Search

Your search keyword '"Yap, Chuin Hong"' showing total 11 results
Start Over Author "Yap, Chuin Hong" Publication Year Range Last 50 years
11 results on '"Yap, Chuin Hong"'

1. Facial micro- and macro-expression spotting and generation methods

Author

Yap, Chuin Hong

Abstract

Facial micro-expression (ME) recognition requires face movement interval as input, but computer methods in spotting ME are still underperformed. This is due to lacking large-scale long video dataset and ME generation methods are in their infancy. This thesis presents methods to address data deficiency issues and introduces a new method for spotting macro- and micro-expressions simultaneously. This thesis introduces SAMM Long Videos (SAMM-LV), which contains 147 annotated long videos, and develops a baseline method to facilitate ME Grand Challenge 2020. Further, a reference-guided style transfer of StarGANv2 is experimented on SAMM-LV to generate a synthetic dataset, namely SAMM-SYNTH. The quality of SAMM-SYNTH is evaluated by using facial action units detected by OpenFace. Quantitative measurement shows high correlations on two Action Units (AU12 and AU6) of the original and synthetic data. In facial expression spotting, a two-stream 3D-Convolutional Neural Network with temporal oriented frame skips that can spot micro- and macro-expression simultaneously is proposed. This method achieves state-of-the-art performance in SAMM-LV and is competitive in CAS(ME)2, it was used as the baseline result of ME Grand Challenge 2021. The F1-score improves to 0.1036 when trained with composite data consisting of SAMM-LV and SAMMSYNTH. On the unseen ME Grand Challenge 2022 evaluation dataset, it achieves F1-score of 0.1531. Finally, a new sequence generation method to explore the capability of deep learning network is proposed. It generates spontaneous facial expressions by using only two input sequences without any labels. SSIM and NIQE were used for image quality analysis and the generated data achieved 0.87 and 23.14. By visualising the movements using optical flow value and absolute frame differences, this method demonstrates its potential in generating subtle ME. For realism evaluation, the generated videos were rated by using two facial expression recognition networks.

Published
2023

2. 3D-CNN for Facial Micro- and Macro-expression Spotting on Long Video Sequences using Temporal Oriented Reference Frame

Author

Yap, Chuin Hong, Yap, Moi Hoon, Davison, Adrian K., Kendrick, Connah, Li, Jingting, Wang, Sujing, and Cunningham, Ryan

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Facial expression spotting is the preliminary step for micro- and macro-expression analysis. The task of reliably spotting such expressions in video sequences is currently unsolved. The current best systems depend upon optical flow methods to extract regional motion features, before categorisation of that motion into a specific class of facial movement. Optical flow is susceptible to drift error, which introduces a serious problem for motions with long-term dependencies, such as high frame-rate macro-expression. We propose a purely deep learning solution which, rather than tracking frame differential motion, compares via a convolutional model, each frame with two temporally local reference frames. Reference frames are sampled according to calculated micro- and macro-expression duration. As baseline for MEGC2021 using leave-one-subject-out evaluation method, we show that our solution achieves F1-score of 0.105 in a high frame-rate (200 fps) SAMM long videos dataset (SAMM-LV) and is competitive in a low frame-rate (30 fps) (CAS(ME)2) dataset. On unseen MEGC2022 challenge dataset, the baseline results are 0.1176 on SAMM Challenge dataset, 0.1739 on CAS(ME)3 and overall performance of 0.1531 on both dataset.

Published
2021

3. SAMM Long Videos: A Spontaneous Facial Micro- and Macro-Expressions Dataset

Author

Yap, Chuin Hong, Kendrick, Connah, and Yap, Moi Hoon

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

With the growth of popularity of facial micro-expressions in recent years, the demand for long videos with micro- and macro-expressions remains high. Extended from SAMM, a micro-expressions dataset released in 2016, this paper presents SAMM Long Videos dataset for spontaneous micro- and macro-expressions recognition and spotting. SAMM Long Videos dataset consists of 147 long videos with 343 macro-expressions and 159 micro-expressions. The dataset is FACS-coded with detailed Action Units (AUs). We compare our dataset with Chinese Academy of Sciences Macro-Expressions and Micro-Expressions (CAS(ME)2) dataset, which is the only available fully annotated dataset with micro- and macro-expressions. Furthermore, we preprocess the long videos using OpenFace, which includes face alignment and detection of facial AUs. We conduct facial expression spotting using this dataset and compare it with the baseline of MEGC III. Our spotting method outperformed the baseline result with F1-score of 0.3299.

Published
2019

4. Self-supervised spontaneous latent-based facial expression sequence generation

Author

Yap, Chuin Hong, Yap, Moi Hoon, Davison, Adrian K, Cunningham, Ryan, Yap, Chuin Hong, Yap, Moi Hoon, Davison, Adrian K, and Cunningham, Ryan

Abstract

In this paper, we investigate the spontaneity issue in facial expression sequence generation. Current leading methods in the field are commonly reliant on manually adjusted conditional variables to direct the model to generate a specific class of expression. We propose a neural network-based method which uses Gaussian noise to model spontaneity in the generation process, removing the need for manual control of conditional generation variables. Our model takes two sequential images as input, with additive noise, and produces the next image in the sequence. We trained two types of models: single-expression, and mixed-expression. With single-expression, unique facial movements of certain emotion class can be generated; with mixed expressions, fully spontaneous expression sequence generation can be achieved. We compared our method to current leading generation methods on a variety of publicly available datasets. Initial qualitative results show our method produces visually more realistic expressions and facial action unit (AU) trajectories; initial quantitative results using image quality metrics (SSIM and NIQE) show the quality of our generated images is higher. Our approach and results are novel in the field of facial expression generation, with potential wider applications to other sequence generation tasks.

Published
2023

Catalog

Books, media, physical & digital resources
See catalog results