1 code implementation • 7 Feb 2024 • Iago Suárez, Ghesn Sfeir, José M. Buenaposada, Luis Baumela
Efficient matching of local image features is a fundamental task in many computer vision applications.
no code implementations • 6 Feb 2024 • Antonio Fernández-Baldera, José M. Buenaposada, Luis Baumela
We present BAdaCost, a multi-class cost-sensitive classification algorithm.
1 code implementation • Pattern Recognition 2024 • Alejandro Cobo, Roberto Valle, José M. Buenaposada, Luis Baumela
We also propose a generalization of the geodesic angular distance metric that enables the construction of a loss that controls the contribution of each training sample to the optimization of the model.
Ranked #1 on Head Pose Estimation on Panoptic
1 code implementation • 13 Oct 2022 • 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.
Ranked #1 on Face Alignment on 300W (Common)
1 code implementation • 4 Feb 2022 • Roberto Valle, José Miguel Buenaposada, Luis Baumela
We contribute with a network architecture and training strategy that harness the strong dependencies among face pose, alignment and visibility, to produce a top performing model for all three tasks.
Ranked #1 on Face Alignment on COFW (Recall at 80% precision (Landmarks Visibility) metric)
1 code implementation • 18 Aug 2021 • 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 requirements.
1 code implementation • 6 Aug 2021 • 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.
1 code implementation • Pattern Recognition Letters 2019 • Roberto Valle, Jose M. Buenaposada, Luis Baumela
In this paper we investigate the use of a cascade of Neural Net regressors to increase the accuracy of the estimated facial landmarks.
Ranked #4 on Face Alignment on COFW (NME (inter-pupil) metric)
1 code implementation • 5 Feb 2019 • Roberto Valle, José M. Buenaposada, Antonio Valdés, Luis Baumela
In this paper we present 3DDE, a robust and efficient face alignment algorithm based on a coarse-to-fine cascade of ensembles of regression trees.
Ranked #2 on Face Alignment on 300W Split 2 (NME (inter-ocular) metric)
1 code implementation • ECCV 2018 • Roberto Valle, Jose M. Buenaposada, Antonio Valdes, Luis Baumela
In this paper we present DCFE, a real-time facial landmark regression method based on a coarse-to-fine Ensemble of Regression Trees (ERT).
Ranked #2 on Face Alignment on 300W Split 2 (FR@8 (inter-ocular) metric)