Search Results for author:
Found 13 papers, 9 papers with code
in2IN: Leveraging individual Information to Generate Human INteractions
For this, we introduce in2IN, a novel diffusion model for human-human motion generation which is conditioned not only on the textual description of the overall interaction but also on the individual descriptions of the actions performed by each person involved in the interaction.
Ranked #1 on
Motion Synthesis
on InterHuman
(using extra training data)
Self-supervised Vision Transformers for 3D Pose Estimation of Novel Objects
This work evaluates and demonstrates the differences between self-supervised CNNs and Vision Transformers for deep template matching.
Exploiting the relationship between visual and textual features in social networks for image classification with zero-shot deep learning
The results obtained demonstrated that trained neural networks such as CLIP can be successfully applied to image classification with little fine-tuning, and considering the associated texts to the images can help to improve the accuracy depending on the goal.
UnrealROX+: An Improved Tool for Acquiring Synthetic Data from Virtual 3D Environments
Synthetic data generation has become essential in last years for feeding data-driven algorithms, which surpassed traditional techniques performance in almost every computer vision problem.
H-GAN: the power of GANs in your Hands
Relying on image-to-image translation, we improve the appearance of synthetic hands to approximate the statistical distribution underlying a collection of real images of hands.
A Review on Deep Learning Techniques for Video Prediction
The ability to predict, anticipate and reason about future outcomes is a key component of intelligent decision-making systems.
UA at SemEval-2019 Task 5: Setting A Strong Linear Baseline for Hate Speech Detection
This paper describes the system developed at the University of Alicante (UA) for the SemEval 2019 Task 5: Shared Task on Multilingual Detection of Hate.
A Visually Plausible Grasping System for Object Manipulation and Interaction in Virtual Reality Environments
On the other hand, for the quantitative evaluation a novel error metric has been proposed to visually analyze the performed grips.
The RobotriX: An eXtremely Photorealistic and Very-Large-Scale Indoor Dataset of Sequences with Robot Trajectories and Interactions
Enter the RobotriX, an extremely photorealistic indoor dataset designed to enable the application of deep learning techniques to a wide variety of robotic vision problems.
TactileGCN: A Graph Convolutional Network for Predicting Grasp Stability with Tactile Sensors
Tactile sensors provide useful contact data during the interaction with an object which can be used to accurately learn to determine the stability of a grasp.
UnrealROX: An eXtremely Photorealistic Virtual Reality Environment for Robotics Simulations and Synthetic Data Generation
Gathering and annotating that sheer amount of data in the real world is a time-consuming and error-prone task.
Three-dimensional planar model estimation using multi-constraint knowledge based on k-means and RANSAC
Plane model extraction from three-dimensional point clouds is a necessary step in many different applications such as planar object reconstruction, indoor mapping and indoor localization.
A Review on Deep Learning Techniques Applied to Semantic Segmentation
This demand coincides with the rise of deep learning approaches in almost every field or application target related to computer vision, including semantic segmentation or scene understanding.
