• Publications
  • Influence
LBP with Six Intersection Points: Reducing Redundant Information in LBP-TOP for Micro-expression Recognition
TLDR
The proposed Local Binary Patterns with Six Intersection Points (LBP-SIP) volumetric descriptor based on the three intersecting lines crossing over the center point reduces the redundancy in LBP-TOP patterns, providing a more compact and lightweight representation; leading to more efficient computational complexity.
Enriched Long-Term Recurrent Convolutional Network for Facial Micro-Expression Recognition
TLDR
An Enriched Long-term Recurrent Convolutional Network (ELRCN) that first encodes each micro- expression frame into a feature vector through CNN module(s), then predicts the micro-expression by passing the feature vectorthrough a Long Short-term Memory (LSTM) module.
MEGC 2019 – The Second Facial Micro-Expressions Grand Challenge
TLDR
The evaluation protocols for the two challenge tasks, the datasets involved, and an analysis of the best performing works from the participating teams are outlined, together with a summary of results.
Efficient Spatio-Temporal Local Binary Patterns for Spontaneous Facial Micro-Expression Recognition
TLDR
This paper draws further inspiration from the concept of LBP-TOP that considers three orthogonal planes by proposing two efficient approaches for feature extraction that preserves the essential patterns and reduces the redundancy that affects the discriminality of the encoded features.
Subtle Expression Recognition Using Optical Strain Weighted Features
TLDR
A novel optical strain weighted feature extraction scheme for subtle facial micro-expression recognition that combines motion information derived from optical strain magnitudes with weights pooled spatio-temporally to obtain block-wise weights for the spatial image plane.
Shallow Triple Stream Three-dimensional CNN (STSTNet) for Micro-expression Recognition
TLDR
A Shallow Triple Stream Three-dimensional CNN (STSTNet) that is computationally light whilst capable of extracting discriminative high level features and details of micro-expressions is designed.
Towards Accurate One-Stage Object Detection With AP-Loss
TLDR
A novel optimization algorithm is developed, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks, and good convergence property of the proposed algorithm is verified theoretically and empirically.
Eulerian emotion magnification for subtle expression recognition
TLDR
It is shown that through motion magnification, subtle expressions can be realistically exaggerated and become more easily recognisable.
Automatic apex frame spotting in micro-expression database
TLDR
This work presents a novel method to spot the apex frame of a spontaneous micro-expression video sequence using a binary search approach to locate the index of the frame in which the peak facial changes occur.
...
...