Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks31 from public data
- Borderline SMOTE Algorithm and Feature Selection-Based Network Anomalies Detection Strategy54
The network anomaly detection strategy proposed in this paper solves the problem of multiple classification of network intrusion and develops a resampling strategy generated by random sampling and Borderline SMOTE data for data balance.
- Review on Video Object Tracking Based on Deep Learning35
In this paper, the existing deep tracking-based target tracking algorithms are classified and sorted out, and several solutions are proposed for the existing methods.
- 27
- Dynamic data-free knowledge distillation by easy-to-hard learning strategy22
This work proposes a novel DFKD method called CuDFKD that teaches students by a dynamic strategy that gradually generates easy-to-hard pseudo samples, mirroring how humans learn and has the fastest convergence and best robustness over other SOTA DFKKD methods.
- 18
- Identifying influential nodes based on graph signal processing in complex networks17
The results show that the GSPC method effectively identifies influential nodes, which correspond well with the underlying ground truth, and is compatible to the previous eigenvector centrality and principal component centrality methods under circumstances where the nodes are homogeneous.
- A Dual Recurrent Neural Network-based Hybrid Approach for Solving Convex Quadratic Bi-Level Programming Problem14
A neural network-based hybrid strategy that combines a Genetic Algorithm and a Dual Recurrent Neural Network for efficiently and accurately solving the quadratic-Bi-level Programming Problem (BLPP).
- 11
- 10
- AdaDFKD: Exploring adaptive inter-sample relationship in data-free knowledge distillation5
This study introduces a novel DFKD approach known as AdaDFKD, designed to establish and utilize relationships among pseudo samples, which is adaptive to the student model, and finally effectively mitigates the aforementioned risk.
- Deep Generative Knowledge Distillation by Likelihood Finetuning4
A new DFKD framework called Generative Knowledge Distillation (GenKD) is proposed that reduces the search space by constructing a prior distribution modeled by DGMs for their power of likelihood estimation and can generate high-quality pseudo samples quantitatively and qualitatively using it.
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 1
- 1
- Optical-fusion attention network for dynamic prediction of children's language learning progress and optical signal-driven personalized teaching strategies–
A hierarchical attention network optimized to weight key learning indicators, including vocabulary retention, grammatical accuracy, and task completion dynamics, for real-time proficiency trend prediction and its effectiveness in balancing personalization and computational efficiency for practical educational implementations is demonstrated.
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.