Search Results for author:
Found 36 papers, 16 papers with code
Trust And Balance: Few Trusted Samples Pseudo-Labeling and Temperature Scaled Loss for Effective Source-Free Unsupervised Domain Adaptation
Deep Neural Networks have significantly impacted many computer vision tasks.
I2EDL: Interactive Instruction Error Detection and Localization
We evaluate the proposed I2EDL on a dataset of instructions containing errors, and further devise a novel metric, the Success weighted by Interaction Number (SIN), to reflect both the navigation performance and the interaction effectiveness.
The impact of Compositionality in Zero-shot Multi-label action recognition for Object-based tasks
We validate our method on the Charades dataset that includes a majority of object-based actions, demonstrating that -- despite its simplicity -- our method performs favorably with respect to existing methods on the complete dataset, and promising performance when tested on unseen actions.
Action Recognition In Videos
Multi-Label Image Classification
+1
Mind the Error! Detection and Localization of Instruction Errors in Vision-and-Language Navigation
Moreover, we formally define the task of Instruction Error Detection and Localization, and establish an evaluation protocol on top of our benchmark dataset.
Key Design Choices in Source-Free Unsupervised Domain Adaptation: An In-depth Empirical Analysis
This study provides a comprehensive benchmark framework for Source-Free Unsupervised Domain Adaptation (SF-UDA) in image classification, aiming to achieve a rigorous empirical understanding of the complex relationships between multiple key design factors in SF-UDA methods.
ConCon-Chi: Concept-Context Chimera Benchmark for Personalized Vision-Language Tasks
We identify the ability to learn new meanings and their compositionality with known ones as two key properties of a personalized system.
LHManip: A Dataset for Long-Horizon Language-Grounded Manipulation Tasks in Cluttered Tabletop Environments
Instructing a robot to complete an everyday task within our homes has been a long-standing challenge for robotics.
Sim2Real Bilevel Adaptation for Object Surface Classification using Vision-Based Tactile Sensors
Our evaluation is conducted on a dataset of tactile images obtained from a set of ten 3D printed YCB objects.
Self-improving object detection via disagreement reconciliation
Object detectors often experience a drop in performance when new environmental conditions are insufficiently represented in the training data.
Key Design Choices for Double-Transfer in Source-Free Unsupervised Domain Adaptation
Fine-tuning and Domain Adaptation emerged as effective strategies for efficiently transferring deep learning models to new target tasks.
Look Around and Learn: Self-Training Object Detection by Exploration
When an object detector is deployed in a novel setting it often experiences a drop in performance.
Collision-aware In-hand 6D Object Pose Estimation using Multiple Vision-based Tactile Sensors
The results demonstrate that our approach estimates object poses that are compatible with actual object-sensor contacts in $87. 5\%$ of cases while reaching an average positional error in the order of $2$ centimeters.
Towards Confidence-guided Shape Completion for Robotic Applications
Many robotic tasks involving some form of 3D visual perception greatly benefit from a complete knowledge of the working environment.
Learn Fast, Segment Well: Fast Object Segmentation Learning on the iCub Robot
In this work, we focus on the instance segmentation task and provide a comprehensive study of different techniques that allow adapting an object segmentation model in presence of novel objects or different domains.
Grasp Pre-shape Selection by Synthetic Training: Eye-in-hand Shared Control on the Hannes Prosthesis
In order to overcome the lack of data of this kind and reduce the need for tedious data collection sessions for training the system, we devise a pipeline for rendering synthetic visual sequences of hand trajectories.
ROFT: Real-Time Optical Flow-Aided 6D Object Pose and Velocity Tracking
In this work, we introduce ROFT, a Kalman filtering approach for 6D object pose and velocity tracking from a stream of RGB-D images.
Active Perception for Ambiguous Objects Classification
We also describe a complete pipeline from a real object's scans to the viewpoint selection and classification.
From Handheld to Unconstrained Object Detection: a Weakly-supervised On-line Learning Approach
We show that the robot can improve adaptation to novel domains, either by interacting with a human teacher (Active Learning) or with an autonomous supervision (Semi-supervised Learning).
Fast Region Proposal Learning for Object Detection for Robotics
This shortens training time while maintaining state-of-the-art performance.
Fast Object Segmentation Learning with Kernel-based Methods for Robotics
Our approach is validated on the YCB-Video dataset which is widely adopted in the computer vision and robotics community, demonstrating that we can achieve and even surpass performance of the state-of-the-art, with a significant reduction (${\sim}6\times$) of the training time.
Compact Belief State Representation for Task Planning
The performance of a task planner relies on the belief state representation.
GRASPA 1.0: GRASPA is a Robot Arm graSping Performance benchmArk
In this paper, we present version 1. 0 of GRASPA, a benchmark to test effectiveness of grasping pipelines on physical robot setups.
Robotics
Learning latent state representation for speeding up exploration
In this work, we take a representation learning viewpoint on exploration, utilizing prior experience to learn effective latent representations, which can subsequently indicate which regions to explore.
Speeding-up Object Detection Training for Robotics with FALKON
We address the size and imbalance of training data by exploiting the stochastic subsampling intrinsic into the method and a novel, fast, bootstrapping approach.
Markerless visual servoing on unknown objects for humanoid robot platforms
To precisely reach for an object with a humanoid robot, it is of central importance to have good knowledge of both end-effector, object pose and shape.
Robotics Systems and Control Computation
Are we done with object recognition? The iCub robot's perspective
We report on an extensive study of the benefits and limitations of current deep learning approaches to object recognition in robot vision scenarios, introducing a novel dataset used for our investigation.
Independent Motion Detection with Event-driven Cameras
In this paper, we propose a method for segmenting the motion of an independently moving object for event-driven cameras.
Controlled Tactile Exploration and Haptic Object Recognition
The method is composed of a grasp stabilization controller and two exploratory behaviours to capture the shape and the softness of an object.
Visual end-effector tracking using a 3D model-aided particle filter for humanoid robot platforms
This paper addresses recursive markerless estimation of a robot's end-effector using visual observations from its cameras.
Robotics
Mobility Map Computations for Autonomous Navigation using an RGBD Sensor
In recent years, the numbers of life-size humanoids as well as their mobile capabilities have steadily grown.
Intelligent Biohybrid Neurotechnologies: Are They Really What They Claim?
In the era of intelligent biohybrid neurotechnologies for brain repair, new fanciful terms are appearing in the scientific dictionary to define what has so far been unimaginable.
Incremental Robot Learning of New Objects with Fixed Update Time
We consider object recognition in the context of lifelong learning, where a robotic agent learns to discriminate between a growing number of object classes as it accumulates experience about the environment.
Enabling Depth-driven Visual Attention on the iCub Humanoid Robot: Instructions for Use and New Perspectives
The importance of depth perception in the interactions that humans have within their nearby space is a well established fact.
Real-world Object Recognition with Off-the-shelf Deep Conv Nets: How Many Objects can iCub Learn?
In this paper we investigate such possibility, while taking further steps in developing a computational vision system to be embedded on a robotic platform, the iCub humanoid robot.
Gaze Stabilization for Humanoid Robots: a Comprehensive Framework
In this work we propose a comprehensive framework for gaze stabilization in a humanoid robot.
iCub World: Friendly Robots Help Building Good Vision Data-Sets
In this paper we present and start analyzing the iCub World data-set, an object recognition data-set, we acquired using a Human-Robot Interaction (HRI) scheme and the iCub humanoid robot platform.
