arXiv subjects

Yu Ding

Publications and source records attributed to Yu Ding.

At least 73 records · Page 4Linked to original sources

arXiv2022

FlowFace: Semantic Flow-guided Shape-aware Face Swapping

In this work, we propose a semantic flow-guided two-stage framework for shape-aware face swapping, namely FlowFace. Unlike most previous methods that focus on transferring the source inner facial features but neglect facial contours, our FlowFace can transfer both of them to a target face, thus leading to more realistic face swapping. Concretely, our FlowFace consists of a face reshaping network and a face swapping network. The face reshaping network addresses the shape outline differences between the source and target faces. It first estimates a semantic flow (i.e., face shape differences) between the source and the target face, and then explicitly warps the target face shape with the estimated semantic flow. After reshaping, the face swapping network generates inner facial features that exhibit the identity of the source face. We employ a pre-trained face masked autoencoder (MAE) to extract facial features from both the source face and the target face. In contrast to previous methods that use identity embedding to preserve identity information, the features extracted by our encoder can better capture facial appearances and identity information. Then, we develop a cross-attention fusion module to adaptively fuse inner facial features from the source face with the target facial attributes, thus leading to better identity preservation. Extensive quantitative and qualitative experiments on in-the-wild faces demonstrate that our FlowFace outperforms the state-of-the-art significantly.

cs.CV↗

arXiv2022

Global-to-local Expression-aware Embeddings for Facial Action Unit Detection

Expressions and facial action units (AUs) are two levels of facial behavior descriptors. Expression auxiliary information has been widely used to improve the AU detection performance. However, most existing expression representations can only describe pre-determined discrete categories (e.g., Angry, Disgust, Happy, Sad, etc.) and cannot capture subtle expression transformations like AUs. In this paper, we propose a novel fine-grained \textsl{Global Expression representation Encoder} to capture subtle and continuous facial movements, to promote AU detection. To obtain such a global expression representation, we propose to train an expression embedding model on a large-scale expression dataset according to global expression similarity. Moreover, considering the local definition of AUs, it is essential to extract local AU features. Therefore, we design a \textsl{Local AU Features Module} to generate local facial features for each AU. Specifically, it consists of an AU feature map extractor and a corresponding AU mask extractor. First, the two extractors transform the global expression representation into AU feature maps and masks, respectively. Then, AU feature maps and their corresponding AU masks are multiplied to generate AU masked features focusing on local facial region. Finally, the AU masked features are fed into an AU classifier for judging the AU occurrence. Extensive experiment results demonstrate the superiority of our proposed method. Our method validly outperforms previous works and achieves state-of-the-art performances on widely-used face datasets, including BP4D, DISFA, and BP4D+.

cs.CV↗

arXiv2022

Facial Action Unit Detection and Intensity Estimation from Self-supervised Representation

As a fine-grained and local expression behavior measurement, facial action unit (FAU) analysis (e.g., detection and intensity estimation) has been documented for its time-consuming, labor-intensive, and error-prone annotation. Thus a long-standing challenge of FAU analysis arises from the data scarcity of manual annotations, limiting the generalization ability of trained models to a large extent. Amounts of previous works have made efforts to alleviate this issue via semi/weakly supervised methods and extra auxiliary information. However, these methods still require domain knowledge and have not yet avoided the high dependency on data annotation. This paper introduces a robust facial representation model MAE-Face for AU analysis. Using masked autoencoding as the self-supervised pre-training approach, MAE-Face first learns a high-capacity model from a feasible collection of face images without additional data annotations. Then after being fine-tuned on AU datasets, MAE-Face exhibits convincing performance for both AU detection and AU intensity estimation, achieving a new state-of-the-art on nearly all the evaluation results. Further investigation shows that MAE-Face achieves decent performance even when fine-tuned on only 1\% of the AU training set, strongly proving its robustness and generalization performance.

cs.CV↗

arXiv2022

Facial Action Units Detection Aided by Global-Local Expression Embedding

Since Facial Action Unit (AU) annotations require domain expertise, common AU datasets only contain a limited number of subjects. As a result, a crucial challenge for AU detection is addressing identity overfitting. We find that AUs and facial expressions are highly associated, and existing facial expression datasets often contain a large number of identities. In this paper, we aim to utilize the expression datasets without AU labels to facilitate AU detection. Specifically, we develop a novel AU detection framework aided by the Global-Local facial Expressions Embedding, dubbed GLEE-Net. Our GLEE-Net consists of three branches to extract identity-independent expression features for AU detection. We introduce a global branch for modeling the overall facial expression while eliminating the impacts of identities. We also design a local branch focusing on specific local face regions. The combined output of global and local branches is firstly pre-trained on an expression dataset as an identity-independent expression embedding, and then finetuned on AU datasets. Therefore, we significantly alleviate the issue of limited identities. Furthermore, we introduce a 3D global branch that extracts expression coefficients through 3D face reconstruction to consolidate 2D AU descriptions. Finally, a Transformer-based multi-label classifier is employed to fuse all the representations for AU detection. Extensive experiments demonstrate that our method significantly outperforms the state-of-the-art on the widely-used DISFA, BP4D and BP4D+ datasets.

cs.CV↗

arXiv2022

A Spatio-temporal Track Association Algorithm Based on Marine Vessel Automatic Identification System Data

Tracking multiple moving objects in real-time in a dynamic threat environment is an important element in national security and surveillance system. It helps pinpoint and distinguish potential candidates posing threats from other normal objects and monitor the anomalous trajectories until intervention. To locate the anomalous pattern of movements, one needs to have an accurate data association algorithm that can associate the sequential observations of locations and motion with the underlying moving objects, and therefore, build the trajectories of the objects as the objects are moving. In this work, we develop a spatio-temporal approach for tracking maritime vessels as the vessel's location and motion observations are collected by an Automatic Identification System. The proposed approach is developed as an effort to address a data association challenge in which the number of vessels as well as the vessel identification are purposely withheld and time gaps are created in the datasets to mimic the real-life operational complexities under a threat environment. Three training datasets and five test sets are provided in the challenge and a set of quantitative performance metrics is devised by the data challenge organizer for evaluating and comparing resulting methods developed by participants. When our proposed track association algorithm is applied to the five test sets, the algorithm scores a very competitive performance.

cs.LG↗

arXiv2022

Augmented Equivariant Attention Networks for Microscopy Image Reconstruction

It is time-consuming and expensive to take high-quality or high-resolution electron microscopy (EM) and fluorescence microscopy (FM) images. Taking these images could be even invasive to samples and may damage certain subtleties in the samples after long or intense exposures, often necessary for achieving high-quality or high resolution in the first place. Advances in deep learning enable us to perform image-to-image transformation tasks for various types of microscopy image reconstruction, computationally producing high-quality images from the physically acquired low-quality ones. When training image-to-image transformation models on pairs of experimentally acquired microscopy images, prior models suffer from performance loss due to their inability to capture inter-image dependencies and common features shared among images. Existing methods that take advantage of shared features in image classification tasks cannot be properly applied to image reconstruction tasks because they fail to preserve the equivariance property under spatial permutations, something essential in image-to-image transformation. To address these limitations, we propose the augmented equivariant attention networks (AEANets) with better capability to capture inter-image dependencies, while preserving the equivariance property. The proposed AEANets captures inter-image dependencies and shared features via two augmentations on the attention mechanism, which are the shared references and the batch-aware attention during training. We theoretically derive the equivariance property of the proposed augmented attention model and experimentally demonstrate its consistent superiority in both quantitative and visual results over the baseline methods.

cs.CV↗

arXiv2022

Hypothesis Tests with Functional Data for Surface Quality Change Detection in Surface Finishing Processes

This work is concerned with providing a principled decision process for stopping or tool-changing in a surface finishing process. The decision process is supposed to work for products of non-flat geometry. The solution is based on conducting hypothesis testing on the bearing area curves from two consecutive stages of a surface finishing process. In each stage, the bearing area curves, which are in fact the nonparametric quantile curves representing the surface roughness, are extracted from surface profile measurements at a number of sampling locations on the surface of the products. The hypothesis test of these curves informs the decision makers whether there is a change in surface quality induced by the current finishing action. When such change is detected, the current action is deemed effective and should thus continue, while when no change is detected, the effectiveness of the current action is then called into question, signaling possibly some change in the course of action. Application of the hypothesis testing-based decision procedure to both spherical and flat surfaces demonstrates the effectiveness and benefit of the proposed method and confirms its geometry-agnostic nature.

stat.ME↗

arXiv2022

Transformer-based Multimodal Information Fusion for Facial Expression Analysis

Human affective behavior analysis has received much attention in human-computer interaction (HCI). In this paper, we introduce our submission to the CVPR 2022 Competition on Affective Behavior Analysis in-the-wild (ABAW). To fully exploit affective knowledge from multiple views, we utilize the multimodal features of spoken words, speech prosody, and facial expression, which are extracted from the video clips in the Aff-Wild2 dataset. Based on these features, we propose a unified transformer-based multimodal framework for Action Unit detection and also expression recognition. Specifically, the static vision feature is first encoded from the current frame image. At the same time, we clip its adjacent frames by a sliding window and extract three kinds of multimodal features from the sequence of images, audio, and text. Then, we introduce a transformer-based fusion module that integrates the static vision features and the dynamic multimodal features. The cross-attention module in the fusion module makes the output integrated features focus on the crucial parts that facilitate the downstream detection tasks. We also leverage some data balancing techniques, data augmentation techniques, and postprocessing methods to further improve the model performance. In the official test of ABAW3 Competition, our model ranks first in the EXPR and AU tracks. The extensive quantitative evaluations, as well as ablation studies on the Aff-Wild2 dataset, prove the effectiveness of our proposed method.

cs.CV↗

arXiv2022

The temporal overfitting problem with applications in wind power curve modeling

This paper is concerned with a nonparametric regression problem in which the input variables and the errors are autocorrelated in time. The motivation for the research stems from modeling wind power curves. Using existing model selection methods, like cross validation, results in model overfitting in presence of temporal autocorrelation. This phenomenon is referred to as temporal overfitting, which causes loss of performance while predicting responses for a time domain different from the training time domain. We propose a Gaussian process (GP)-based method to tackle the temporal overfitting problem. Our model is partitioned into two parts -- a time-invariant component and a time-varying component, each of which is modeled through a GP. We modify the inference method to a thinning-based strategy, an idea borrowed from Markov chain Monte Carlo sampling, to overcome temporal overfitting and estimate the time-invariant component. We extensively compare our proposed method with both existing power curve models and available ideas for handling temporal overfitting on real wind turbine datasets. Our approach yields significant improvement when predicting response for a time period different from the training time period. Supplementary material and computer code for this article is available online.

stat.AP↗

arXiv2021

One-shot Talking Face Generation from Single-speaker Audio-Visual Correlation Learning

Audio-driven one-shot talking face generation methods are usually trained on video resources of various persons. However, their created videos often suffer unnatural mouth shapes and asynchronous lips because those methods struggle to learn a consistent speech style from different speakers. We observe that it would be much easier to learn a consistent speech style from a specific speaker, which leads to authentic mouth movements. Hence, we propose a novel one-shot talking face generation framework by exploring consistent correlations between audio and visual motions from a specific speaker and then transferring audio-driven motion fields to a reference image. Specifically, we develop an Audio-Visual Correlation Transformer (AVCT) that aims to infer talking motions represented by keypoint based dense motion fields from an input audio. In particular, considering audio may come from different identities in deployment, we incorporate phonemes to represent audio signals. In this manner, our AVCT can inherently generalize to audio spoken by other identities. Moreover, as face keypoints are used to represent speakers, AVCT is agnostic against appearances of the training speaker, and thus allows us to manipulate face images of different identities readily. Considering different face shapes lead to different motions, a motion field transfer module is exploited to reduce the audio-driven dense motion field gap between the training identity and the one-shot reference. Once we obtained the dense motion field of the reference image, we employ an image renderer to generate its talking face videos from an audio clip. Thanks to our learned consistent speaking style, our method generates authentic mouth shapes and vivid movements. Extensive experiments demonstrate that our synthesized videos outperform the state-of-the-art in terms of visual quality and lip-sync.

cs.CV↗

arXiv2021

Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion

We propose an audio-driven talking-head method to generate photo-realistic talking-head videos from a single reference image. In this work, we tackle two key challenges: (i) producing natural head motions that match speech prosody, and (ii) maintaining the appearance of a speaker in a large head motion while stabilizing the non-face regions. We first design a head pose predictor by modeling rigid 6D head movements with a motion-aware recurrent neural network (RNN). In this way, the predicted head poses act as the low-frequency holistic movements of a talking head, thus allowing our latter network to focus on detailed facial movement generation. To depict the entire image motions arising from audio, we exploit a keypoint based dense motion field representation. Then, we develop a motion field generator to produce the dense motion fields from input audio, head poses, and a reference image. As this keypoint based representation models the motions of facial regions, head, and backgrounds integrally, our method can better constrain the spatial and temporal consistency of the generated videos. Finally, an image generation network is employed to render photo-realistic talking-head videos from the estimated keypoint based motion fields and the input reference image. Extensive experiments demonstrate that our method produces videos with plausible head motions, synchronized facial expressions, and stable backgrounds and outperforms the state-of-the-art.

cs.CV↗

arXiv2021

A Reproducing Kernel Hilbert Space Approach to Functional Calibration of Computer Models

This paper develops a frequentist solution to the functional calibration problem, where the value of a calibration parameter in a computer model is allowed to vary with the value of control variables in the physical system. The need of functional calibration is motivated by engineering applications where using a constant calibration parameter results in a significant mismatch between outputs from the computer model and the physical experiment. Reproducing kernel Hilbert spaces (RKHS) are used to model the optimal calibration function, defined as the functional relationship between the calibration parameter and control variables that gives the best prediction. This optimal calibration function is estimated through penalized least squares with an RKHS-norm penalty and using physical data. An uncertainty quantification procedure is also developed for such estimates. Theoretical guarantees of the proposed method are provided in terms of prediction consistency and consistency of estimating the optimal calibration function. The proposed method is tested using both real and synthetic data and exhibits more robust performance in prediction and uncertainty quantification than the existing parametric functional calibration method and a state-of-art Bayesian method.

stat.ME↗

arXiv2021

Prior Aided Streaming Network for Multi-task Affective Recognitionat the 2nd ABAW2 Competition

Automatic affective recognition has been an important research topic in human computer interaction (HCI) area. With recent development of deep learning techniques and large scale in-the-wild annotated datasets, the facial emotion analysis is now aimed at challenges in the real world settings. In this paper, we introduce our submission to the 2nd Affective Behavior Analysis in-the-wild (ABAW2) Competition. In dealing with different emotion representations, including Categorical Emotions (CE), Action Units (AU), and Valence Arousal (VA), we propose a multi-task streaming network by a heuristic that the three representations are intrinsically associated with each other. Besides, we leverage an advanced facial expression embedding as prior knowledge, which is capable of capturing identity-invariant expression features while preserving the expression similarities, to aid the down-streaming recognition tasks. The extensive quantitative evaluations as well as ablation studies on the Aff-Wild2 dataset prove the effectiveness of our proposed prior aided streaming network approach.

cs.CV↗

arXiv2021

Cardiac Functional Analysis with Cine MRI via Deep Learning Reconstruction

Retrospectively gated cine (retro-cine) MRI is the clinical standard for cardiac functional analysis. Deep learning (DL) based methods have been proposed for the reconstruction of highly undersampled MRI data and show superior image quality and magnitude faster reconstruction time than CS-based methods. Nevertheless, it remains unclear whether DL reconstruction is suitable for cardiac function analysis. To address this question, in this study we evaluate and compare the cardiac functional values (EDV, ESV and EF for LV and RV, respectively) obtained from highly accelerated MRI acquisition using DL based reconstruction algorithm (DL-cine) with values from CS-cine and conventional retro-cine. To the best of our knowledge, this is the first work to evaluate the cine MRI with deep learning reconstruction for cardiac function analysis and compare it with other conventional methods. The cardiac functional values obtained from cine MRI with deep learning reconstruction are consistent with values from clinical standard retro-cine MRI.

eess.IV↗

arXiv2021

Write-a-speaker: Text-based Emotional and Rhythmic Talking-head Generation

In this paper, we propose a novel text-based talking-head video generation framework that synthesizes high-fidelity facial expressions and head motions in accordance with contextual sentiments as well as speech rhythm and pauses. To be specific, our framework consists of a speaker-independent stage and a speaker-specific stage. In the speaker-independent stage, we design three parallel networks to generate animation parameters of the mouth, upper face, and head from texts, separately. In the speaker-specific stage, we present a 3D face model guided attention network to synthesize videos tailored for different individuals. It takes the animation parameters as input and exploits an attention mask to manipulate facial expression changes for the input individuals. Furthermore, to better establish authentic correspondences between visual motions (i.e., facial expression changes and head movements) and audios, we leverage a high-accuracy motion capture dataset instead of relying on long videos of specific individuals. After attaining the visual and audio correspondences, we can effectively train our network in an end-to-end fashion. Extensive experiments on qualitative and quantitative results demonstrate that our algorithm achieves high-quality photo-realistic talking-head videos including various facial expressions and head motions according to speech rhythms and outperforms the state-of-the-art.

cs.CV↗

arXiv2021

Graph Regularized Autoencoder and its Application in Unsupervised Anomaly Detection

Dimensionality reduction is a crucial first step for many unsupervised learning tasks including anomaly detection and clustering. Autoencoder is a popular mechanism to accomplish dimensionality reduction. In order to make dimensionality reduction effective for high-dimensional data embedding nonlinear low-dimensional manifold, it is understood that some sort of geodesic distance metric should be used to discriminate the data samples. Inspired by the success of geodesic distance approximators such as ISOMAP, we propose to use a minimum spanning tree (MST), a graph-based algorithm, to approximate the local neighborhood structure and generate structure-preserving distances among data points. We use this MST-based distance metric to replace the Euclidean distance metric in the embedding function of autoencoders and develop a new graph regularized autoencoder, which outperforms a wide range of alternative methods over 20 benchmark anomaly detection datasets. We further incorporate the MST regularizer into two generative adversarial networks and find that using the MST regularizer improves the performance of anomaly detection substantially for both generative adversarial networks. We also test our MST regularized autoencoder on two datasets in a clustering application and witness its superior performance as well.

cs.LG↗

arXiv2021

A Graph-Theoretic Approach for Spatial Filtering and Its Impact on Mixed-type Spatial Pattern Recognition in Wafer Bin Maps

Statistical quality control in semiconductor manufacturing hinges on effective diagnostics of wafer bin maps, wherein a key challenge is to detect how defective chips tend to spatially cluster on a wafer--a problem known as spatial pattern recognition. Recently, there has been a growing interest in mixed-type spatial pattern recognition--when multiple defect patterns, of different shapes, co-exist on the same wafer. Mixed-type spatial pattern recognition entails two central tasks: (1) spatial filtering, to distinguish systematic patterns from random noises; and (2) spatial clustering, to group filtered patterns into distinct defect types. Observing that spatial filtering is instrumental to high-quality mixed-type pattern recognition, we propose to use a graph-theoretic method, called adjacency-clustering, which leverages spatial dependence among adjacent defective chips to effectively filter the raw wafer maps. Tested on real-world data and compared against a state-of the-art approach, our proposed method achieves at least 46% gain in terms of internal cluster validation quality (i.e., validation without external class labels), and about ~5% gain in terms of Normalized Mutual Information--an external cluster validation metric based on external class labels. Interestingly, the margin of improvement appears to be a function of the pattern complexity, with larger gains achieved for more complex-shaped patterns.

stat.AP↗

arXiv2021

A Case Study of Space-time Performance Comparison of Wind Turbines on a Wind Farm

This paper presents an academia-industry joint case study, which was conducted to quantify and compare multi-year changes in power production performance of multiple turbines scattered over a mid-size wind farm. This analysis is referred to as a space-time performance comparison. One key aspect in power performance analysis is to have the wind and environmental inputs controlled for. This research employs, in a sequential fashion, two principal modeling components to exercise tight control of multiple input conditions -- a covariate matching method, followed by a Gaussian process model-based functional comparison. The analysis method is applied to a wind farm that houses 66 turbines on a moderately complex terrain. The power production and environmental data span nearly four years, during which period the turbines have gone through multiple technical upgrades. The space-time analysis presents a quantitative and global picture showing how turbines differ relative to each other as well as how each of them changes over time.

stat.AP↗