First Person Vision @ Image Processing Laboratory - University of Catania's repositories
DA-RetinaNet
Official Detectron2 implementation of DA-RetinaNet of our Image and Vision Computing 2021 work 'An unsupervised domain adaptation scheme for single-stage artwork recognition in cultural sites'
STMDA-RetinaNet
Official Detectron2 implementation of STMDA-RetinaNet of our Computer Vision and Image Understanding 2022 work 'A Multi Camera Unsupervised Domain Adaptation Pipeline for Object Detection in Cultural Sites through Adversarial Learning and Self-Training'
action-anticipation-losses
Implements the loss used in A. Furnari, S. Battiato, G. M. Farinella (2018). Leveraging Uncertainty to Rethink Loss Functions and Evaluation Measures for Egocentric Action Anticipation . In International Workshop on Egocentric Perception, Interaction and Computing (EPIC) in conjunction with ECCV .
synchronization-is-all-you-need
Synchronization is All You Need: Exocentric-to-Egocentric Transfer for Temporal Action Segmentation with Unlabeled Synchronized Video Pairs
WMM-detection-for-visual-navigation-systems
Code and documentation of the paper World-map misalignment detection for visual navigation systems
Quasi-Online-Detection-Take-Release
Code for the Paper: Quasi-Online Detection of Take and Release Actions from Egocentric Videos. International Conference on Image Analysis and Processing 2023.
WS-Attended-Object-Detection
Code of the paper Weakly Supervised Attended Object Detection Using Gaze Data as Annotations