arXiv subjects

Jiayi Wang

Publications and source records attributed to Jiayi Wang.

At least 127 records · Page 7Linked to original sources

arXiv2021

EventHands: Real-Time Neural 3D Hand Pose Estimation from an Event Stream

3D hand pose estimation from monocular videos is a long-standing and challenging problem, which is now seeing a strong upturn. In this work, we address it for the first time using a single event camera, i.e., an asynchronous vision sensor reacting on brightness changes. Our EventHands approach has characteristics previously not demonstrated with a single RGB or depth camera such as high temporal resolution at low data throughputs and real-time performance at 1000 Hz. Due to the different data modality of event cameras compared to classical cameras, existing methods cannot be directly applied to and re-trained for event streams. We thus design a new neural approach which accepts a new event stream representation suitable for learning, which is trained on newly-generated synthetic event streams and can generalise to real data. Experiments show that EventHands outperforms recent monocular methods using a colour (or depth) camera in terms of accuracy and its ability to capture hand motions of unprecedented speed. Our method, the event stream simulator and the dataset are publicly available; see https://4dqv.mpi-inf.mpg.de/EventHands/

cs.CV↗

arXiv2021

Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation

Quality Estimation (QE) plays an essential role in applications of Machine Translation (MT). Traditionally, a QE system accepts the original source text and translation from a black-box MT system as input. Recently, a few studies indicate that as a by-product of translation, QE benefits from the model and training data's information of the MT system where the translations come from, and it is called the "glass-box QE". In this paper, we extend the definition of "glass-box QE" generally to uncertainty quantification with both "black-box" and "glass-box" approaches and design several features deduced from them to blaze a new trial in improving QE's performance. We propose a framework to fuse the feature engineering of uncertainty quantification into a pre-trained cross-lingual language model to predict the translation quality. Experiment results show that our method achieves state-of-the-art performances on the datasets of WMT 2020 QE shared task.

cs.CL↗

arXiv2021

RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video

Tracking and reconstructing the 3D pose and geometry of two hands in interaction is a challenging problem that has a high relevance for several human-computer interaction applications, including AR/VR, robotics, or sign language recognition. Existing works are either limited to simpler tracking settings (e.g., considering only a single hand or two spatially separated hands), or rely on less ubiquitous sensors, such as depth cameras. In contrast, in this work we present the first real-time method for motion capture of skeletal pose and 3D surface geometry of hands from a single RGB camera that explicitly considers close interactions. In order to address the inherent depth ambiguities in RGB data, we propose a novel multi-task CNN that regresses multiple complementary pieces of information, including segmentation, dense matchings to a 3D hand model, and 2D keypoint positions, together with newly proposed intra-hand relative depth and inter-hand distance maps. These predictions are subsequently used in a generative model fitting framework in order to estimate pose and shape parameters of a 3D hand model for both hands. We experimentally verify the individual components of our RGB two-hand tracking and 3D reconstruction pipeline through an extensive ablation study. Moreover, we demonstrate that our approach offers previously unseen two-hand tracking performance from RGB, and quantitatively and qualitatively outperforms existing RGB-based methods that were not explicitly designed for two-hand interactions. Moreover, our method even performs on-par with depth-based real-time methods.

cs.CV↗

arXiv2021

Matrix Completion with Model-free Weighting

In this paper, we propose a novel method for matrix completion under general non-uniform missing structures. By controlling an upper bound of a novel balancing error, we construct weights that can actively adjust for the non-uniformity in the empirical risk without explicitly modeling the observation probabilities, and can be computed efficiently via convex optimization. The recovered matrix based on the proposed weighted empirical risk enjoys appealing theoretical guarantees. In particular, the proposed method achieves a stronger guarantee than existing work in terms of the scaling with respect to the observation probabilities, under asymptotically heterogeneous missing settings (where entry-wise observation probabilities can be of different orders). These settings can be regarded as a better theoretical model of missing patterns with highly varying probabilities. We also provide a new minimax lower bound under a class of heterogeneous settings. Numerical experiments are also provided to demonstrate the effectiveness of the proposed method.

stat.ML↗

arXiv2021

Generative Model-Based Loss to the Rescue: A Method to Overcome Annotation Errors for Depth-Based Hand Pose Estimation

We propose to use a model-based generative loss for training hand pose estimators on depth images based on a volumetric hand model. This additional loss allows training of a hand pose estimator that accurately infers the entire set of 21 hand keypoints while only using supervision for 6 easy-to-annotate keypoints (fingertips and wrist). We show that our partially-supervised method achieves results that are comparable to those of fully-supervised methods which enforce articulation consistency. Moreover, for the first time we demonstrate that such an approach can be used to train on datasets that have erroneous annotations, i.e. "ground truth" with notable measurement errors, while obtaining predictions that explain the depth images better than the given "ground truth".

cs.CV↗

arXiv2021

Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrifice

Pre-trained contextualized language models (PrLMs) have led to strong performance gains in downstream natural language understanding tasks. However, PrLMs can still be easily fooled by adversarial word substitution, which is one of the most challenging textual adversarial attack methods. Existing defence approaches suffer from notable performance loss and complexities. Thus, this paper presents a compact and performance-preserved framework, Anomaly Detection with Frequency-Aware Randomization (ADFAR). In detail, we design an auxiliary anomaly detection classifier and adopt a multi-task learning procedure, by which PrLMs are able to distinguish adversarial input samples. Then, in order to defend adversarial word substitution, a frequency-aware randomization process is applied to those recognized adversarial input samples. Empirical results show that ADFAR significantly outperforms those newly proposed defense methods over various tasks with much higher inference speed. Remarkably, ADFAR does not impair the overall performance of PrLMs. The code is available at https://github.com/LilyNLP/ADFAR

cs.CL↗

arXiv2021

Estimation of Partially Conditional Average Treatment Effect by Hybrid Kernel-covariate Balancing

We study nonparametric estimation for the partially conditional average treatment effect, defined as the treatment effect function over an interested subset of confounders. We propose a hybrid kernel weighting estimator where the weights aim to control the balancing error of any function of the confounders from a reproducing kernel Hilbert space after kernel smoothing over the subset of interested variables. In addition, we present an augmented version of our estimator which can incorporate estimations of outcome mean functions. Based on the representer theorem, gradient-based algorithms can be applied for solving the corresponding infinite-dimensional optimization problem. Asymptotic properties are studied without any smoothness assumptions for propensity score function or the need of data splitting, relaxing certain existing stringent assumptions. The numerical performance of the proposed estimator is demonstrated by a simulation study and an application to the effect of a mother's smoking on a baby's birth weight conditioned on the mother's age.

stat.ME↗

arXiv2020

Enhancing Pre-trained Language Model with Lexical Simplification

For both human readers and pre-trained language models (PrLMs), lexical diversity may lead to confusion and inaccuracy when understanding the underlying semantic meanings of given sentences. By substituting complex words with simple alternatives, lexical simplification (LS) is a recognized method to reduce such lexical diversity, and therefore to improve the understandability of sentences. In this paper, we leverage LS and propose a novel approach which can effectively improve the performance of PrLMs in text classification. A rule-based simplification process is applied to a given sentence. PrLMs are encouraged to predict the real label of the given sentence with auxiliary inputs from the simplified version. Using strong PrLMs (BERT and ELECTRA) as baselines, our approach can still further improve the performance in various text classification tasks.

cs.CL↗

arXiv2020

Strain-induced anion ordering in perovskite oxyfluoride films

Anionic ordering is a promising route to engineer physical properties in functional heteroanionic materials. A central challenge in the study of anion-ordered compounds lies in developing robust synthetic strategies to control anion occupation and in understanding the resultant implications for electronic structure. Here, we show that epitaxial strain induces preferential occupation of F and O on the anion sites in perovskite oxyfluoride SrMnO2.5-dFg films grown on different substrates. Under compressive strain, F tends to take the apical-like sites, which was revealed by F and O K-edge linearly polarized x-ray absorption spectroscopy and density functional theory calculations, resulting in an enhanced c-axis expansion. Under tensile strain, F tends to take the equatorial-like sites, enabling the longer Mn-F bonds to lie within the plane. The anion ordered oxyfluoride films exhibit a significant orbital polarization of the 3d electrons, distinct F-site dependence to their valence band density of states, and an enhanced resistivity when F occupies the apical-like anion site compared to the equatorial-like site. By demonstrating a general strategy for inducing anion-site order in oxyfluoride perovskites, this work lays the foundation for future materials design and synthesis efforts that leverage this greater degree of atomic control to realize new polar or quasi-two-dimensional materials.

cond-mat.mtrl-sci↗

arXiv2020

Computer Assisted Translation with Neural Quality Estimation and Automatic Post-Editing

With the advent of neural machine translation, there has been a marked shift towards leveraging and consuming the machine translation results. However, the gap between machine translation systems and human translators needs to be manually closed by post-editing. In this paper, we propose an end-to-end deep learning framework of the quality estimation and automatic post-editing of the machine translation output. Our goal is to provide error correction suggestions and to further relieve the burden of human translators through an interpretable model. To imitate the behavior of human translators, we design three efficient delegation modules -- quality estimation, generative post-editing, and atomic operation post-editing and construct a hierarchical model based on them. We examine this approach with the English--German dataset from WMT 2017 APE shared task and our experimental results can achieve the state-of-the-art performance. We also verify that the certified translators can significantly expedite their post-editing processing with our model in human evaluation.

cs.CL↗

arXiv2020

Low-Rank Covariance Function Estimation for Multidimensional Functional Data

Multidimensional function data arise from many fields nowadays. The covariance function plays an important role in the analysis of such increasingly common data. In this paper, we propose a novel nonparametric covariance function estimation approach under the framework of reproducing kernel Hilbert spaces (RKHS) that can handle both sparse and dense functional data. We extend multilinear rank structures for (finite-dimensional) tensors to functions, which allow for flexible modeling of both covariance operators and marginal structures. The proposed framework can guarantee that the resulting estimator is automatically semi-positive definite, and can incorporate various spectral regularizations. The trace-norm regularization in particular can promote low ranks for both covariance operator and marginal structures. Despite the lack of a closed form, under mild assumptions, the proposed estimator can achieve unified theoretical results that hold for any relative magnitudes between the sample size and the number of observations per sample field, and the rate of convergence reveals the "phase-transition" phenomenon from sparse to dense functional data. Based on a new representer theorem, an ADMM algorithm is developed for the trace-norm regularization. The appealing numerical performance of the proposed estimator is demonstrated by a simulation study and the analysis of a dataset from the Argo project.

stat.ME↗

arXiv2020

Neural Zero-Inflated Quality Estimation Model For Automatic Speech Recognition System

The performances of automatic speech recognition (ASR) systems are usually evaluated by the metric word error rate (WER) when the manually transcribed data are provided, which are, however, expensively available in the real scenario. In addition, the empirical distribution of WER for most ASR systems usually tends to put a significant mass near zero, making it difficult to simulate with a single continuous distribution. In order to address the two issues of ASR quality estimation (QE), we propose a novel neural zero-inflated model to predict the WER of the ASR result without transcripts. We design a neural zero-inflated beta regression on top of a bidirectional transformer language model conditional on speech features (speech-BERT). We adopt the pre-training strategy of token level mask language modeling for speech-BERT as well, and further fine-tune with our zero-inflated layer for the mixture of discrete and continuous outputs. The experimental results show that our approach achieves better performance on WER prediction in the metrics of Pearson and MAE, compared with most existed quality estimation algorithms for ASR or machine translation.

cs.CL↗

arXiv2020

Balance of the vorticity direction and the vorticity magnitude in 3D fractional Navier-Stokes equations

Fractional Navier-Stokes equations -- featuring a fractional Laplacian -- provide a `bridge' between the Euler equations (zero diffusion) and the Navier-Stokes equations (full diffusion). The problem of whether an initially smooth flow can spontaneously develop a singularity is a fundamental problem in mathematical physics, open for the full range of models -- from Euler to Navier-Stokes. The purpose of this work is to present a hybrid, geometric-analytic regularity criterion for solutions to the 3D fractional Navier-Stokes equations expressed as a balance -- in the average sense -- between the vorticity direction and the vorticity magnitude, key geometric and analytic descriptors of the flow, respectively.

math.AP↗

arXiv2019

Convex Optimisation for Inverse Kinematics

We consider the problem of inverse kinematics (IK), where one wants to find the parameters of a given kinematic skeleton that best explain a set of observed 3D joint locations. The kinematic skeleton has a tree structure, where each node is a joint that has an associated geometric transformation that is propagated to all its child nodes. The IK problem has various applications in vision and graphics, for example for tracking or reconstructing articulated objects, such as human hands or bodies. Most commonly, the IK problem is tackled using local optimisation methods. A major downside of these approaches is that, due to the non-convex nature of the problem, such methods are prone to converge to unwanted local optima and therefore require a good initialisation. In this paper we propose a convex optimisation approach for the IK problem based on semidefinite programming, which admits a polynomial-time algorithm that globally solves (a relaxation of) the IK problem. Experimentally, we demonstrate that the proposed method significantly outperforms local optimisation methods using different real-world skeletons.

cs.LG↗

arXiv2019

An encoding framework with brain inner state for natural image identification

Neural encoding and decoding, which aim to characterize the relationship between stimuli and brain activities, have emerged as an important area in cognitive neuroscience. Traditional encoding models, which focus on feature extraction and mapping, consider the brain as an input-output mapper without inner states. In this work, inspired by the fact that human brain acts like a state machine, we proposed a novel encoding framework that combines information from both the external world and the inner state to predict brain activity. The framework comprises two parts: forward encoding model that deals with visual stimuli and inner state model that captures influence from intrinsic connections in the brain. The forward model can be any traditional encoding model, making the framework flexible. The inner state model is a linear model to utilize information in the prediction residuals of the forward model. The proposed encoding framework can achieve much better performance on natural image identification from fMRI response than forwardonly models. The identification accuracy will decrease slightly with the dataset size increasing, but remain relatively stable with different identification methods. The results confirm that the new encoding framework is effective and robust when used for brain decoding.

q-bio.NC↗

arXiv2019

Predicting Eating Events in Free Living Individuals -- A Technical Report

This technical report records the experiments of applying multiple machine learning algorithms for predicting eating and food purchasing behaviors of free-living individuals. Data was collected with accelerometer, global positioning system (GPS), and body-worn cameras called SenseCam over a one week period in 81 individuals from a variety of ages and demographic backgrounds. These data were turned into minute-level features from sensors as well as engineered features that included time (e.g., time since last eating) and environmental context (e.g., distance to nearest grocery store). Algorithms include Logistic Regression, RBF-SVM, Random Forest, and Gradient Boosting. Our results show that the Gradient Boosting model has the highest mean accuracy score (0.7289) for predicting eating events before 0 to 4 minutes. For predicting food purchasing events, the RBF-SVM model (0.7395) outperforms others. For both prediction models, temporal and spatial features were important contributors to predicting eating and food purchasing events.

cs.LG↗

arXiv2018

"Bilingual Expert" Can Find Translation Errors

Recent advances in statistical machine translation via the adoption of neural sequence-to-sequence models empower the end-to-end system to achieve state-of-the-art in many WMT benchmarks. The performance of such machine translation (MT) system is usually evaluated by automatic metric BLEU when the golden references are provided for validation. However, for model inference or production deployment, the golden references are prohibitively available or require expensive human annotation with bilingual expertise. In order to address the issue of quality evaluation (QE) without reference, we propose a general framework for automatic evaluation of translation output for most WMT quality evaluation tasks. We first build a conditional target language model with a novel bidirectional transformer, named neural bilingual expert model, which is pre-trained on large parallel corpora for feature extraction. For QE inference, the bilingual expert model can simultaneously produce the joint latent representation between the source and the translation, and real-valued measurements of possible erroneous tokens based on the prior knowledge learned from parallel data. Subsequently, the features will further be fed into a simple Bi-LSTM predictive model for quality evaluation. The experimental results show that our approach achieves the state-of-the-art performance in the quality estimation track of WMT 2017/2018.

cs.CL↗

arXiv2018

Low-Rank Phase Retrieval via Variational Bayesian Learning

In this paper, we consider the problem of low-rank phase retrieval whose objective is to estimate a complex low-rank matrix from magnitude-only measurements. We propose a hierarchical prior model for low-rank phase retrieval, in which a Gaussian-Wishart hierarchical prior is placed on the underlying low-rank matrix to promote the low-rankness of the matrix. Based on the proposed hierarchical model, a variational expectation-maximization (EM) algorithm is developed. The proposed method is less sensitive to the choice of the initialization point and works well with random initialization. Simulation results are provided to illustrate the effectiveness of the proposed algorithm.

stat.ML↗