Search Results for author:
Found 14 papers, 5 papers with code
Removing supervision in semantic segmentation with local-global matching and area balancing
Our model attains state-of-the-art in Weakly Supervised Semantic Segmentation, only image-level labels, with 75% mIoU on PascalVOC2012 val set and 46% on MS-COCO2014 val set.
Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation
On the other hand, WSSS methods based on Vision Transformers (ViT) have not yet explored valid alternatives to CAM.
Spatio-Temporal SAR-Optical Data Fusion for Cloud Removal via a Deep Hierarchical Model
Cloud removal is a relevant topic in Remote Sensing as it fosters the usability of high-resolution optical images for Earth monitoring and study.
3D Multi-Robot Patrolling with a Two-Level Coordination Strategy
This target selection relies on a shared idleness representation and a coordination mechanism preventing topological conflicts.
Visual search and recognition for robot task execution and monitoring
Visual search of relevant targets in the environment is a crucial robot skill.
Deep execution monitor for robot assistive tasks
We consider a novel approach to high-level robot task execution for a robot assistive task.
Anticipation and next action forecasting in video: an end-to-end model with memory
Action anticipation and forecasting in videos do not require a hat-trick, as far as there are signs in the context to foresee how actions are going to be deployed.
A Hybrid Approach for Trajectory Control Design
This work presents a methodology to design trajectory tracking feedback control laws, which embed non-parametric statistical models, such as Gaussian Processes (GPs).
Discovery and recognition of motion primitives in human activities
Given new video data and given the estimated pose of the subject appearing on the video, the motion is segmented into primitives, which are recognized with a probability given according to the parameters of the learned models.
Vision-based deep execution monitoring
Execution monitor of high-level robot actions can be effectively improved by visual monitoring the state of the world in terms of preconditions and postconditions that hold before and after the execution of an action.
Single Image Object Modeling Based on BRDF and R-Surfaces Learning
A methodology for 3D surface modeling from a single image is proposed.
Confidence driven TGV fusion
We introduce a novel model for spatially varying variational data fusion, driven by point-wise confidence values.
Bayesian Non-Parametric Inference for Manifold Based MoCap Representation
We propose a novel approach to human action recognition, with motion capture data (MoCap), based on grouping sub-body parts.
Component-Wise Modeling of Articulated Objects
We introduce a novel framework for modeling articulated objects based on the aspects of their components.
