Searcharxiv⌕ Search

arXiv subjects

Xudong Liu

Publications and source records attributed to Xudong Liu.

At least 55 records · Page 3Linked to original sources
arXiv2022

Controllable and Lossless Non-Autoregressive End-to-End Text-to-Speech

Some recent studies have demonstrated the feasibility of single-stage neural text-to-speech, which does not need to generate mel-spectrograms but generates the raw waveforms directly from the text. Single-stage text-to-speech often faces two problems: a) the one-to-many mapping problem due to multiple speech variations and b) insufficiency of high frequency reconstruction due to the lack of supervision of ground-truth acoustic features during training. To solve the a) problem and generate more expressive speech, we propose a novel phoneme-level prosody modeling method based on a variational autoencoder with normalizing flows to model underlying prosodic information in speech. We also use the prosody predictor to support end-to-end expressive speech synthesis. Furthermore, we propose the dual parallel autoencoder to introduce supervision of the ground-truth acoustic features during training to solve the b) problem enabling our model to generate high-quality speech. We compare the synthesis quality with state-of-the-art text-to-speech systems on an internal expressive English dataset. Both qualitative and quantitative evaluations demonstrate the superiority and robustness of our method for lossless speech generation while also showing a strong capability in prosody modeling.

cs.SD↗
arXiv2022

Dual-Flattening Transformers through Decomposed Row and Column Queries for Semantic Segmentation

It is critical to obtain high resolution features with long range dependency for dense prediction tasks such as semantic segmentation. To generate high-resolution output of size $H\times W$ from a low-resolution feature map of size $h\times w$ ($hw\ll HW$), a naive dense transformer incurs an intractable complexity of $\mathcal{O}(hwHW)$, limiting its application on high-resolution dense prediction. We propose a Dual-Flattening Transformer (DFlatFormer) to enable high-resolution output by reducing complexity to $\mathcal{O}(hw(H+W))$ that is multiple orders of magnitude smaller than the naive dense transformer. Decomposed queries are presented to retrieve row and column attentions tractably through separate transformers, and their outputs are combined to form a dense feature map at high resolution. To this end, the input sequence fed from an encoder is row-wise and column-wise flattened to align with decomposed queries by preserving their row and column structures, respectively. Row and column transformers also interact with each other to capture their mutual attentions with the spatial crossings between rows and columns. We also propose to perform attentions through efficient grouping and pooling to further reduce the model complexity. Extensive experiments on ADE20K and Cityscapes datasets demonstrate the superiority of the proposed dual-flattening transformer architecture with higher mIoUs.

cs.CV↗
arXiv2021

An Empirical Study on End-to-End Singing Voice Synthesis with Encoder-Decoder Architectures

With the rapid development of neural network architectures and speech processing models, singing voice synthesis with neural networks is becoming the cutting-edge technique of digital music production. In this work, in order to explore how to improve the quality and efficiency of singing voice synthesis, in this work, we use encoder-decoder neural models and a number of vocoders to achieve singing voice synthesis. We conduct experiments to demonstrate that the models can be trained using voice data with pitch information, lyrics and beat information, and the trained models can produce smooth, clear and natural singing voice that is close to real human voice. As the models work in the end-to-end manner, they allow users who are not domain experts to directly produce singing voice by arranging pitches, lyrics and beats.

cs.SD↗
arXiv2020

Short Video-based Advertisements Evaluation System: Self-Organizing Learning Approach

With the rising of short video apps, such as TikTok, Snapchat and Kwai, advertisement in short-term user-generated videos (UGVs) has become a trending form of advertising. Prediction of user behavior without specific user profile is required by advertisers, as they expect to acquire advertisement performance in advance in the scenario of cold start. Current recommender system do not take raw videos as input; additionally, most previous work of Multi-Modal Machine Learning may not deal with unconstrained videos like UGVs. In this paper, we proposed a novel end-to-end self-organizing framework for user behavior prediction. Our model is able to learn the optimal topology of neural network architecture, as well as optimal weights, through training data. We evaluate our proposed method on our in-house dataset. The experimental results reveal that our model achieves the best performance in all our experiments.

cs.MM↗
arXiv2020

Themes Informed Audio-visual Correspondence Learning

The applications of short-term user-generated video (UGV), such as Snapchat, and Youtube short-term videos, booms recently, raising lots of multimodal machine learning tasks. Among them, learning the correspondence between audio and visual information from videos is a challenging one. Most previous work of the audio-visual correspondence(AVC) learning only investigated constrained videos or simple settings, which may not fit the application of UGV. In this paper, we proposed new principles for AVC and introduced a new framework to set sight of videos' themes to facilitate AVC learning. We also released the KWAI-AD-AudVis corpus which contained 85432 short advertisement videos (around 913 hours) made by users. We evaluated our proposed approach on this corpus, and it was able to outperform the baseline by 23.15% absolute difference.

cs.AI↗
arXiv2020

Towards Optimal Filter Pruning with Balanced Performance and Pruning Speed

Filter pruning has drawn more attention since resource constrained platform requires more compact model for deployment. However, current pruning methods suffer either from the inferior performance of one-shot methods, or the expensive time cost of iterative training methods. In this paper, we propose a balanced filter pruning method for both performance and pruning speed. Based on the filter importance criteria, our method is able to prune a layer with approximate layer-wise optimal pruning rate at preset loss variation. The network is pruned in the layer-wise way without the time consuming prune-retrain iteration. If a pre-defined pruning rate for the entire network is given, we also introduce a method to find the corresponding loss variation threshold with fast converging speed. Moreover, we propose the layer group pruning and channel selection mechanism for channel alignment in network with short connections. The proposed pruning method is widely applicable to common architectures and does not involve any additional training except the final fine-tuning. Comprehensive experiments show that our method outperforms many state-of-the-art approaches.

cs.CV↗
arXiv2020

Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations

The idea of using multi-task learning approaches to address the joint extraction of entity and relation is motivated by the relatedness between the entity recognition task and the relation classification task. Existing methods using multi-task learning techniques to address the problem learn interactions among the two tasks through a shared network, where the shared information is passed into the task-specific networks for prediction. However, such an approach hinders the model from learning explicit interactions between the two tasks to improve the performance on the individual tasks. As a solution, we design a multi-task learning model which we refer to as recurrent interaction network which allows the learning of interactions dynamically, to effectively model task-specific features for classification. Empirical studies on two real-world datasets confirm the superiority of the proposed model.

cs.CL↗
arXiv2020

IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval

Enabling bi-directional retrieval of images and texts is important for understanding the correspondence between vision and language. Existing methods leverage the attention mechanism to explore such correspondence in a fine-grained manner. However, most of them consider all semantics equally and thus align them uniformly, regardless of their diverse complexities. In fact, semantics are diverse (i.e. involving different kinds of semantic concepts), and humans usually follow a latent structure to combine them into understandable languages. It may be difficult to optimally capture such sophisticated correspondences in existing methods. In this paper, to address such a deficiency, we propose an Iterative Matching with Recurrent Attention Memory (IMRAM) method, in which correspondences between images and texts are captured with multiple steps of alignments. Specifically, we introduce an iterative matching scheme to explore such fine-grained correspondence progressively. A memory distillation unit is used to refine alignment knowledge from early steps to later ones. Experiment results on three benchmark datasets, i.e. Flickr8K, Flickr30K, and MS COCO, show that our IMRAM achieves state-of-the-art performance, well demonstrating its effectiveness. Experiments on a practical business advertisement dataset, named \Ads{}, further validates the applicability of our method in practical scenarios.

cs.CV↗
arXiv2019

Face Beautification: Beyond Makeup Transfer

Facial appearance plays an important role in our social lives. Subjective perception of women's beauty depends on various face-related (e.g., skin, shape, hair) and environmental (e.g., makeup, lighting, angle) factors. Similar to cosmetic surgery in the physical world, virtual face beautification is an emerging field with many open issues to be addressed. Inspired by the latest advances in style-based synthesis and face beauty prediction, we propose a novel framework of face beautification. For a given reference face with a high beauty score, our GAN-based architecture is capable of translating an inquiry face into a sequence of beautified face images with referenced beauty style and targeted beauty score values. To achieve this objective, we propose to integrate both style-based beauty representation (extracted from the reference face) and beauty score prediction (trained on SCUT-FBP database) into the process of beautification. Unlike makeup transfer, our approach targets at many-to-many (instead of one-to-one) translation where multiple outputs can be defined by either different references or varying beauty scores. Extensive experimental results are reported to demonstrate the effectiveness and flexibility of the proposed face beautification framework.

cs.CV↗
arXiv2019

Digital Twin: Acquiring High-Fidelity 3D Avatar from a Single Image

We present an approach to generate high fidelity 3D face avatar with a high-resolution UV texture map from a single image. To estimate the face geometry, we use a deep neural network to directly predict vertex coordinates of the 3D face model from the given image. The 3D face geometry is further refined by a non-rigid deformation process to more accurately capture facial landmarks before texture projection. A key novelty of our approach is to train the shape regression network on facial images synthetically generated using a high-quality rendering engine. Moreover, our shape estimator fully leverages the discriminative power of deep facial identity features learned from millions of facial images. We have conducted extensive experiments to demonstrate the superiority of our optimized 2D-to-3D rendering approach, especially its excellent generalization property on real-world selfie images. Our proposed system of rendering 3D avatars from 2D images has a wide range of applications from virtual/augmented reality (VR/AR) and telepsychiatry to human-computer interaction and social networks.

cs.CV↗
arXiv2019

An Extensible and Personalizable Multi-Modal Trip Planner

Despite a tremendous amount of work in the literature and in the commercial sectors, current approaches to multi-modal trip planning still fail to consistently generate plans that users deem optimal in practice. We believe that this is due to the fact that current planners fail to capture the true preferences of users, e.g., their preferences depend on aspects that are not modeled. An example of this could be a preference not to walk through an unsafe area at night. We present a novel multi-modal trip planner that allows users to upload auxiliary geographic data (e.g., crime rates) and to specify temporal constraints and preferences over these data in combination with typical metrics such as time and cost. Concretely, our planner supports the modes walking, biking, driving, public transit, and taxi, uses linear temporal logic to capture temporal constraints, and preferential cost functions to represent preferences. We show by examples that this allows the expression of very interesting preferences and constraints that, naturally, lead to quite diverse optimal plans.

cs.AI↗
arXiv2019

Human-In-The-Loop Learning of Qualitative Preference Models

In this work, we present a novel human-in-the-loop framework to help the human user understand the decision making process that involves choosing preferred options. We focus on qualitative preference models over alternatives from combinatorial domains. This framework is interactive: the user provides her behavioral data to the framework, and the framework explains the learned model to the user. It is iterative: the framework collects feedback on the learned model from the user and tries to improve it accordingly till the user terminates the iteration. In order to communicate the learned preference model to the user, we develop visualization of intuitive and explainable graphic models, such as lexicographic preference trees and forests, and conditional preference networks. To this end, we discuss key aspects of our framework for lexicographic preference models.

cs.AI↗
arXiv2019

Learning Optimal and Near-Optimal Lexicographic Preference Lists

We consider learning problems of an intuitive and concise preference model, called lexicographic preference lists (LP-lists). Given a set of examples that are pairwise ordinal preferences over a universe of objects built of attributes of discrete values, we want to learn (1) an optimal LP-list that decides the maximum number of these examples, or (2) a near-optimal LP-list that decides as many examples as it can. To this end, we introduce a dynamic programming based algorithm and a genetic algorithm for these two learning problems, respectively. Furthermore, we empirically demonstrate that the sub-optimal models computed by the genetic algorithm very well approximate the de facto optimal models computed by our dynamic programming based algorithm, and that the genetic algorithm outperforms the baseline greedy heuristic with higher accuracy predicting new preferences.

cs.AI↗
arXiv2019

Understanding Beauty via Deep Facial Features

The concept of beauty has been debated by philosophers and psychologists for centuries, but most definitions are subjective and metaphysical, and deficit in accuracy, generality, and scalability. In this paper, we present a novel study on mining beauty semantics of facial attributes based on big data, with an attempt to objectively construct descriptions of beauty in a quantitative manner. We first deploy a deep convolutional neural network (CNN) to extract facial attributes, and then investigate correlations between these features and attractiveness on two large-scale datasets labelled with beauty scores. Not only do we discover the secrets of beauty verified by statistical significance tests, our findings also align perfectly with existing psychological studies that, e.g., small nose, high cheekbones, and femininity contribute to attractiveness. We further leverage these high-level representations to original images by a generative adversarial network (GAN). Beauty enhancements after synthesis are visually compelling and statistically convincing verified by a user survey of 10,000 data points.

cs.CV↗
arXiv2018

Semi-supervised Text Regression with Conditional Generative Adversarial Networks

Enormous online textual information provides intriguing opportunities for understandings of social and economic semantics. In this paper, we propose a novel text regression model based on a conditional generative adversarial network (GAN), with an attempt to associate textual data and social outcomes in a semi-supervised manner. Besides promising potential of predicting capabilities, our superiorities are twofold: (i) the model works with unbalanced datasets of limited labelled data, which align with real-world scenarios; and (ii) predictions are obtained by an end-to-end framework, without explicitly selecting high-level representations. Finally we point out related datasets for experiments and future research directions.

cs.CL↗
arXiv2018

Attributes in Multiple Facial Images

Facial attribute recognition is conventionally computed from a single image. In practice, each subject may have multiple face images. Taking the eye size as an example, it should not change, but it may have different estimation in multiple images, which would make a negative impact on face recognition. Thus, how to compute these attributes corresponding to each subject rather than each single image is a profound work. To address this question, we deploy deep training for facial attributes prediction, and we explore the inconsistency issue among the attributes computed from each single image. Then, we develop two approaches to address the inconsistency issue. Experimental results show that the proposed methods can handle facial attribute estimation on either multiple still images or video frames, and can correct the incorrectly annotated labels. The experiments are conducted on two large public databases with annotations of facial attributes.

cs.CV↗
arXiv2018

Graph Pattern Matching for Dynamic Team Formation

Finding a list of k teams of experts, referred to as top-k team formation, with the required skills and high collaboration compatibility has been extensively studied. However, existing methods have not considered the specific collaboration relationships among different team members, i.e., structural constraints, which are typically needed in practice. In this study, we first propose a novel graph pattern matching approach for top-k team formation, which incorporates both structural constraints and capacity bounds. Second, we formulate and study the dynamic top-k team formation problem due to the growing need of a dynamic environment. Third, we develop an unified incremental approach, together with an optimization technique, to handle continuous pattern and data updates, separately and simultaneously, which has not been explored before. Finally, using real-life and synthetic data, we conduct an extensive experimental study to show the effectiveness and efficiency of our graph pattern matching approach for (dynamic) top-k team formation.

cs.DB↗