114 citations · 340 across the 11 of their papers we have counts for
13 papers
HuC-VideoMAE: Human-Centric Video Masked Autoencoding from synthetic data
Ricardo Pizarro, Roberto Valle, José M. Buenaposada +2
Modern action recognition models rely on video transformers pretrained on massive collections of web-crawled videos, such as Kinetics-700. However, the use of such data raises ethi…
Auditing Demographic Bias in Facial Landmark Detection for Fair Human-Robot Interaction
Pablo Parte, Roberto Valle, José M. Buenaposada +1
Fairness in human-robot interaction critically depends on the reliability of the perceptual models that enable robots to interpret human behavior. While demographic biases have bee…
Beyond Flicker: Detecting Kinematic Inconsistencies for Generalizable Deepfake Video Detection
Alejandro Cobo, Roberto Valle, José Miguel Buenaposada +1
Generalizing deepfake detection to unseen manipulations remains a key challenge. A recent approach to tackle this issue is to train a network with pristine face images that have be…
PO-GUISE+: Pose and object guided transformer token selection for efficient driver action recognition
Ricardo Pizarro, Roberto Valle, Rafael Barea +3
We address the task of identifying distracted driving by analyzing in-car videos using efficient transformers. Although transformer models have achieved outstanding performance in…
BEBLID: Boosted efficient binary local image descriptor
Iago Suárez, Ghesn Sfeir, José M. Buenaposada +1
Efficient matching of local image features is a fundamental task in many computer vision applications. However, the real-time performance of top matching algorithms is compromised…
BAdaCost: Multi-class Boosting with Costs
Antonio Fernández-Baldera, José M. Buenaposada, Luis Baumela
We present BAdaCost, a multi-class cost-sensitive classification algorithm. It combines a set of cost-sensitive multi-class weak learners to obtain a strong classification rule wit…
On the representation and methodology for wide and short range head pose estimation
Alejandro Cobo, Roberto Valle, José M. Buenaposada +1
Head pose estimation (HPE) is a problem of interest in computer vision to improve the performance of face processing tasks in semi-frontal or profile settings. Recent applications…
Shape Preserving Facial Landmarks with Graph Attention Networks
Andrés Prados-Torreblanca, José M. Buenaposada, Luis Baumela
Top-performing landmark estimation algorithms are based on exploiting the excellent ability of large convolutional neural networks (CNNs) to represent local appearance. However, it…
Multi-task head pose estimation in-the-wild
Roberto Valle, José Miguel Buenaposada, Luis Baumela
We present a deep learning-based multi-task approach for head pose estimation in images. We contribute with a network architecture and training strategy that harness the strong dep…
Revisiting Binary Local Image Description for Resource Limited Devices
Iago Suárez, José M. Buenaposada, Luis Baumela
The advent of a panoply of resource limited devices opens up new challenges in the design of computer vision algorithms with a clear compromise between accuracy and computational r…
ELSED: Enhanced Line SEgment Drawing
Iago Suárez, José M. Buenaposada, Luis Baumela
Detecting local features, such as corners, segments or blobs, is the first step in the pipeline of many Computer Vision applications. Its speed is crucial for real-time application…
Face Alignment using a 3D Deeply-initialized Ensemble of Regression Trees
Roberto Valle, José M. Buenaposada, Antonio Valdés +1
Face alignment algorithms locate a set of landmark points in images of faces taken in unrestricted situations. State-of-the-art approaches typically fail or lose accuracy in the pr…
Learning Depth from Monocular Videos using Direct Methods
Chaoyang Wang, Jose Miguel Buenaposada, Rui Zhu +1
The ability to predict depth from a single image - using recent advances in CNNs - is of increasing interest to the vision community. Unsupervised strategies to learning are partic…