XLXueqiong Li

Xueqiong Li

*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


Xueqiong Li has a total of 53 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    MoViS: Interactive 3D Human Motion Authoring via Zero-3D Visual Prompts

    by Huibin Tan, Songyuan Yang, Jianing Yang, Yize Sui, Meng Zhang, Jintao Huang, Xiaoming Yan, Ligong Cao, Nan Hu, Kedi Zhang, et al.

    Generating spatially-aware 3D human motions from natural language remains a fundamental challenge, as text inherently lacks precise trajectory control. While recent methods condition generation on explicit 3D scenes to enforce physical grounding, they impose a severe human-computer interaction (HCI) bottleneck, demanding specialized 3D expertise and cumbersome user inputs. To democratize spatial control, we propose a paradigm shift: an interactive, zero-3D multimodal authoring framework named MoViS. MoViS empowers users to dictate complex spatial intent simply by drawing a 2D planar sketch (Visual Prompt) over a scene image, complemented by a text instruction. However, inferring 3D physical geometry from ambiguous 2D sketches presents extreme challenges in perspective scale and long-horizon intent drift. To overcome these, MoViS introduces a Physics-Grounded Cross-Modal Alignment mechanism, uniting 3D landmark distillation and continuous 2D perspective projection to embed true spatial awareness into a discrete generative backbone. Furthermore, we propose a cognitive-inspired Sketch-Driven Compositional Decoding strategy to robustly execute complex, multi-stage tasks. To catalyze this new paradigm, we construct IndoorViS, a large-scale multimodal dataset featuring 2,015 daily tasks across 1,173 diverse scenes. Extensive experiments demonstrate that MoViS strictly maintains the physical fidelity of explicit 3D-aware models while reducing human authoring overhead by over 90%, establishing a new standard for accessible and expressive embodied agent control.

  • Open Access

    Tensor Coupled Federated Multi-view Clustering with Multi-order Anchor Graph

    by Yangfan Du, Suyuan Liu, Jiyuan Liu, Hao Tan, Qi Liu, Xinzhong Zhu, Xueqiong Li, Xinwang Liu

    Graph-based federated multi-view clustering (FMVC) enables privacy-preserving collaborative analysis, yet traditional methods rely on full-sample graphs and suffer from prohibitive O(N2) complexities, especially on large-scale data. Recent advances have introduced anchor graphs into FMVC, effectively reducing overhead to linear complexity. Despite efficiency, existing anchor-based FMVC methods exhibit two critical limitations: 1) They strictly rely on first-order similarities, failing to mine the latent high-order nonlinear semantics of complex data. 2) Due to the independent construction of local anchor spaces, there is a severe lack of correlation and geometric alignment among them. To tackle these issues, we propose a novel framework termed Tensor Coupled Federated Multi-View Clustering with Multi-order Anchor Graph (TFedMAG). Specifically, on the client, TFedMAG employs a multi-order anchor graph learning strategy to capture high-order correlations, while utilizing virtual anchors for privacy protection, and further produces a unified anchor graph. On the server, TFedMAG receives and splices fused graphs uploaded by each client into a third-order tensor to capture global multi-client features. Then, a tensor low-rank constraint is applied to enhance consistency and complementarity among clients. Additionally, extensive experiments are conducted on several real-world datasets, and the corresponding results demonstrate that the TFedMAG method achieves state-of-the-art clustering performance compared to existing FMVC methods.

  • Open Access

    BeyondFacial: Identity-Preserving Personalized Generation Beyond Facial Close-ups

    by Songsong Zhang, Chuanqi Tang, Minglong Li, Xueqiong Li, Shaowu Yang, Yuanxi Peng, Wenjing Yang, Jing Zhao

  • DDIRNet: Robust Radar Emitter Recognition via Single Domain Generalization

    by Wu Honglin, Li Xueqiong, Huang Junjie, Jin Ruochun, Tang Yuhua

    Automatically recognizing radar emitters from complex electromagnetic environments is important but non-trivial. Moreover, the changing electromagnetic environment results in inconsistent signal distribution in the real world, which makes the existing approaches perform poorly for recognition tasks in different scenes. In this paper, we propose a domain generalization framework is proposed to improve the adaptability of radar emitter signal recognition in changing environments. Specifically, we propose an end-to-end denoising based domain-invariant radar emitter recognition network (DDIRNet) consisting of a denoising model and a domain invariant representation learning model (IRLM), which mutually benefit from each other. For the signal denoising model, a loss function is proposed to match the feature of the radar signals and guarantee the effectiveness of the model. For the domain invariant representation learning model, contrastive learning is introduced to learn the cross-domain feature by aligning the source and unseen domain distribution. Moreover, we design a data augmentation method that improves the diversity of signal data for training. Extensive experiments on classification have shown that DDIRNet achieves up to 6.4% improvement compared with the state-of-the-art radar emitter recognition methods. The proposed method provides a promising direction to solve the radar emitter signal recognition problem.

  • TIG-CL: Teacher-Guided Individual- and Group-Aware Contrastive Learning for Unsupervised Person Reidentification in Internet of Things

    by Xiao Teng, Chuan Li, Xueqiong Li, Xinwang Liu, Long Lan

    Unsupervised person reidentification (Re-ID) has attracted widespread due to its potential in Internet of Things applications, such as intelligent visual surveillance, it refers to retrieving the same individual across different camera views without using labeled data. To tackle the problem, a prevalent technique adopted by existing methods involves generating pseudo labels through clustering algorithms. However, this approach can result in merging individuals with different identities into the same group (i.e., cluster) during the training process. As a result, the resulting group centers may obscure the inherent characteristics of individual identities, thereby hindering the model from learning discriminative representations. To address the issue, we present a teacher-guided individual- and group-aware contrastive learning framework. Specifically, we propose a departure from the traditional approach of relying solely on contrastive learning between individual features and their corresponding group centers. Instead, we also exploit the relationship among individuals to construct contrast pairs and facilitate the learning of more discriminative features. This strategy enables the model to learn more about the individual characteristics that distinguish different persons, thus enhancing its ability to reidentify individuals accurately. Moreover, our method introduces a novel hybrid distillation module that enables simultaneous probability distillation at the group level and relationship distillation at the individual level. Guided by the teacher model, this module leads to improved feature representations of the student model. Extensive experimental results verify the effectiveness of our approach on four popular Re-ID data sets. The code will be made publicly available.


  • Joint Spatial–Spectral Optimization for the High-Magnification Fusion of Hyperspectral and Multispectral Images

    by Jian Long, Yibing Zhan, Zhengbin Pang, Tong Zhou, Xueqiong Li, Long Lan, Yuanxi Peng

    The fusion of hyperspectral and multispectral images is an important strategy for enhancing the spatial resolution of hyperspectral images. With the rapid advancement of multispectral imaging technology, the disparity in spatial resolution between multispectral and hyperspectral images is increasing. In certain scenarios, termed high-magnification, this difference can exceed 32×. Previous methods do not perform well under high-magnification fusion, and naturally, a challenge arises in achieving effective high-magnification super-resolution fusion. In light of the above analysis, this paper introduces a novel algorithm for high-magnification super-resolution fusion of hyperspectral and multispectral images based on the joint optimization of spatial and spectral information. Specifically, our algorithm consists of three stages: 1) a fast preliminary fusion stage based on the Moore-Penrose inverse and singular value correlation priors for the rapid acquisition of preliminary solutions, 2) a joint spatial-spectral optimization stage where a coupled optimization framework is constructed to achieve integrated optimization of spatial and spectral information, and 3) an error backpropagation optimization stage where an effective error optimization term is introduced to further refine the fusion performance. We conducted extensive experiments on widely employed publicly available simulated datasets and real datasets. The experimental results unequivocally indicate that our proposed methodology consistently exhibits superior fusion performance compared with state-of-the-art methods, even under the condition of ≥60× super-resolution.


  • Open Access

    Towards Radar Emitter Recognition in Changing Environments with Domain Generalization

    by Honglin Wu, Xueqiong Li, Long Lan, Liyang Xu, Yuhua Tang

    Analyzing radar signals from complex Electronic Warfare (EW) environment is a non-trivial task. However, in the real world, the changing EW environment results in inconsistent signal distribution, such as the pulse repetition interval (PRI) mismatch between different detected scenes. In this paper, we propose a novel domain generalization framework to improve the adaptability of signal recognition in changing environments. Specifically, we first design several noise generators to simulate varied scenes. Different from conventional augmentation methods, our introduced generators carefully enhance the diversity of the detected signals and meanwhile maintain the semantic features of the signals. Moreover, we propose a signal scene domain classifier that works in the manner of adversarial learning. The proposed classifier guarantees the signal predictor to generalize to different scenes. Extensive comparative experiments prove the proposed method's superiority.


  • Highly Efficient Active Learning With Tracklet-Aware Co-Cooperative Annotators for Person Re-Identification

    by Xiao Teng, Long Lan, Jing Zhao, Xueqiong Li, Yuhua Tang

    Supervised person re-identification (ReID) has attracted widespread attentions in the computer vision community due to its great potential in real-world applications. However, the demand of human annotation heavily limits the application as it is costly to annotate identical pedestrians appearing from different cameras. Thus, how to reduce the annotation cost while preserving the performance remains challenging and has been studied extensively. In this article, we propose a tracklet-aware co-cooperative annotators’ framework to reduce the demand of human annotation. Specifically, we partition the training samples into different clusters and associate adjacent images in each cluster to produce the robust tracklet which decreases the annotation requirements significantly. Besides, to further reduce the cost, we introduce a powerful teacher model in our framework to implement the active learning strategy and select the most informative tracklets for human annotator, the teacher model itself, in our setting, also acts as an annotator to label the relatively certain tracklets. Thus, our final model could be well-trained with both confident pseudo-labels and human-given annotations. Extensive experiments on three popular person ReID datasets demonstrate that our approach could achieve competitive performance compared with state-of-the-art methods in both active learning and unsupervised learning (USL) settings.


  • Open Access

    Unknown Radar Signals Deinterleaving Based on TCN Network

    by Liying Ma, Xueqiong Li, Yuhua Tang

    Radar signals deinterleaving plays a critical role in electronic reconnaissance. Nevertheless, due to the extremely high density of intercepted signal trains and the unknown number of emitters, along with the low probability of interception (LPI), high loss rate, and high spurious rate, the deinterleaving task is becoming more challenging. In this paper, we propose a temporal convolutional network (TCN)-based method for deinterleaving radar signal pulse trains, using only the time of arrival (TOA) parameter without knowing how many emitters there are. Simulation results indicate that the proposed method can still achieve high accuracy in situations with high pulse loss and spurious rates.