About me

I’m currently at my second Postdoc position as a Researcher in Artificial Intelligence at the Division of Robotics, Perception and Learning (RPL) of KTH Royal Institute of Technology, in Stockholm. Until mid 2025, I was a Postdoc at the Computer Science Department of Sapienza University of Rome. My research lies at the intersection of Computer Vision, Continual Learning, and Representation Learning.

I hold a PhD from the Italian National PhD in Artificial Intelligence program, where I deepened my expertise in AI and Deep Learning. My doctoral research, titled “Sparking Light on Deep Learning in EEG Research”, critically examined the recent success of neural networks in physiological signal analysis, highlighting and challenging some of the more surprising claims in the field.

Before pursuing my PhD, I earned both my BSc and MSc in Computer Science at Sapienza, graduating with honors. My master’s thesis, “Laplacian-regularized Transductive Inference for Few-shot Object Detection”, was supervised by Prof. Fabio Galasso.

Beyond research, I actively contribute to the academic community. I serve as a reviewer for top-tier conferences and journals such as ICCV, NeurIPS, IEEE Transactions on Multimedia, and Nature Scientific Reports, and co-organize workshops at major venues, including BISCUIT and VisionDocs at ICCV’25.

You can find my complete CV here.

News

You can find an updated list of news about me on my LinkedIn profile.

2025

September

Just started my second Postdoc position, this time at KTH!

May

Our proposed workshops, BISCUIT and VisionDocs have been accepted at ICCV’25

January

Finally defended my PhD thesis “Sparking Light on Deep Learning in EEG Research” in front of the committee

2024

July

Proud to have won a best presentation award at the poster competition at the International Computer Vision Summer School (ICVSS’24)

Organized workshops

BISCUIT @ ICCV’25
^{1st International Workshop on Biomedical Image and Signal Computing for Unbiasedness, Interpretability, and Trustworthiness}
VisionDocs @ ICCV’25
^{2nd Workshop on Computer Vision Systems for Document Analysis and Recognition}

Selected publications

You can find a complete list of my articles on my Google Scholar profile.

Conferences

Towards Multi-View Hand Pose Recognition Using a Fusion of Image Embeddings and Leap 2 Landmarks

Esteban-Romero, S., Lanzino, R., Marini, M. R., & Gil-Martín, M. (2025). Towards Multi-View Hand Pose Recognition Using a Fusion of Image Embeddings and Leap 2 Landmarks. Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART, 918–925. doi:10.5220/0013234300003890

CycleBNN: Cyclic Precision Training in Binary Neural Networks

Fontana, F., Lanzino, R., Diko, A., Foresti, G. L., & Cinque, L. (2025). CycleBNN: Cyclic Precision Training in Binary Neural Networks. In A. Del Bue, C. Canton, J. Pont-Tuset, & T. Tommasi (Eds.), Computer Vision -- ECCV 2024 Workshops (pp. 113–130). Cham: Springer Nature Switzerland.

NT-ViT: Neural Transcoding Vision Transformers for EEG-to-fMRI Synthesis

Lanzino, R., Fontana, F., Cinque, L., Scarcello, F., & Maki, A. (2025). Neural Transcoding Vision Transformers for EEG-to-fMRI Synthesis. In A. Del Bue, C. Canton, J. Pont-Tuset, & T. Tommasi (Eds.), Computer Vision -- ECCV 2024 Workshops (pp. 53–70). Cham: Springer Nature Switzerland.

LieToMe: An LSTM-Based Method for Deception Detection by Hand Movements

Avola, D., Cinque, L., De Marsico, M., Di Mambro, A., Fagioli, A., Foresti, G. L., Lanzino, R., … Scarcello, F. (2023). LieToMe: An LSTM-Based Method for Deception Detection by Hand Movements. In G. L. Foresti, A. Fusiello, & E. Hancock (Eds.), Image Analysis and Processing -- ICIAP 2023 (pp. 387–398). Cham: Springer Nature Switzerland.

Faster Than Lies: Real-time Deepfake Detection using Binary Neural Networks

Lanzino, R., Fontana, F., Diko, A., Marini, M. R., & Cinque, L. (2024). Faster Than Lies: Real-time Deepfake Detection using Binary Neural Networks. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 3771–3780. doi:10.1109/CVPRW63382.2024.00381

The NuragAI project: Artificial Intelligence-driven image analysis of Sardinia landscape, searching for unknown monuments

Palombini, A., Baiocchi, E., Lanzino, R., Malatesta, S. G., Marini, M. R., & Rosati, P. (2023). The NuragAI project: Artificial Intelligence-driven Image Analysis of Sardinia Landscape, Searching for Unknown Monuments. In A. Bucciero, B. Fanini, H. Graf, S. Pescarin, & S. Rizvic (Eds.), Eurographics Workshop on Graphics and Cultural Heritage. doi:10.2312/gch.20231179

Journals

Distilled Gradual Pruning With Pruned Fine-Tuning

Fontana, F., Lanzino, R., Marini, M. R., Avola, D., Cinque, L., Scarcello, F., & Foresti, G. L. (2024). Distilled Gradual Pruning With Pruned Fine-Tuning. IEEE Transactions on Artificial Intelligence, 5(8), 4269–4279. doi:10.1109/TAI.2024.3366497

Multi-Stream 1D CNN for EEG Motor Imagery Classification of Limbs Activation

Avola, D., Cinque, L., Di Mambro, A., Lanzino, R., Pannone, D., & Scarcello, F. (2024). Multi-Stream 1D CNN for EEG Motor Imagery Classification of Limbs Activation. IEEE Access, 12, 83940–83951. doi:10.1109/ACCESS.2024.3412710

SATEER: Subject-Aware Transformer for EEG-Based Emotion Recognition

Lanzino, R., Avola, D., Fontana, F., Cinque, L., Scarcello, F., & Foresti, G. L. (2024). SATEER: Subject-Aware Transformer for EEG-Based Emotion Recognition. International journal of neural systems, 2550002. Advance online publication. https://doi.org/10.1142/S0129065725500029

A Novel Transformer-Based IMU Self-Calibration Approach through On-Board RGB Camera for UAV Flight Stabilization

Avola, D., Cinque, L., Foresti, G. L., Lanzino, R., Marini, M. R., Mecca, A., & Scarcello, F. (2023). A Novel Transformer-Based IMU Self-Calibration Approach through On-Board RGB Camera for UAV Flight Stabilization. Sensors, 23(5), 2655. https://doi.org/10.3390/s23052655

A Novel GAN-Based Anomaly Detection and Localization Method for Aerial Video Surveillance at Low Altitude

Avola, D., Cannistraci, I., Cascio, M., Cinque, L., Diko, A., Fagioli, A., Foresti, G. L., Lanzino, R., Mancini, M., Mecca, A., & Pannone, D. (2022). A Novel GAN-Based Anomaly Detection and Localization Method for Aerial Video Surveillance at Low Altitude. Remote Sensing, 14(16), 4110. https://doi.org/10.3390/rs14164110

Romeo Lanzino