254 citations · 390 across the 30 of their papers we have counts for
34 papers
Integrating Affordances and Attention models for Short-Term Object Interaction Anticipation
Lorenzo Mur Labadia, Ruben Martinez-Cantin, Jose J. Guerrero +2
Short Term object-interaction Anticipation consists in detecting the location of the next active objects, the noun and verb categories of the interaction, as well as the time to co…
O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views
Lorenzo Mur-Labadia, Maria Santos-Villafranca, Jesus Bermudez-Cameo +3
Understanding the world from multiple perspectives is essential for intelligent systems operating together, where segmenting common objects across different views remains an open p…
DIV-FF: Dynamic Image-Video Feature Fields For Environment Understanding in Egocentric Videos
Lorenzo Mur-Labadia, Josechu Guerrero, Ruben Martinez-Cantin
Environment understanding in egocentric videos is an important step for applications like robotics, augmented reality and assistive technologies. These videos are characterized by…
FALCONEye: Finding Answers and Localizing Content in ONE-hour-long videos with multi-modal LLMs
Carlos Plou, Cesar Borja, Ruben Martinez-Cantin +1
Finding information in hour-long videos is a challenging task even for top-performing Vision Language Models (VLMs), as encoding visual content quickly exceeds available context wi…
Influence of field of view in visual prostheses design: Analysis with a VR system
Melani Sanchez-Garcia, Ruben Martinez-Cantin, Jesus Bermudez-Cameo +1
Visual prostheses are designed to restore partial functional vision in patients with total vision loss. Retinal visual prostheses provide limited capabilities as a result of low re…
Bayesian optimization for robust robotic grasping using a sensorized compliant hand
Juan G. Lechuz-Sierra, Ana Elvira H. Martin, Ashok M. Sundaram +2
One of the first tasks we learn as children is to grasp objects based on our tactile perception. Incorporating such skill in robots will enable multiple applications, such as incre…
Gen-Swarms: Adapting Deep Generative Models to Swarms of Drones
Carlos Plou, Pablo Pueyo, Ruben Martinez-Cantin +3
Gen-Swarms is an innovative method that leverages and combines the capabilities of deep generative models with reactive navigation algorithms to automate the creation of drone show…
ZARRIO @ Ego4D Short Term Object Interaction Anticipation Challenge: Leveraging Affordances and Attention-based models for STA
Lorenzo Mur-Labadia, Ruben Martinez-Cantin, Josechu Guerrero-Campo +1
Short-Term object-interaction Anticipation (STA) consists of detecting the location of the next-active objects, the noun and verb categories of the interaction, and the time to con…
CARLOR @ Ego4D Step Grounding Challenge: Bayesian temporal-order priors for test time refinement
Carlos Plou, Lorenzo Mur-Labadia, Ruben Martinez-Cantin +1
The goal of the Step Grounding task is to locate temporal boundaries of activities based on natural language descriptions. This technical report introduces a Bayesian-VSLNet to add…
AFF-ttention! Affordances and Attention models for Short-Term Object Interaction Anticipation
Lorenzo Mur-Labadia, Ruben Martinez-Cantin, Josechu Guerrero +2
Short-Term object-interaction Anticipation consists of detecting the location of the next-active objects, the noun and verb categories of the interaction, and the time to contact f…
Active Exploration in Bayesian Model-based Reinforcement Learning for Robot Manipulation
Carlos Plou, Ana C. Murillo, Ruben Martinez-Cantin
Efficiently tackling multiple tasks within complex environments, such as those found in robot manipulation, remains an ongoing challenge in robotics and an opportunity for data-dri…
EventSleep: Sleep Activity Recognition with Event Cameras
Carlos Plou, Nerea Gallego, Alberto Sabater +5
Event cameras are a promising technology for activity recognition in dark environments due to their unique properties. However, real event camera datasets under low-lighting condit…
Finding safe 3D robot grasps through efficient haptic exploration with unscented Bayesian optimization and collision penalty
Joao Castanheira, Pedro Vicente, Ruben Martinez-Cantin +2
Robust grasping is a major, and still unsolved, problem in robotics. Information about the 3D shape of an object can be obtained either from prior knowledge (e.g., accurate models…
Bayesian Optimization with Adaptive Kernels for Robot Control
Ruben Martinez-Cantin
Active policy search combines the trial-and-error methodology from policy search with Bayesian optimization to actively find the optimal policy. First, policy search is a type of r…
Gaussian Mixture Models for Affordance Learning using Bayesian Networks
Pedro Osório, Alexandre Bernardino, Ruben Martinez-Cantin +1
Affordances are fundamental descriptors of relationships between actions, objects and effects. They provide the means whereby a robot can predict effects, recognize actions, select…
Body Schema Acquisition through Active Learning
Ruben Martinez-Cantin, Manuel Lopes, Luis Montesano
We present an active learning algorithm for the problem of body schema learning, i.e. estimating a kinematic model of a serial robot. The learning process is done online using Recu…
Multi-label affordance mapping from egocentric vision
Lorenzo Mur-Labadia, Jose J. Guerrero, Ruben Martinez-Cantin
Accurate affordance detection and segmentation with pixel precision is an important piece in many complex systems based on interactions, such as robots and assitive devices. We pre…
Bayesian Deep Learning for Affordance Segmentation in images
Lorenzo Mur-Labadia, Ruben Martinez-Cantin, Jose J. Guerrero
Affordances are a fundamental concept in robotics since they relate available actions for an agent depending on its sensory-motor capabilities and the environment. We present a nov…
Robust Fusion for Bayesian Semantic Mapping
David Morilla-Cabello, Lorenzo Mur-Labadia, Ruben Martinez-Cantin +1
The integration of semantic information in a map allows robots to understand better their environment and make high-level decisions. In the last few years, neural networks have sho…
Assessing visual acuity in visual prostheses through a virtual-reality system
Melani Sanchez-Garcia, Roberto Morollon-Ruiz, Ruben Martinez-Cantin +2
Current visual implants still provide very low resolution and limited field of view, thus limiting visual acuity in implanted patients. Developments of new strategies of artificial…
Augmented reality navigation system for visual prosthesis
Melani Sanchez-Garcia, Alejandro Perez-Yus, Ruben Martinez-Cantin +1
The visual functions of visual prostheses such as field of view, resolution and dynamic range, seriously restrict the person's ability to navigate in unknown environments. Implante…
Bayesian deep learning of affordances from RGB images
Lorenzo Mur-Labadia, Ruben Martinez-Cantin
Autonomous agents, such as robots or intelligent devices, need to understand how to interact with objects and its environment. Affordances are defined as the relationships between…
Robust Policy Search for Robot Navigation
Javier Garcia-Barcos, Ruben Martinez-Cantin
Complex robot navigation and control problems can be framed as policy search problems. However, interactive learning in uncertain environments can be expensive, requiring the use o…
Fully Distributed Bayesian Optimization with Stochastic Policies
Javier Garcia-Barcos, Ruben Martinez-Cantin
Bayesian optimization has become a popular method for high-throughput computing, like the design of computer experiments or hyperparameter tuning of expensive models, where sample…