Ning Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ning Li has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Bineng Zhong
Guangxi Normal University
15 shared publications - Qihua Liang
Guangxi Normal University
12 shared publications - Shuxiang Song
Guangxi Normal University
8 shared publications - Zhiyi Mo
Guangxi Key Laboratory of Machine Vision and Intelligent Control, Wuzhou University, Wuzhou, China
4 shared publications - Yaozong Zheng
Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China
3 shared publications - Guangtong Zhang
College of Computer Science and Technology, Jilin University, Changchun, China
2 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (11) , 17843-17854
Frequency-Guided and Temporal Prompt Information Integration for RGB-T Tracking
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (11) , 17843-17854
Frequency-Guided and Temporal Prompt Information Integration for RGB-T Tracking
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (11) , 17832-17842
DTP-Track: Diversity-Guided Token Pruning and Purification for Vision–Language Tracking
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (11) , 17832-17842
DTP-Track: Diversity-Guided Token Pruning and Purification for Vision–Language Tracking
- Open Access
- 22 July 2026
- Published by Springer Nature in Cybersecurity
- Vol. 9 (1) , 194
No train, no pain: a training-free few-shot traffic classifier based on LLMs
Encrypted web traffic and evolving Internet technologies pose an increasing challenge to network traffic analysis. However, existing traffic classification methods, though effective, require large labeled datasets and complex training. This makes sustaining them prohibitively expensive and difficult in real-world scenarios. To narrow this gap, we propose a novel training-free few-shot network traffic classification framework based on large language models (LLMs). By integrating meta-learning with LLMs, it reduces reliance on labeled data, eliminates task-specific training, and improves performance. Specifically, we first apply an efficient feature extraction method to extract features from traffic flows. We then design meta-tasks that combine task descriptions with textualized features to produce natural language meta-task formulations. Building on these meta-tasks, the LLM performs reasoning to carry out traffic classification. Finally, to mitigate hallucination in the LLM outputs, we exploit the temporal characteristics of network traffic and aggregate predictions over samples within a defined time window. Extensive experiments on three widely-used encrypted traffic datasets demonstrate that our proposed framework outperforms the state-of-the-art methods, achieving an average absolute improvement in F1 score of 9.75, 9.82, and 12.06 percentage points on the three datasets, respectively.
- 22 July 2026
- Published by Springer Nature in Cybersecurity
- Vol. 9 (1) , 194
Open AccessNo train, no pain: a training-free few-shot traffic classifier based on LLMs
Encrypted web traffic and evolving Internet technologies pose an increasing challenge to network traffic analysis. However, existing traffic classification methods, though effective, require large labeled datasets and complex training. This makes sustaining them prohibitively expensive and difficult in real-world scenarios. To narrow this gap, we propose a novel training-free few-shot network traffic classification framework based on large language models (LLMs). By integrating meta-learning with LLMs, it reduces reliance on labeled data, eliminates task-specific training, and improves performance. Specifically, we first apply an efficient feature extraction method to extract features from traffic flows. We then design meta-tasks that combine task descriptions with textualized features to produce natural language meta-task formulations. Building on these meta-tasks, the LLM performs reasoning to carry out traffic classification. Finally, to mitigate hallucination in the LLM outputs, we exploit the temporal characteristics of network traffic and aggregate predictions over samples within a defined time window. Extensive experiments on three widely-used encrypted traffic datasets demonstrate that our proposed framework outperforms the state-of-the-art methods, achieving an average absolute improvement in F1 score of 9.75, 9.82, and 12.06 percentage points on the three datasets, respectively.
- 16 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
Text-guided Vision Token Reduction with Low-rank Adaptation for Efficient Visual Grounding
Transformer-based pretrained models have advanced Visual Grounding (VG) significantly, but their scaling up has caused soaring training and inference costs. While efforts adapting Parameter-Efficient Fine-Tuning to VG have cut training expenses to some extent, inference costs are over-looked, stemming from Transformer’s computation costs growing quadratically with input token length. To address the above challenge, we propose a text-guided token prune method based on a one-stream architecture for VG, named OneSVG. Specifically, OneSVG transfers low-rank adaptation LoRA to VG, and calculates the relevance between each vision token and text semantics in multiple stages, and gradually prunes the vision tokens with low relevance. In addition, traditional VG methods use a single [REG] token to predict bounding boxes, and the [REG] token relies on complete vision tokens during training, pruning large number of vision tokens will disrupt the spatial orientation information of images. Therefore, the prediction head in OneSVG first restores the square structure of images by padding the missing area, and then accepts complete vision tokens. Experimental results on three widely-used benchmarks demonstrate that our OneSVG achieves state-of-the-art real-time speed while maintaining the best accuracy with only 34.3% tokens. Codes and models are available at https://github.com/ltShi/OneSVG.
- 16 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
Text-guided Vision Token Reduction with Low-rank Adaptation for Efficient Visual Grounding
Transformer-based pretrained models have advanced Visual Grounding (VG) significantly, but their scaling up has caused soaring training and inference costs. While efforts adapting Parameter-Efficient Fine-Tuning to VG have cut training expenses to some extent, inference costs are over-looked, stemming from Transformer’s computation costs growing quadratically with input token length. To address the above challenge, we propose a text-guided token prune method based on a one-stream architecture for VG, named OneSVG. Specifically, OneSVG transfers low-rank adaptation LoRA to VG, and calculates the relevance between each vision token and text semantics in multiple stages, and gradually prunes the vision tokens with low relevance. In addition, traditional VG methods use a single [REG] token to predict bounding boxes, and the [REG] token relies on complete vision tokens during training, pruning large number of vision tokens will disrupt the spatial orientation information of images. Therefore, the prediction head in OneSVG first restores the square structure of images by padding the missing area, and then accepts complete vision tokens. Experimental results on three widely-used benchmarks demonstrate that our OneSVG achieves state-of-the-art real-time speed while maintaining the best accuracy with only 34.3% tokens. Codes and models are available at https://github.com/ltShi/OneSVG.
- 27 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-13
Robust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-tuning and Modality Fusion Prompt Generation
Recently, visual prompt tuning is introduced to RGB-Thermal (RGB-T) tracking as a parameter-efficient finetuning (PEFT) method. However, these PEFT-based RGB-T tracking methods typically rely solely on spatial domain information as prompts for feature extraction. As a result, they often fail to achieve optimal performance by overlooking the crucial role of frequency-domain information in prompt learning. To address this issue, we propose an efficient Visual Fourier Prompt Tracking (named VFPTrack) method to learn modality-related prompts via Fast Fourier Transform (FFT). Our method consists of symmetric feature extraction encoder with shared parameters, visual-fourier prompts, and Modality Fusion Prompt Generator that generates bidirectional interaction prompts through multi-modal feature fusion. Specifically, we first use a frozen feature extraction encoder to extract RGB and thermal infrared (TIR) modality features. Then, we combine the visual prompts in the spatial domain with the frequency domain prompts obtained from the FFT, which allows for the full extraction and understanding of modality features from different domain information. Finally, unlike previous fusion methods, the modality fusion prompt generation module we use combines features from different modalities to generate a fused modality prompt. This modality prompt is interacted with each individual modality to fully enable feature interaction across different modalities. Extensive experiments conducted on three popular RGB-T tracking benchmarks show that our method demonstrates outstanding performance.
- 27 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-13
Robust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-tuning and Modality Fusion Prompt Generation
Recently, visual prompt tuning is introduced to RGB-Thermal (RGB-T) tracking as a parameter-efficient finetuning (PEFT) method. However, these PEFT-based RGB-T tracking methods typically rely solely on spatial domain information as prompts for feature extraction. As a result, they often fail to achieve optimal performance by overlooking the crucial role of frequency-domain information in prompt learning. To address this issue, we propose an efficient Visual Fourier Prompt Tracking (named VFPTrack) method to learn modality-related prompts via Fast Fourier Transform (FFT). Our method consists of symmetric feature extraction encoder with shared parameters, visual-fourier prompts, and Modality Fusion Prompt Generator that generates bidirectional interaction prompts through multi-modal feature fusion. Specifically, we first use a frozen feature extraction encoder to extract RGB and thermal infrared (TIR) modality features. Then, we combine the visual prompts in the spatial domain with the frequency domain prompts obtained from the FFT, which allows for the full extraction and understanding of modality features from different domain information. Finally, unlike previous fusion methods, the modality fusion prompt generation module we use combines features from different modalities to generate a fused modality prompt. This modality prompt is interacted with each individual modality to fully enable feature interaction across different modalities. Extensive experiments conducted on three popular RGB-T tracking benchmarks show that our method demonstrates outstanding performance.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 14335-14344
SACATrack: Joint Scale-Aware and Context-Aware for Robust RGB-T Tracking
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 14335-14344
SACATrack: Joint Scale-Aware and Context-Aware for Robust RGB-T Tracking
- 20 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 6369-6381
Robust Multi-Stage Tracking via Multi-Scale and Multi-Level Representation Learning
How to learn multi-scale and multi-level representations is crucial for robust tracking. However, most current one-stream structure based trackers with visual transformers (dubbed ViTs) cannot effectively capture multi-scale representations due to the structure of their adopted ViTs is non-hierarchical. Meanwhile, they often only use the output features from the final layer for predicting results (i.e., ignoring the utilization of low-level features from the shallow layers) which may result in a certain degree of lacking multi-level representation learning ability. To address these issues, we propose a robust multi-stage tracker that effectively combines the advantages of both hierarchical and one-stream structured ViT as a tracking backbone to improve the multi-scale and multi-level representation learning abilities. Specifically, first of all, we design a hierarchical tracker with a three-stage backbone. In the first two stages of our tracker, we utilize a dual-branch structure to obtain multi-scale features of the template and search region separately. Especially, We design the local scale awareness modules based on simple MLP layers to capture multi-scale features. These modules remove complex operations such as convolutions or shifted window attentions, thus avoiding the performance degradation caused by traditional hierarchical ViTs. In the third stage (i.e. the main stage), we construct a global encoder based on the one-stream ViT to achieve efficient feature extraction and feature interaction for our tracker. Then, we design a multi-level feature integration module in the main stage to explicitly utilize the representation information learned from the shallow layers and fuse them with the features of the final layer to obtain multi-level representation information. Lastly, benefit from the these designs, our tracker can effectively capture more multi-scale and multi-level representations for robust tracking. Comprehensive experiments on GOT-10k, LaSOT, LaSOT$_{ext}$, TNL2K, UAV123, TrackingNet and VOT2020 benchmarks validate the effectiveness and robustness of our method.
- 20 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 6369-6381
Robust Multi-Stage Tracking via Multi-Scale and Multi-Level Representation Learning
How to learn multi-scale and multi-level representations is crucial for robust tracking. However, most current one-stream structure based trackers with visual transformers (dubbed ViTs) cannot effectively capture multi-scale representations due to the structure of their adopted ViTs is non-hierarchical. Meanwhile, they often only use the output features from the final layer for predicting results (i.e., ignoring the utilization of low-level features from the shallow layers) which may result in a certain degree of lacking multi-level representation learning ability. To address these issues, we propose a robust multi-stage tracker that effectively combines the advantages of both hierarchical and one-stream structured ViT as a tracking backbone to improve the multi-scale and multi-level representation learning abilities. Specifically, first of all, we design a hierarchical tracker with a three-stage backbone. In the first two stages of our tracker, we utilize a dual-branch structure to obtain multi-scale features of the template and search region separately. Especially, We design the local scale awareness modules based on simple MLP layers to capture multi-scale features. These modules remove complex operations such as convolutions or shifted window attentions, thus avoiding the performance degradation caused by traditional hierarchical ViTs. In the third stage (i.e. the main stage), we construct a global encoder based on the one-stream ViT to achieve efficient feature extraction and feature interaction for our tracker. Then, we design a multi-level feature integration module in the main stage to explicitly utilize the representation information learned from the shallow layers and fuse them with the features of the final layer to obtain multi-level representation information. Lastly, benefit from the these designs, our tracker can effectively capture more multi-scale and multi-level representations for robust tracking. Comprehensive experiments on GOT-10k, LaSOT, LaSOT$_{ext}$, TNL2K, UAV123, TrackingNet and VOT2020 benchmarks validate the effectiveness and robustness of our method.
- 22 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (10) , 10330-10338
Adaptive Expert Decision for RGB-T Tracking
The features provided by RGB and Thermal Infrared (TIR) images have their own characteristics. Therefore, how to adaptively fuse multi-modal features according to different tracking scenarios is crucial for RGB-T tracking. However, current mainstream RGB-T tracking algorithms often use fixed fusion operations for modal interaction in different scenarios. Consequently, their tracking permanence is deteriorated due to they are unable to dynamically adjust the fused multi-modal features based on the current scenes. To address this issue, we propose a novel RGB-T tracking algorithm called AETrack, which can dynamically extract effective modal features in different scenarios for adaptive fusion. Firstly, we design an adaptive expert decision mechanism that employs multiple experts to process the input features. Each expert focuses on and learns different relevant features. Based on this mechanism, we then propose a feature-guided method that leverages the correlations between modalities to provide cross-modal information. This guidance enables the adaptive expert mechanism to adaptively select the most suitable expert to output effective features based on different scenarios, ensuring that our proposed AETrack prioritizes effective features and thus alleviates interference from irrelevant information. Finally, we design a Progressive Cross-modal Fusion operation to achieve multi-level adaptive fusion of effective features across different modalities. Benefiting from this adaptive fusion process, we can effectively achieve multi-modal interaction in different scenarios to guide robust tracking. Extensive experiments on three popular benchmarks (i.e., LasHeR, RGBT210, RGBT234) show that our proposed AETrack can significantly improve tracking performance.
- 22 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (10) , 10330-10338
Adaptive Expert Decision for RGB-T Tracking
The features provided by RGB and Thermal Infrared (TIR) images have their own characteristics. Therefore, how to adaptively fuse multi-modal features according to different tracking scenarios is crucial for RGB-T tracking. However, current mainstream RGB-T tracking algorithms often use fixed fusion operations for modal interaction in different scenarios. Consequently, their tracking permanence is deteriorated due to they are unable to dynamically adjust the fused multi-modal features based on the current scenes. To address this issue, we propose a novel RGB-T tracking algorithm called AETrack, which can dynamically extract effective modal features in different scenarios for adaptive fusion. Firstly, we design an adaptive expert decision mechanism that employs multiple experts to process the input features. Each expert focuses on and learns different relevant features. Based on this mechanism, we then propose a feature-guided method that leverages the correlations between modalities to provide cross-modal information. This guidance enables the adaptive expert mechanism to adaptively select the most suitable expert to output effective features based on different scenarios, ensuring that our proposed AETrack prioritizes effective features and thus alleviates interference from irrelevant information. Finally, we design a Progressive Cross-modal Fusion operation to achieve multi-level adaptive fusion of effective features across different modalities. Benefiting from this adaptive fusion process, we can effectively achieve multi-modal interaction in different scenarios to guide robust tracking. Extensive experiments on three popular benchmarks (i.e., LasHeR, RGBT210, RGBT234) show that our proposed AETrack can significantly improve tracking performance.
- Top Cited Papers
- 11 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (8) , 7554-7567
AVLTrack: Dynamic Sparse Learning for Aerial Vision-Language Tracking
The introduction of natural language for vision-language (VL) tracking has been proven to improve performance. However, natural language remains under-explored in existing aerial trackers. Moreover, existing VL trackers ignore the misalignment of language with dynamic target states, which is prominent in complex UAV scenarios. In this work, we present AVLTrack, a flexible framework for aerial vision-language tracking. It consists of three key components, a dynamic sparse learning (DSL) module, an efficient Transformer backbone, and a multi-level language perception (MLP) strategy. First, DSL sparsely connects language and images via dynamic sparse attention, providing accurate multi-modal prompts. To adapt to target state variations, the sparsity in DSL is dynamically adjusted based on semantic information, flexibly highlighting target-specific tokens. Next, the Transformer backbone follows highly parallelized one-stream architectures, allowing efficient multi-modal feature extraction and interaction. Finally, MLP enables the iterative interaction of language and visual information, aiming to utilize language priori to guide the generation of discriminative visual features. Moreover, we construct the DTB70-NLP dataset to facilitate UAV vision-language tracking. Extensive experiments on WebUAV-3M and DTB70-NLP demonstrate the leading performance of AVLTrack compared to existing outstanding trackers while maintaining a high running speed of 80.5 FPS. The dataset and codes are available at https://github.com/xyl-507/AVLTrack.
- 11 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (8) , 7554-7567
Top Cited PapersAVLTrack: Dynamic Sparse Learning for Aerial Vision-Language Tracking
The introduction of natural language for vision-language (VL) tracking has been proven to improve performance. However, natural language remains under-explored in existing aerial trackers. Moreover, existing VL trackers ignore the misalignment of language with dynamic target states, which is prominent in complex UAV scenarios. In this work, we present AVLTrack, a flexible framework for aerial vision-language tracking. It consists of three key components, a dynamic sparse learning (DSL) module, an efficient Transformer backbone, and a multi-level language perception (MLP) strategy. First, DSL sparsely connects language and images via dynamic sparse attention, providing accurate multi-modal prompts. To adapt to target state variations, the sparsity in DSL is dynamically adjusted based on semantic information, flexibly highlighting target-specific tokens. Next, the Transformer backbone follows highly parallelized one-stream architectures, allowing efficient multi-modal feature extraction and interaction. Finally, MLP enables the iterative interaction of language and visual information, aiming to utilize language priori to guide the generation of discriminative visual features. Moreover, we construct the DTB70-NLP dataset to facilitate UAV vision-language tracking. Extensive experiments on WebUAV-3M and DTB70-NLP demonstrate the leading performance of AVLTrack compared to existing outstanding trackers while maintaining a high running speed of 80.5 FPS. The dataset and codes are available at https://github.com/xyl-507/AVLTrack.