network operations. At last, MLP and Softmax layer are operated as classification head. We evaluate our model on eight benchmark datasets: NinaPro DB1, DB2, DB4, DB5, CapgMyo DB-a, DB-b, and DB-c, and BandMyo, the accuracy on them are 91.9%, 90.0%, 90.1%, 96.1%, 94.1%, 93.8%, 95.1%, 76.9%, respectively, the results show that STMS-Net achieves or exceeds state-of-art performance.


  • Open Access

    TCAD: Unsupervised Anomaly Detection Based on Global Local Representation Differences

    by Yaqiong Duan, Mian Xiang, Bingtao Zhou, Desu Fu, Hongxiao Liu

    Multivariate time series anomaly detection is of great interest because of its wide range of applications. Since it is difficult to obtain accurate anomaly labels, many unsupervised anomaly detection algorithms have been developed. However, it is challenging to build an unsupervised multivariate anomaly detection model because we need to find a criterion with anomaly discriminative power. Previously, researchers have focused on extracting the association of time points with global sequences, while ignoring the association of time points with local sequences. In this paper, we propose a combined model TCAD based on Transformer and Resnet, which learns global and local features of sequences using Transformer and Resnet, and constrains the learning of rich global local representations using reconstructed differences and global local representation differences. In addition, this paper proposes an anomaly score based on global and local feature discrepancies. TCAD is extensively tested on four public datasets and two private datasets.


  • Expanding-Window BATS Code With Intermediate Feedback

    by Mian Xiang, Benshun Yi, Kang Qiu, Taiqi Huang

    In this letter, we investigate feedback in expanding window BATS (EW-BATS) code. A single intermediate message is fed back to inform the more important packets have been decoded completely. The asymptotic decoding probabilities of various types of input packets with the proposed feedback expanding window BATS (FEW-BATS) code is analyzed via And-Or tree evaluation, we also optimized the degree distribution for FEWBATS code based on the analytical results. Simulation results show that the proposed FEW-BATS code can decrease average overhead of successful decoding in less important packets and has no affect to decoding performance of more important packets.