Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,291 papers · 148 categories

Trend · papers per month

471114 · Oct 201919922001200920182026
48 results for facial landmarks

Study uses stacked hourglass networks to improve facial landmark detection for medical diagnosis.

problem Improving accuracy of facial landmark detection for medical diagnosis.
method Conducted a study on landmark localisation methods using stacked hourglass networks.
result State-of-the-art stacked hourglass architecture outperforms traditional methods.

Paper evaluates CNN-based facial landmark detection methods.

problem Evaluate characteristics and performance of CNN-based facial landmark detection methods.
method Divided into regression and heatmap approaches, investigated using a hybrid loss function and discrimination network.
result Proposed model outperforms other models in all tested datasets.

Synthesizes faces from facial features, invariant to pose and expression.

problem Creating realistic face images from facial features.
method Learning facial landmarks and textures from facial-recognition features, training on frontal, neutral-expression images.
result Generated images are invariant to lighting, pose, and expression.

Study reveals biases in facial landmark detection methods for dementia patients.

problem Challenges in facial landmark detection for older adults with dementia.
method Evaluation of seven facial landmark detection methods on frontal, profile, and various face regions.
result Significant performance differences between dementia patients and non-patients, and biases across face regions.

Facial landmark localization and occlusion estimation for driver safety.

problem Robust facial landmark localization and occlusion estimation under harsh lighting and occlusion.
method Occluded Stacked Hourglass approach based on Stacked Hourglass network.
result State-of-the-art results in face detection, head pose, and occlusion estimation on various datasets.

Estimation of facial expressions, as spatio-temporal processes, can take advantage of kernel methods if one considers facial landmark positions and their motion in 3D space. We applied support vector classification with kernels derived from dynamic time-warping similarity measures. We achieved over 99% accuracy - measu…

2013-06-08abs ↗pdf ↗

Task-assisted domain adaptation improves performance on synthetic-to-real image tasks.

problem Models trained on synthetic images often fail to generalize to real images due to domain shift.
method Introduce anchor tasks with easy-to-obtain annotations, apply reeze technique to learn cross-task guidance.
result Using anchor tasks on both synthetic and real domains improves performance compared to training on one domain.

This work generates synthetic 3D thermal facial data using 2D facial data and deep learning.

problem Creating large datasets for deep learning in computer vision.
method 3D facial modelling techniques and deep learning methodologies.
result Synthetic 3D thermal facial data created for deep learning applications.

First steps towards a mathematical theory of deep convolutional neural networks for feature extraction were made---for the continuous-time case---in Mallat, 2012, and Wiatowski and Bölcskei, 2015. This paper considers the discrete case, introduces new convolutional neural network architectures, and proposes a mathemati…

2016-05-26abs ↗pdf ↗

CAOS aggregates multiple one-shot predictors for efficient uncertainty quantification.

problem Lack of principled uncertainty quantification in one-shot prediction.
method CAOS, a conformal framework that aggregates multiple one-shot predictors and uses a leave-one-out calibration scheme.
result CAOS produces smaller prediction sets with reliable coverage compared to split conformal baselines.

The study extends stochastic completeness to landmark spaces with any number of landmarks.

problem Stochastic completeness for landmark spaces with arbitrary numbers of landmarks.
method Volume growth criterion and eigenvalue bounds for geodesic balls.
result Stochastic completeness for landmark spaces with any number of landmarks is proven.

Method converts facial expressions and voice of a source speaker into a target speaker.

problem Separate conversion of facial and acoustic features leads to unnatural results.
method Uses three neural networks: conversion, waveform generation, and image reconstruction.
result Significantly higher naturalness achieved when converting both features together.

Unsupervised method discovers object landmarks by factorizing image deformations.

problem Learning object structure in unsupervised settings.
method Factorizing image deformations to learn landmarks consistently across different viewpoints and object deformations.
result Learned landmarks establish meaningful correspondences between different object instances without explicit requirement.

FEAFA dataset annotates facial expressions with high detail.

problem Lack of detailed facial expression annotations in existing datasets.
method Manual annotation of 122 participants' facial expressions.
result FEAFA dataset provides detailed annotations for facial expressions.

Paper proposes a new landmark selection method for kernel ridge regression.

problem Efficient landmark selection for scalable kernel methods.
method Two-step approach: first computes importance scores, then clusters them into landmarks.
result Proposed method provides better accuracy and efficiency trade-offs.

Unsupervised model predicts facial attractiveness with high accuracy.

problem Capturing the complexity of facial attractiveness through machine learning.
method Infer probabilistic models of facial preferences using Maximum Entropy and neural networks.
result High prediction accuracy in gender classification of sculpting subjects.

Researchers prove long-time existence for two landmark Brownian motion.

problem Proving long-time existence of Brownian motion on configurations of two landmarks.
method Classification and analysis of long-time existence for configurations of exactly two landmarks, using a radial kernel.
result For configurations of exactly two landmarks, long-time existence is possible for certain kernels, but not for others.

Landmark-based node embeddings approximate shortest path distances in random graphs.

problem Capturing global graph distances in node representations.
method Landmark-based node embeddings using shortest path distances from a subset of reference nodes (landmarks).
result Random graphs require lower dimensions in landmark-based embeddings compared to worst-case graphs.

Exact universal interpolation property for landmark configurations in Euclidean space.

problem Representing and deforming landmark configurations through flows of vector fields.
method Explicitly describe vector fields for exact universal interpolation property in all dimensions.
result Achieve controllability by combining constant and polynomial vector fields.

Fawkes protects images from unauthorized facial recognition models.

problem Unauthorized training of facial recognition models poses privacy risks.
method Fawkes adds imperceptible pixel-level changes (cloaks) to images before release.
result Fawkes can protect images from misidentification by 95% and 80% even when clean images are leaked.

Neumann eigenmaps improve landmark-based diffusion map embeddings.

problem Landmark-based diffusion map embeddings can be computationally inefficient and unstable.
method NeuMaps use a renormalized Neumann Laplacian for eigendecomposition, incorporating landmarks as a subgraph.
result NeuMaps offer a computationally efficient and stable embedding method.

Paper introduces conformal prediction for reliable uncertainty quantification in landmark localization.

problem Systematic underestimation of total predictive uncertainty in landmark localization.
method Conformal prediction framework for multi-output regression, generating flexible prediction regions.
result Methods outperform existing approaches in validity and efficiency across 2D and 3D datasets.

Novel deep learning framework for mandible segmentation and landmarking.

problem Challenging problem of mandible segmentation and anatomical landmarking from CBCT scans.
method Three-step approach: deep neural network for segmentation, geodesic space for landmarks, LSTM for closely spaced landmarks.
result Superior efficacy compared to state-of-the-art methods in craniofacial anomalies and diseased states.

Polynomial fusion layer improves speech-driven facial animation.

problem Recent facial synthesis relies on low-dimensional representations and concatenation, ignoring higher-order interactions.
method Proposes a polynomial fusion layer to model higher-order interactions of facial encodings.
result Demonstrates improved video quality, audiovisual synchronisation, and blink generation.

The paper explores a new method for landmark matching using sub-Riemannian geometry and neural networks.

problem Finding a time-dependent vector field to warp points from an initial set to a target set.
method Sub-Riemannian geometry and residual neural networks.
result Demonstrates the importance of regularization in landmark matching.

Kernel methods obtain superb performance in terms of accuracy for various machine learning tasks since they can effectively extract nonlinear relations. However, their time complexity can be rather large especially for clustering tasks. In this paper we define a general class of kernels that can be easily approximated …

2015-10-28abs ↗pdf ↗

This work predicts and interpolates long-range videos using unsupervised landmarks.

problem Predicting and interpolating long-range video data with occlusions and appearance changes.
method Unsupervised latent structure inference followed by temporal prediction in a latent space.
result High-quality long-range video interpolation and extrapolation achieved through landmark representation.

Proposes a linear model for facial action recognition without requiring large datasets.

problem Limited annotated data for facial expression and action units.
method Exploits low-rank property across frames and group sparsity to subtract neutral faces and recognize actions.
result One-shot automatic method on raw face videos performs competitively and better than previous methods.