Andrea Maracani

According to our database, Andrea Maracani authored at least 15 papers between 2020 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Decoding Text Spans for Efficient and Accurate Named-Entity Recognition.

Andrea Maracani, Savas Özkan, Junyi Zhu, Sinan Mutlu, Mete Ozay

CoRR, April, 2026

Geometrically Consistent Multi-View Scene Generation from Freehand Sketches.

Ahmed Bourouis, Savas Özkan, Andrea Maracani, Yi-Zhe Song, Mete Ozay

CoRR, April, 2026

RECALL+: Adversarial web-based replay for continual learning in semantic segmentation.

Chang Liu, Giulia Rizzoli, Francesco Barbato, Andrea Maracani, Marco Toldo, Umberto Michieli, Yi Niu, Pietro Zanuttigh

Image Vis. Comput., 2026

2025

In-domain Self-supervised Learning for Plankton Image Classification on a Budget.

Massimiliano Ciranni, Ani Gjergji, Andrea Maracani, Vittorio Murino, Vito Paolo Pastore

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2025

Efficient and Accurate Scene Text Recognition with Cascaded-Transformers.

Savas Özkan, Andrea Maracani, Mete Ozay, Hyowon Kim, Sijun Cho, Eunchung Noh, Jeongwon Min, Jung Min Cho

Proceedings of the 16th ACM Multimedia Systems Conference, 2025

Multi-Task Pre-Finetuning of Lightweight Transformer Encoders for Text Classification and NER.

Junyi Zhu, Savas Özkan, Andrea Maracani, Sinan Mutlu, Cho Jung Min, Mete Ozay

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillation.

Andrea Maracani, Savas Özkan, Sijun Cho, Hyowon Kim, Eunchung Noh, Jeongwon Min, Cho Jung Min, Dookun Park, Mete Ozay

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

2024

Knowledge Transferability for Data-Efficient Deep Learning.

Andrea Maracani

PhD thesis, 2024

Trust And Balance: Few Trusted Samples Pseudo-Labeling and Temperature Scaled Loss for Effective Source-Free Unsupervised Domain Adaptation.

Andrea Maracani, Lorenzo Rosasco, Lorenzo Natale

CoRR, 2024

Key Design Choices in Source-Free Unsupervised Domain Adaptation: An In-depth Empirical Analysis.

Andrea Maracani, Raffaello Camoriano, Elisa Maiettini, Davide Talon, Lorenzo Rosasco, Lorenzo Natale

CoRR, 2024

Sim2Real Bilevel Adaptation for Object Surface Classification using Vision-Based Tactile Sensors.

Gabriele M. Caddeo, Andrea Maracani, Paolo Didier Alfano, Nicola A. Piga, Lorenzo Rosasco, Lorenzo Natale

Proceedings of the IEEE International Conference on Robotics and Automation, 2024

2023

Key Design Choices for Double-Transfer in Source-Free Unsupervised Domain Adaptation.

Andrea Maracani, Raffaello Camoriano, Elisa Maiettini, Davide Talon, Lorenzo Rosasco, Lorenzo Natale

CoRR, 2023

2022

From Handheld to Unconstrained Object Detection: a Weakly-supervised On-line Learning Approach.

Elisa Maiettini, Andrea Maracani, Raffaello Camoriano, Giulia Pasquale, Vadim Tikhanoff, Lorenzo Rosasco, Lorenzo Natale

Proceedings of the 31st IEEE International Conference on Robot and Human Interactive Communication, 2022

2021

RECALL: Replay-based Continual Learning in Semantic Segmentation.

Andrea Maracani, Umberto Michieli, Marco Toldo, Pietro Zanuttigh

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

2020

Unsupervised Domain Adaptation in Semantic Segmentation: a Review.

Marco Toldo, Andrea Maracani, Umberto Michieli, Pietro Zanuttigh

CoRR, 2020