Rising Senior (B.Eng. in Intelligent Science and Technology) · Computer Vision · Federated Learning · Multimodal Learning · Edge Computing
I am currently seeking an on-site or remote research internship for my final undergraduate year (2025 – 2026).
I would be grateful for the chance to contribute to research in computer vision, multimodal learning, or multi-agent systems.
Please feel free to reach out via email if my background aligns with your research objectives.
- 🎥 Video Anomaly Detection
- 🌐 Federated Learning / Edge Computing
- 🤖 Weakly Supervised Learning
- 🖼 Image & Video Processing
- Developing advanced algorithms for robust weakly supervised video anomaly detection.
- Designing federated learning methods to address privacy and data heterogeneity in cross-scene video anomaly detection.
| 📅 Date | 📜 Publication Title | 🏛 Venue | 🔗 Links |
|---|---|---|---|
| Jun 2025 | Dual-detector Re-optimization for Federated Weakly Supervised Video Anomaly Detection via Adaptive Dynamic Recursive Mapping | IEEE Trans. Ind. Inform. 2025 | 📄 Paper 💻 GitHub 🌐 Project Page |
| May 2025 | Federated Weakly-Supervised Video Anomaly Detection with Mixture of Local-to-Global Experts | Inf. Fusion 2025 | 📄 Paper |
| Apr 2025 | Gaze-Guided Learning: Avoiding Shortcut Bias in Visual Classification | pre print | 📄 Paper 💻 GitHub 🌐 Project Page 🗂️ Dataset |
| Mar 2025 | View-Robust Backbone and Discriminative Reconstruction for Few-Shot Fine-Grained Image Classification | IJCNN 2025 (Oral) | 📄 Paper coming soon 💻 GitHub |
| 🛠 Role | 🏟 Venues / Workshops |
|---|---|
| Journal Reviewer | EAAI, Ad Hoc Netw |
| Conference Reviewer | BMVC 2025, IJCNN 2025, CogSci 2025, AOM 2025 |
| Workshop Reviewer | PUT@ICML 2025, WCUA@ICML 2025, SVU@ICCV 2025 |
🎙️ Beyond research, I have a passion for dubbing, especially for anime characters. 🎬
📧 lijiahang041119[at]gmail[dot]com
Feel free to reach out for academic collaboration or discussions!