Journals
Marsocci, V., Scardapane, S. "Continual Barlow Twins: Continual Self-Supervised Learning for Remote Sensing Semantic Segmentation," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, doi: 10.1109/JSTARS.2023.3280029. Link
Valerio Marsocci, Virginia Coletta, Roberta Ravanelli, Simone Scardapane, Mattia Crespi, Inferring 3D change detection from bitemporal optical images, ISPRS Journal of Photogrammetry and Remote Sensing, Volume 196, 2023, Pages 325-339, ISSN 0924-2716. Link - arXiv.
Marsocci, V., Scardapane, S., & Komodakis, N. (2021). MARE: Self-Supervised Multi-Attention REsu-Net for Semantic Segmentation in Remote Sensing. Remote Sensing, 13(16), 3275. Link
Marsocci, V., & Lastilla, L. (2021). POSE-ID-on—A Novel Framework for Artwork Pose Clustering. ISPRS International Journal of Geo-Information, 10(4), 257. Link
Conferences
Valerio Marsocci, Nicolas Gonthier, Anatol Garioud, Simone Scardapane, Clément Mallet; GeoMultiTaskNet: Remote Sensing Unsupervised Domain Adaptation Using Geographical Coordinates. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 2074-2084. Link
H. Moieez, V. Marsocci and S. Scardapane, "Continual Self-Supervised Learning in Earth Observation with Embedding Regularization," IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Pasadena, CA, USA, 2023, pp. 5029-5032, doi: 10.1109/IGARSS52108.2023.10283121. Link
Coletta, V., Marsocci, V., & Ravanelli, R. (2022). 3DCD: A NEW DATASET FOR 2D AND 3D CHANGE DETECTION USING DEEP LEARNING TECHNIQUES. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 43, 1349-1354. Link
Preprints
Marsocci, V., & Audebert, N. (2024). Cross-sensor self-supervised training and alignment for remote sensing. arXiv preprint arXiv:2405.09922. Link
Scardapane, S., Baiocchi, A., Devoto, A., Marsocci, V., Minervini, P., & Pomponi, J. (2024). Conditional computation in neural networks: principles and research trends. arXiv preprint arXiv:2403.07965. Link