Author name cluster

Shuang 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.

45 papers

2 author rows

EAAI Journal 2026 Journal Article

A spatio-temporal graph attention prediction method for coal spontaneous combustion temperature integrating time-frequency domain lag features

Shuang Li
Ningke Xu

Coal spontaneous combustion is one of the main causes of mine fires, and accurate prediction of coal spontaneous combustion temperature is the key to preventing coal spontaneous combustion from occurring. Existing methods for predicting spontaneous coal combustion temperature have limited feature extraction capabilities and ignore the spatial correlation that exists between spontaneous coal combustion temperature and other variables. In order to accurately predict the coal spontaneous combustion temperature, this paper proposed a residual correction prediction method of coal spontaneous combustion temperature based on spatio-temporal graph attention mechanism with time-frequency domain lag feature fusion. In the two-dimensional domain, the time-frequency domain lag feature fusion method is proposed for the first time. In the three-dimensional domain, the spatial characteristics are extracted based on the improved graph convolution network, and the multi-channel information of the data is fully exploited through parallel dilated convolutional operations and the channel attention mechanism. Finally, the prediction results of the baseline model are corrected by residuals using the Crossformer model. The practical application results in coal mining enterprises show that, compared with the traditional baseline model, the mean absolute error, root mean square error, and mean absolute percentage error prediction error indicators of the proposed method have an average reduction of 9. 91, 10. 50, and 7. 79 respectively, and the coefficient of determination value has increased by 7. 43 %. Therefore, the method proposed in this study has better applicability and prediction accuracy, which can effectively prevent coal mine accidents and promote the sustainable development of the coal mining industry.

Details DOI

AAAI Conference 2026 Conference Paper

Dynamic-Static Collaboration for Unsupervised Domain Adaptive Video-Based Visible-Infrared Person Re-Identification

Jiaxu Leng
Zhengjie Wang
Shuang Li
Xinbo Gao

Video-based visible-infrared person re-identification (VVI-ReID) aims to match pedestrian sequences across modalities for all-day surveillance. While supervised methods have shown progress, their dependence on large-scale cross-modal annotations limits scalability. We investigate the task of unsupervised domain adaptation for VVI-ReID (UDA-VVI-ReID), where a model trained on a labeled source domain is adapted to an unlabeled target domain. Directly extending existing image-based unsupervised VI-ReID methods to video scenarios by simply averaging frame-level features is suboptimal, as this naive strategy neglects the rich temporal dynamics in video data and leads to unreliable pseudo-labels due to occlusion-induced noise. To overcome these limitations, we propose a Dynamic-Static Collaboration (DSC) framework that explicitly leverages the complementary strengths of motion and appearance cues. The Dynamic-Static Label Unification (DSLU) module refines pseudo-labels by validating the consistency between static and dynamic predictions. Based on these labels, the Dynamic-Static Joint Learning (DSJL) module performs neighbor-aware contrastive learning in both feature spaces, promoting robust representation learning under cross-modal and temporal variations. Experiments on HITSZ-VCM and BUPTCampus show that DSC sets a strong baseline for this new task, enabling robust cross-modal video ReID without target labels.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Hierarchical Prompt Learning for Image- and Text-Based Person Re-Identification

Linhan Zhou
Shuang Li
Neng Dong
Yonghang Tai
Yafei Zhang
Huafeng Li

Person re-identification (ReID) aims to retrieve target pedestrian images given either visual queries (image-to-image, I2I) or textual descriptions (text-to-image, T2I). Although both tasks share a common retrieval objective, they pose distinct challenges: I2I emphasizes discriminative identity learning, while T2I requires accurate cross-modal semantic alignment. Existing methods often treat these tasks separately, which may lead to representation entanglement and suboptimal performance. To address this, we propose a unified framework named Hierarchical Prompt Learning (HPL), which leverages task-aware prompt modeling to jointly optimize both tasks. Specifically, we first introduce a Task-Routed Transformer, which incorporates dual classification tokens into a shared visual encoder to route features for I2I and T2I branches respectively. On top of this, we develop a hierarchical prompt generation scheme that integrates identity-level learnable tokens with instance-level pseudo-text tokens. These pseudo-tokens are derived from image or text features via modality-specific inversion networks, injecting fine-grained, instance-specific semantics into the prompts. Furthermore, we propose a Cross-Modal Prompt Regularization strategy to enforce semantic alignment in the prompt token space, ensuring that pseudo-prompts preserve source-modality characteristics while enhancing cross-modal transferability. Extensive experiments on multiple ReID benchmarks validate the effectiveness of our method, achieving state-of-the-art performance on both I2I and T2I tasks.

PDF Details DOI

TMLR Journal 2026 Journal Article

MIRA: Multi-view Information Retrieval with Adaptive Routing for Test-time Long-video Comprehension

Zecheng Hao
Wayne Ma
Yufeng Cui
Shuang Li
Xinlong Wang
Tiejun Huang

Foundational Multi-modal Large Language Models (MLLMs) have achieved rapid progress in handling complex tasks across diverse modalities. However, they still struggle to deliver satisfactory performance on Long-video Comprehension (LVC) tasks involving thousands of frames. Existing optimization strategies can be broadly categorized into LVC-specific fine-tuning, built-in token compression and training-free keyframe extraction, with the latter being most suitable for flexible deployment across various MLLMs. Unfortunately, current training-free approaches predominantly focus on query-frame relevance retrieval, overlooking other levels of visual information and the inherent heterogeneity of LVC tasks. In this work, we propose the $\textbf{M}$ulti-view $\textbf{I}$nformation $\textbf{R}$etrieval with $\textbf{A}$daptive Routing ($\textbf{MIRA}$) framework, which evaluates video frames using distinct metrics for relevance and causality, combines these scores to select a balanced pool of keyframes, and employs an adaptive feedback loop to tailor the retrieval process to different user queries, enabling more precise and sample-grained video comprehension. Extensive experiments demonstrate the advanced performance of our scheme across multiple challenging LVC benchmarks. For instance, integrating $\textbf{MIRA}$ with Qwen-2.5-VL yields performance gains of 3.5% to 13.1% on LVB, VideoMME and MLVU.