Multi-View Dynamic Facial Action Unit Detection (2017-04-25T00:00:00.000000Z)

TL;DR

This work proposes a novel convolutional neural network approach to address the fine-grained recognition problem of multi-view dynamic facial action unit detection by formulating the task of predicting the presence or absence of a specific action unit in a still image of a human face as holistic classification.

Authors

Pablo Arbeláez

7 papers

Andrés Romero

3 papers

Juan León

1 papers

TL;DR

Authors

References59 items

Facial action coding system

Automatic differentiation in PyTorch

View-Independent Facial Action Unit Detection

Multi View Facial Action Unit Detection Based on CNN and BLSTM-RNN

FERA 2017 - Addressing Head Pose in the Third Facial Expression Recognition and Analysis Challenge

EAC-Net: A Region-Based Deep Enhancing and Cropping Approach for Facial Action Unit Detection

Multi-region Two-Stream R-CNN for Action Detection

A Main Directional Mean Optical Flow Feature for Spontaneous Micro-Expression Recognition

Modeling Spatial and Temporal Cues for Multi-label Facial Action Unit Detection

Deep Region and Multi-label Learning for Facial Action Unit Detection

Multimodal Spontaneous Emotion Corpus for Human Behavior Analysis

Extended DISFA Dataset: Investigating Posed and Spontaneous Facial Expressions

Deep learning the dynamic appearance and shape of facial action units

Object Contour Detection with a Fully Convolutional Encoder-Decoder Network

Instance-Aware Semantic Segmentation via Multi-task Network Cascades

Deep Residual Learning for Image Recognition

Learning to Transfer: Transferring Latent Task Structures and Its Application to Person-Specific Facial Action Unit Detection

Confidence Preserving Machine for Facial Action Unit Detection

Multi-conditional Latent Variable Model for Joint Facial Action Unit Detection

Understanding Neural Networks Through Deep Visualization

P-CNN: Pose-Based CNN Features for Action Recognition

Joint patch and multi-label learning for facial action unit detection

Latent trees for estimating intensity of Facial Action Units

ActivityNet: A large-scale video benchmark for human activity understanding

A large-scale car dataset for fine-grained categorization and verification

Learning Deconvolution Network for Semantic Segmentation

Automatic facial expression recognition using features of salient facial patches

Deep learning based FACS Action Unit occurrence and intensity estimation

Holistically-Nested Edge Detection

Adam: A Method for Stochastic Optimization

Finding action tubes

Deeply Learning Deformable Facial Action Parts Model for Dynamic Expression Analysis

BP4D-Spontaneous: a high-resolution spontaneous 3D dynamic facial expression database

Going deeper with convolutions

Facial Expression Analysis Based on High Dimensional Binary Features

Very Deep Convolutional Networks for Large-Scale Image Recognition

Facial Expression Recognition via a Boosted Deep Belief Network

Caffe: Convolutional Architecture for Fast Feature Embedding

Microsoft COCO: Common Objects in Context

Compound facial expressions of emotion

Capturing Global Semantic Relationships for Facial Action Unit Recognition

Visualizing and Understanding Convolutional Networks

AU-aware Deep Networks for facial expression recognition

Lattice Computing Extension of the FAM Neural Classifier for Human Facial Expression Recognition

ImageNet classification with deep convolutional neural networks

Meta-Analysis of the First Facial Expression Recognition Challenge

The Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression

Histograms of oriented optical flow and Binet-Cauchy kernels on nonlinear dynamical systems for the recognition of human actions

ImageNet: A large-scale hierarchical image database

Bosphorus Database for 3D Face Analysis

What the face reveals : basic and applied studies of spontaneous expression using the facial action coding system (FACS)

Object recognition from local scale-invariant features

Active Appearance Models

Performance evaluation of texture measures with classification based on Kullback discrimination of distributions

Determining Optical Flow

Optimization Methods

Open source computer vision library

Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation

International Journal of Computer Vision manuscript No. (will be inserted by the editor) The PASCAL Visual Object Classes (VOC) Challenge

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL

Alternate Names