First Person Vision @ Image Processing Laboratory - University of Catania
- 18 followers
- Catania, Italy
- http://iplab.dmi.unict.it/fpv
Popular repositories Loading
-
DA-RetinaNet
DA-RetinaNet PublicOfficial Detectron2 implementation of DA-RetinaNet, An unsupervised domain adaptation scheme for single-stage artwork recognition in cultural sites, Image and Vision Computing (IMAVIS) 2021
-
STMDA-RetinaNet
STMDA-RetinaNet PublicOfficial Detectron2 implementation of STMDA-RetinaNet, A Multi Camera Unsupervised Domain Adaptation Pipeline for Object Detection in Cultural Sites through Adversarial Learning and Self-Training, …
-
Differentiable-Task-Graph-Learning
Differentiable-Task-Graph-Learning PublicCode for the paper "Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos" [NeurIPS (spotlight), 2024]
Repositories
- ProSkill Public
- ProSKILL_WACV Public
We introduce PROSKILL, the first benchmark dataset for action-level skill assessment in procedural tasks. PROSKILL provides absolute skill assessment annotations, along with pairwise ones.
- ProSKILL-PP Public
- fpv_reading_group Public
- SignIT Public
- EgoInteract Public
EgoInteract is a controllable simulator for generating synthetic egocentric video data with fine-grained spatial and temporal annotations. It supports precise modeling of camera motion, hand-object interactions, and scene dynamics, enabling large-scale dataset generation for tasks such as TAS, NAO detection, and interaction anticipation.
- ENIGMA-360 Public
This repository contains the official data organization and processing tools for the ENIGMA-360 dataset, a multi-view video collection focused on human-object interaction and temporal action segmentation.
- HOI-Synth Public
This repository contains the official implementation, data generation tools, and benchmark datasets for our research on synthetic data for Egocentric Hand-Object Interaction Detection.
Top languages
Loading…
Most used topics
Loading…