RECORD
Deep Structure Inference Network for Facial Action Unit Recognition
Computer Vision and Pattern Recognition · Submitted 15 Mar 2018
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim We show that by training the model end-to-end with increased supervision we improve state-of-the-art by 5.3% and 8.2% performance on BP4D and DISFA datasets, respectively.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Facial expressions are combinations of basic components called Action Units (AU). Recognizing AUs is key for developing general facial expression analysis. In recent years, most efforts in automatic AU recognition have been dedicated to learning combinations of local features and to exploiting correlations between Action Units. In this paper, we propose a deep neural architecture that tackles both problems by combining learned local and global features in its initial stages and replicating a message passing algorithm between classes similar to a graphical model inference approach in later stages. We show that by training the model end-to-end with increased supervision we improve state-of-the-art by 5.3% and 8.2% performance on BP4D and DISFA datasets, respectively.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Facial expressions are combinations of basic components called Action Units (AU). | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s1 | Recognizing AUs is key for developing general facial expression analysis. | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| s2 | In recent years, most efforts in automatic AU recognition have been dedicated to learning combinations of local features and to exploiting correlations between Action Units. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s3 | In this paper, we propose a deep neural architecture that tackles both problems by combining learned local and global features in its initial stages and replicating a message passing algorithm between classes similar to a graphical model inference approach in later stages. | method 0.74 | 0.87 | 0.12 | asserted 0.99 |
| s4 | We show that by training the model end-to-end with increased supervision we improve state-of-the-art by 5.3% and 8.2% performance on BP4D and DISFA datasets, respectively. | result 1.00 | 0.97 | 0.79 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Facial expressions are combinations of basic components called Action Units (AU). Recognizing AUs is key for developing general facial expression analysis. In recent years, most efforts in automatic AU recognition have been dedicated to learning combinations of local features and to exploiting correlations between Action Units. In this paper, we propose a deep neural architecture that tackles both problems by combining learned local and global features in its initial stages and replicating a message passing algorithm between classes similar to a graphical model inference approach in later stages. We show that by training the model end-to-end with increased supervision we improve state-of-the-art by 5.3% and 8.2% performance on BP4D and DISFA datasets, respectively.
Human review
How the literature uses it
1 arXiv paper cite this in 2 sentences
Papers citing it · 1 sentence without a confident label
Compares with it 1 paper
-
We compare our method to alternative methods, including linear SVM(LSVM) [ref] , Joint Patch and Multi-label Learning(JPML) [ref] , ConvNet with locally connected layer(LCN) [ref] , Deep Region and Multi-label Learning(DRML) [ref] , Region Adaptation, Multi-label Learning(ROI) [ref] and Deep Structure Inference Network(DSIN) [ref] .
Semantic Relationships Guided Representation Learning for Facial Action Unit Recognition · Comparison with the State of the Art · 0.99
What it cites · 5 sentences without a confident label
Uses the method or tool of 1 paper
-
Similarly to [ref] , on DISFA we take the best CNNs trained for patch prediction on the BP4D and retrained fully connected layers for the new set of outputs.
Action Unit Detection with Region Adaptation, Multi-labeling Learning and Optimal Temporal Fusing · Training. · 0.87
Compares with 1 paper
-
We compare against CPM [ref] , APL [ref] , JPML [ref] , DRML [ref] , and ROI [ref] state-of-the-art alternatives.
Action Unit Detection with Region Adaptation, Multi-labeling Learning and Optimal Temporal Fusing · Methods and metrics. · 1.00
Cites as background 2 papers
-
While initial methods for AU recognition (like JPML [ref] and APL [ref] ) were using shallow predefined representations, recent methods (like DRML [ref] , ROI [ref] and GL [ref] ) applied deep learning to learn richer local features that capture facial morphology.
Action Unit Detection with Region Adaptation, Multi-labeling Learning and Optimal Temporal Fusing · Introduction · 0.81
-
Two main ways of solving multi-label learning in AU recognition are either capturing correlations through fully-connected layers [ref] or inferring structure through probabilistic graphical models (PGM) [ref] .
Deep Structured Learning for Facial Action Unit Intensity Estimation · Method · 0.97
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.