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.

169,181 papers · 148 categories

Trend · papers per month

3672108144 · Jun 202019922001200920182026
48 results for facial embeddings

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.

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.

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.

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.

Proposes a faster Isomap algorithm by reducing eigenvalue decomposition complexity.

problem High computational complexity of Isomap, especially in eigenvalue decomposition stage.
method Introduces a projection operator to reduce the complexity of the eigenvalue decomposition stage to linear order.
result Reduces Isomap's computational complexity to linear order while preserving structural information.

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.

We present a method for synthesizing a frontal, neutral-expression image of a person's face given an input face photograph. This is achieved by learning to generate facial landmarks and textures from features extracted from a facial-recognition network. Unlike previous approaches, our encoding feature vector is largely…

2017-01-17abs ↗pdf ↗

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.

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.

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.

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.

Aff-Wild database expands facial expression recognition to real-world conditions.

problem Lack of spontaneous facial expression databases in real-world conditions.
method Collects spontaneous facial expressions from YouTube, annotates with valence and arousal, uses deep learning techniques.
result Developed an end-to-end DNN model achieving 0.555 CCC for valence and 0.499 CCC for arousal.

Limited annotated data available for the recognition of facial expression and action units embarrasses the training of deep networks, which can learn disentangled invariant features. However, a linear model with just several parameters normally is not demanding in terms of training data. In this paper, we propose an el…

2017-01-11abs ↗pdf ↗

AI misidentifies facial expressions in videos, often misinterpreting happiness as sadness.

problem Automated facial emotion recognition in videos, especially with mixed modalities (visual and audio).
method Applied state-of-the-art visual and temporal networks, explored feature fusion methods.
result Machine learning models misclassify emotions, particularly happiness as sadness.

Enhances 2D face recognition with 3D features using active illumination.

problem Improving robustness of 2D face recognition to spoofing attacks and low-light conditions.
method Projecting a high spatial frequency pattern onto the face to recover 3D information and a 2D image simultaneously.
result Significantly boosts face recognition performance and dramatically improves robustness to spoofing attacks.

This paper improves facial expression recognition using CNNs and coherence constraints.

problem Facial expression recognition from static images and video sequences is challenging.
method Investigates the use of Convolutional Neural Networks (CNNs) with coherence constraints in a semi-supervised setting.
result Coherence constraints improve facial expression recognition quality, especially in the presence of occlusions.

New method compresses facial videos using GANs and latent space optimization.

problem Efficiently compressing facial videos at low bit rates.
method Leverages StyleGAN for latent space representation and compression, learns optimal compression through entropy model and perceptual loss.
result Significantly reduces perceptual distortion at low bit rates compared to state-of-the-art codecs.