Li Li
Research Subjects
Research Interests
Li Li has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Caiming Zhang
School of Software, Shandong University, Jinan, China
1 shared publication Faqiang Huang
1 shared publication- Honghao Dai
School of Software, Shandong University, Jinan, 250101, China
1 shared publication Lei Li
1 shared publication- Shanshan Gao
School of Computer Science and Technology, Shandong University of Finance and Economics, China
1 shared publication - Shuheng Lyu1 shared publication
Latest Publications
- Open Access
- 11 July 2026
- Published by Elsevier in SSRN Electronic Journal
KPN: Keypoint Network for Semi‑Supervised Small Object Detection
Small objects occupy a very small proportion of pixels in images, making feature extraction difficult. This leads to existing neural networks struggling to accurately determine the location and category of small objects. Meanwhile, it is difficult to manually label the position and category of small objects, which makes the small objects lack of enough high-quality datasets. Most of the existing solutions rely on additional auxiliary branches to focus on the enhancement of spatial domain features, the model generalization ability is weak and the detection performance is heavily dependent on high-quality data sets. Therefore, we design a semi supervised detection algorithm KPN (Keypoint Network) for small targets, which uses custom keypoints to solve the problem of small target localization with limited labeled data. Specifically, we rethink the definition and role of keypoints, and thus define three types of keypoints to guide the network in accurately localizing small objects: the object center point for bounding box positioning, the object presence point with the highest probability in the heatmap and the adaptive point with strong response from the backbone network. Additionally, to address the difficulty of feature extraction of small targets, we introduce the frequency domain supplement module to focus on the frequency domain feature enhancement. Finally, we propose a joint confidence estimation and an adaptive thresholding strategy to resolve pseudo-label ambiguity. The experimental results confirm the superiority of our approach against other advanced methods, showing significant performance gains in small object detection.
- 11 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessKPN: Keypoint Network for Semi‑Supervised Small Object Detection
Small objects occupy a very small proportion of pixels in images, making feature extraction difficult. This leads to existing neural networks struggling to accurately determine the location and category of small objects. Meanwhile, it is difficult to manually label the position and category of small objects, which makes the small objects lack of enough high-quality datasets. Most of the existing solutions rely on additional auxiliary branches to focus on the enhancement of spatial domain features, the model generalization ability is weak and the detection performance is heavily dependent on high-quality data sets. Therefore, we design a semi supervised detection algorithm KPN (Keypoint Network) for small targets, which uses custom keypoints to solve the problem of small target localization with limited labeled data. Specifically, we rethink the definition and role of keypoints, and thus define three types of keypoints to guide the network in accurately localizing small objects: the object center point for bounding box positioning, the object presence point with the highest probability in the heatmap and the adaptive point with strong response from the backbone network. Additionally, to address the difficulty of feature extraction of small targets, we introduce the frequency domain supplement module to focus on the frequency domain feature enhancement. Finally, we propose a joint confidence estimation and an adaptive thresholding strategy to resolve pseudo-label ambiguity. The experimental results confirm the superiority of our approach against other advanced methods, showing significant performance gains in small object detection.
- Open Access
- 1 January 2026
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 2026 (1)
MSA‐xLSTM: Multimodal Stock Price Forecasting With Multiscale Emotional Attention and Extended LSTM
Financial time series forecasting is a long‐standing challenge due to the high complexity, randomness, and nonstationary of data. While predictions are typically made based on historical data with multiple features, existing models often fail to effectively integrate and utilize these diverse inputs, limiting forecasting accuracy. To address this, we propose MSA‐xLSTM, a multimodal stock price prediction model incorporating a sentiment attention mechanism. This model is designed to enhance the integration of sentiment features and technical indicators through a multiscale processing approach and sentiment attention module. Specifically, sentiment index sequences are extracted from textual sources such as financial news and stock comments. For technical indicators, both basic and derived metrics are analyzed for correlation with the prediction target, and only highly relevant ones are selected. We validate the effectiveness of each model component through comparative and ablation experiments. Furthermore, backtesting experiments demonstrate the model’s practical value in real‐world trading scenarios.
- 1 January 2026
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 2026 (1)
Open AccessMSA‐xLSTM: Multimodal Stock Price Forecasting With Multiscale Emotional Attention and Extended LSTM
Financial time series forecasting is a long‐standing challenge due to the high complexity, randomness, and nonstationary of data. While predictions are typically made based on historical data with multiple features, existing models often fail to effectively integrate and utilize these diverse inputs, limiting forecasting accuracy. To address this, we propose MSA‐xLSTM, a multimodal stock price prediction model incorporating a sentiment attention mechanism. This model is designed to enhance the integration of sentiment features and technical indicators through a multiscale processing approach and sentiment attention module. Specifically, sentiment index sequences are extracted from textual sources such as financial news and stock comments. For technical indicators, both basic and derived metrics are analyzed for correlation with the prediction target, and only highly relevant ones are selected. We validate the effectiveness of each model component through comparative and ablation experiments. Furthermore, backtesting experiments demonstrate the model’s practical value in real‐world trading scenarios.