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

4896143191 · Jun 202019922001200920182026
48 results for Facial Action Units

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.

We propose a novel GP auto-encoder for ordinal facial action unit prediction.

problem Simultaneous feature fusion and modeling of discrete ordinal outputs.
method Variational Gaussian Process Auto-Encoder (GPAE) with latent space projection and ordinal label constraints.
result Our model achieves robust feature fusion and joint ordinal prediction of facial action units.

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.

Project uses GANs to recognize facial expressions and emotions from-the-wild with dual model approach.

problem Facial expression and emotion recognition in real-world scenarios.
method Created a dual GAN model architecture for Action Units and Valence Arousal annotations.
result Dual GAN model achieved better results than single model for emotion recognition.

New system detects pain from facial AU combinations using MIL and MCIL.

problem Detecting pain from facial expressions reliably.
method Weakly supervised learning, multiple instance learning, multiple clustered instance learning.
result 87% pain recognition accuracy on UNBC-McMaster Shoulder Pain Expression dataset.

Paper tackles multi-task learning for emotion recognition and generation using Aff-Wild dataset.

problem Developing a multi-task learning approach for emotion recognition and generation using Aff-Wild dataset.
method Deep neural network with shared hidden layers and GAN for multi-task learning and image generation.
result Good performance of the proposed approach on Aff-Wild dataset.

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.

This research improves facial emotion recognition using autoencoders and CNNs.

problem Facial emotion recognition as a challenging problem in computer vision.
method Two methods: autoencoders for representation and 8-layer CNN.
result CNN model outperforms state-of-the-art methods for emotion recognition.

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.

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.

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.

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.

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.

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.

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.

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.

Paper introduces a method for generating interlocutor-aware facial gestures in dyadic settings.

problem Generating appropriate non-verbal behavior for conversational agents in dyadic settings.
method Probabilistic method using multi-modal cues from the interlocutor to synthesize facial gestures.
result The model successfully leverages multi-modal input from the interlocutor to generate more appropriate behavior.

Bayesian Neural Networks improve uncertainty modeling in facial emotion recognition.

problem High aleatoric uncertainty and visual ambiguity in facial emotion recognition.
method Bayesian Neural Networks approximated using MC-Dropout, MC-DropConnect, or Ensemble methods.
result Bayesian Neural Networks produce more human-like output probabilities.

Paper studies facial keypoint detection using various algorithms.

problem Challenges in accurately detecting facial keypoints from complex images.
method Preprocess data with PCA and LBP, apply multiple algorithms including linear regression, tree models, neural networks, and CNNs.
result Demonstrates the effectiveness of the proposed framework through comprehensive experiments.

AttGAN edits facial attributes by changing only what you want, preserving details.

problem Facial attribute editing with preservation of details.
method Encoder-decoder architecture with attribute classification and reconstruction learning.
result Outperforms state-of-the-arts on realistic attribute editing with preserved details.

Paper proposes a method to combine multiple facial analysis models for better performance.

problem Facial analysis models from different sources have low transferability.
method Two-step process: 1) Auto-encoder for common embedding, 2) Distillation for lightweight model.
result Lightweight model outperforms state-of-the-art on 15 facial analysis tasks.

AutoTune learns wireless identifiers for facial recognition in real-world settings.

problem Facial recognition requires extensive user training, making it impractical for widespread deployment.
method Uses ambient wireless identifiers to train deep neural networks for facial recognition without user effort.
result Demonstrates a system that continuously refines facial recognition using wireless identifiers over time.

Efficient facial feature learning with shared representations reduces redundancy and improves accuracy.

problem Redundancy and high computational load in training deep ensemble models.
method Wide Ensemble-based Convolutional Neural Networks (ESRs) with varying branching levels.
result ESRs reduce residual generalization error and outperform state-of-the-art methods on facial expression recognition.

This work introduces a framework to detect unintended bias in facial analysis models.

problem Detecting unintended biases in facial analysis models used in critical applications.
method Image counterfactual sensitivity analysis using generative adversarial networks.
result Identifies factors affecting facial classifier predictions, revealing unintended biases.

DepthNets learns 3D face geometry and transformations without supervision.

problem Learning 3D face geometry and transformations from a single image.
method Unsupervised learning of facial keypoints depth, using backpropable loss for 3D transformations.
result DepthNets can predict 3D transformations and re-target faces to new poses or geometries.

This paper explores how facial recognition systems can be fooled by adversarial attacks.

problem Adversarial attacks on facial recognition systems.
method Applying Fast Gradient Sign Method and crafting various black-box attack algorithms.
result High levels of perturbation can significantly decrease classifier confidence and misclassification rates.

Develops a fast non-invasive tool for diagnosing pediatric sleep apnea.

problem Diagnosing pediatric obstructive sleep apnea using an overnight sleep study is often impractical.
method Combines persistent homology, geometric shape analysis, and convolutional neural networks to classify facial images.
result Facial features associated with obstructive sleep apnea can be recognized for diagnosis.

Study shows horizontal diameter of unit spheres is π for specific foliations.

problem Understanding horizontal diameter in unit spheres with specific foliations.
method Analyzing singular Riemannian foliations on unit spheres.
result Horizontal diameter of unit spheres is π for polar and infinitesimally polar actions.

Content based image retrieval, a technique which uses visual contents of image to search images from large scale image databases according to users' interests. This paper provides a comprehensive survey on recent technology used in the area of content based face image retrieval. Nowadays digital devices and photo shari…

2014-02-20abs ↗pdf ↗

New CNN architecture detects face spoofing with deep local features.

problem Face recognition systems are vulnerable to face spoofing attacks.
method Two-step CNN architecture: first learns features from facial regions, then fine-tunes on whole images.
result Improves face spoofing detection performance and convergence speed.

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.

Proposes k-Same-Siamese-GAN for de-identifying facial images efficiently and preserving privacy.

problem Ensuring privacy of facial images while preserving useful data.
method Uses k-Same-Anonymity, GAN, hyperparameter tuning, and mixed precision training.
result Efficient de-identification of high-resolution facial images with privacy guarantees.

This study compares global vs local observation and action representations for DRL in RTS games.

problem Improving Deep Reinforcement Learning performance in RTS games.
method Comparing two observation and action representations in μRTS.
result Local representation outperforms global representation in resource harvesting tasks.