Search Results for author: Wei Liu

Found 271 papers, 89 papers with code

PointPWC-Net: Cost Volume on Point Clouds for (Self-)Supervised Scene Flow Estimation

1 code implementation ECCV 2020 Wenxuan Wu, Zhi Yuan Wang, Zhuwen Li, Wei Liu, Li Fuxin

We propose a novel end-to-end deep scene flow model, called PointPWC-Net, that directly processes 3D point cloud scenes with large motions in a coarse-to-fine fashion.

Scene Flow Estimation

Decentralized Federated Learning: Balancing Communication and Computing Costs

no code implementations26 Jul 2021 Wei Liu, Li Chen, Wenyi Zhang

Decentralized federated learning (DFL) is a powerful framework of distributed machine learning and decentralized stochastic gradient descent (SGD) is a driving engine for DFL.

A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing

1 code implementation15 Jul 2021 Wei Liu, Pingping Zhang, Yinjie Lei, Xiaolin Huang, Jie Yang, Michael Ng

The effectiveness and superior performance of our approach are validated through comprehensive experiments in a range of applications.

image smoothing

Controlled Caption Generation for Images Through Adversarial Attacks

no code implementations7 Jul 2021 Nayyer Aafaq, Naveed Akhtar, Wei Liu, Mubarak Shah, Ajmal Mian

In contrast, we propose a GAN-based algorithm for crafting adversarial examples for neural image captioning that mimics the internal representation of the CNN such that the resulting deep features of the input image enable a controlled incorrect caption generation through the recurrent network.

Image Captioning Language Modelling

Robust Pose Transfer with Dynamic Details using Neural Video Rendering

no code implementations27 Jun 2021 Yang-tian Sun, Hao-Zhi Huang, Xuan Wang, Yu-Kun Lai, Wei Liu, Lin Gao

Moreover, we introduce a concise temporal loss in the training stage to suppress the detail flickering that is made more visible due to high-quality dynamic details generated by our method.

Neural Rendering Pose Transfer

Stock Market Analysis with Text Data: A Review

no code implementations23 Jun 2021 Kamaladdin Fataliyev, Aneesh Chivukula, Mukesh Prasad, Wei Liu

Then, we cover the analysis techniques and create a taxonomy of the main stock market forecast models.

Simple Distillation Baselines for Improving Small Self-supervised Models

1 code implementation21 Jun 2021 Jindong Gu, Wei Liu, Yonglong Tian

While large self-supervised models have rivalled the performance of their supervised counterparts, small models still struggle.

Subjective Bias in Abstractive Summarization

no code implementations18 Jun 2021 Lei LI, Wei Liu, Marina Litvak, Natalia Vanetik, Jiacheng Pei, Yinan Liu, Siya Qi

Due to the subjectivity of the summarization, it is a good practice to have more than one gold summary for each training document.

Abstractive Text Summarization

Structure-Regularized Attention for Deformable Object Representation

1 code implementation12 Jun 2021 Shenao Zhang, Li Shen, Zhifeng Li, Wei Liu

Capturing contextual dependencies has proven useful to improve the representational power of deep neural networks.

UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase Prediction

1 code implementation9 Jun 2021 Huanqin Wu, Wei Liu, Lei LI, Dan Nie, Tao Chen, Feng Zhang, Di Wang

Keyphrase Prediction (KP) task aims at predicting several keyphrases that can summarize the main idea of the given document.

Attacking Adversarial Attacks as A Defense

no code implementations9 Jun 2021 Boxi Wu, Heng Pan, Li Shen, Jindong Gu, Shuai Zhao, Zhifeng Li, Deng Cai, Xiaofei He, Wei Liu

In this work, we find that the adversarial attacks can also be vulnerable to small perturbations.

A Generative Node-attribute Network Model for Detecting Generalized Structure

no code implementations5 Jun 2021 Wei Liu, Zhenhai Chang, Caiyan Jia, Yimei Zheng

Exploring meaningful structural regularities embedded in networks is a key to understanding and analyzing the structure and function of a network.

Image-to-Video Generation via 3D Facial Dynamics

no code implementations31 May 2021 Xiaoguang Tu, Yingtian Zou, Jian Zhao, Wenjie Ai, Jian Dong, Yuan YAO, Zhikang Wang, Guodong Guo, Zhifeng Li, Wei Liu, Jiashi Feng

Video generation from a single face image is an interesting problem and usually tackled by utilizing Generative Adversarial Networks (GANs) to integrate information from the input face image and a sequence of sparse facial landmarks.

Video Generation Video Prediction

Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter

1 code implementation15 May 2021 Wei Liu, Xiyan Fu, Yue Zhang, Wenming Xiao

Lexicon information and pre-trained models, such as BERT, have been combined to explore Chinese sequence labelling tasks due to their respective strengths.

Named Entity Recognition Part-Of-Speech Tagging

Joint Face Image Restoration and Frontalization for Recognition

no code implementations12 May 2021 Xiaoguang Tu, Jian Zhao, Qiankun Liu, Wenjie Ai, Guodong Guo, Zhifeng Li, Wei Liu, Jiashi Feng

First, MDFR is a well-designed encoder-decoder architecture which extracts feature representation from an input face image with arbitrary low-quality factors and restores it to a high-quality counterpart.

Face Recognition Image Restoration

Poisoning MorphNet for Clean-Label Backdoor Attack to Point Clouds

no code implementations11 May 2021 Guiyu Tian, Wenhao Jiang, Wei Liu, Yadong Mu

To this end, MorphNet jointly optimizes two objectives for sample-adaptive poisoning: a reconstruction loss that preserves the visual similarity between benign / poisoned point clouds, and a classification loss that enforces a modern recognition model of point clouds tends to mis-classify the poisoned sample to a pre-specified target category.

Adversarial Attack Denoising

Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior

no code implementations9 May 2021 Kaihao Zhang, Wenhan Luo, Yanjiang Yu, Wenqi Ren, Fang Zhao, Changsheng Li, Lin Ma, Wei Liu, Hongdong Li

We first use a coarse deraining network to reduce the rain streaks on the input images, and then adopt a pre-trained semantic segmentation network to extract semantic features from the coarse derained image.

Rain Removal Semantic Segmentation

Causal factors discovering from Chinese construction accident cases

no code implementations4 May 2021 Zi-jian Ni, Wei Liu

In China, most of the cases are from accident investigation reports.

Physical world assistive signals for deep neural network classifiers -- neither defense nor attack

no code implementations3 May 2021 Camilo Pestana, Wei Liu, David Glance, Robyn Owens, Ajmal Mian

We discuss how we can exploit these insights to re-think, or avoid, some patterns that might contribute to, or degrade, the detectability of objects in the real-world.

Improved Matrix Gaussian Mechanism for Differential Privacy

no code implementations30 Apr 2021 Jungang Yang, Liyao Xiang, Weiting Li, Wei Liu, Xinbing Wang

The wide deployment of machine learning in recent years gives rise to a great demand for large-scale and high-dimensional data, for which the privacy raises serious concern.

ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows

1 code implementation CVPR 2021 Jie An, Siyu Huang, Yibing Song, Dejing Dou, Wei Liu, Jiebo Luo

The forward inference projects input images into deep features, while the backward inference remaps deep features back to input images in a lossless and unbiased way.

Style Transfer

COSINE: A Web Server for Clonal and Subclonal Structure Inference and Evolution in Cancer Genomics

no code implementations28 Mar 2021 Xiguo Yuan, Yuan Zhao, Yang Guo, Linmei Ge, Wei Liu, Shiyu Wen, Qi Li, Zhangbo Wan, Peina Zheng, Tao Guo, Zhida Li, Martin Peifer, Yupeng Cun

In the past decade, a variety of methods have been developed for subclonal reconstruction using bulk tumor sequencing data.

DeFLOCNet: Deep Image Editing via Flexible Low-level Controls

1 code implementation CVPR 2021 Hongyu Liu, Ziyu Wan, Wei Huang, Yibing Song, Xintong Han, Jing Liao, Bing Jiang, Wei Liu

While existing methods combine an input image and these low-level controls for CNN inputs, the corresponding feature representations are not sufficient to convey user intentions, leading to unfaithfully generated content.

Texture Synthesis

Generalizing Face Forgery Detection with High-frequency Features

1 code implementation CVPR 2021 Yuchen Luo, Yong Zhang, Junchi Yan, Wei Liu

The second is the residual-guided spatial attention module that guides the low-level RGB feature extractor to concentrate more on forgery traces from a new perspective.

Enhanced Spatio-Temporal Interaction Learning for Video Deraining: A Faster and Better Framework

no code implementations23 Mar 2021 Kaihao Zhang, Dongxu Li, Wenhan Luo, Wen-Yan Lin, Fang Zhao, Wenqi Ren, Wei Liu, Hongdong Li

Video deraining is an important task in computer vision as the unwanted rain hampers the visibility of videos and deteriorates the robustness of most outdoor vision systems.

Rain Removal

Human-like Controllable Image Captioning with Verb-specific Semantic Roles

1 code implementation CVPR 2021 Long Chen, Zhihong Jiang, Jun Xiao, Wei Liu

However, we argue that almost all existing objective control signals have overlooked two indispensable characteristics of an ideal control signal: 1) Event-compatible: all visual contents referred to in a single sentence should be compatible with the described activity.

Image Captioning Semantic Role Labeling

Disentangled Cycle Consistency for Highly-realistic Virtual Try-On

1 code implementation CVPR 2021 Chongjian Ge, Yibing Song, Yuying Ge, Han Yang, Wei Liu, Ping Luo

To this end, DCTON can be naturally trained in a self-supervised manner following cycle consistency learning.

Virtual Try-on

LARNet: Lie Algebra Residual Network for Face Recognition

no code implementations15 Mar 2021 Xiaolong Yang, Xiaohong Jia, Dihong Gong, Dong-Ming Yan, Zhifeng Li, Wei Liu

We prove that face rotation in the image space is equivalent to an additive residual component in the feature space of CNNs, which is determined solely by the rotation.

Face Recognition Robust Face Recognition

VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples

1 code implementation CVPR 2021 Tian Pan, Yibing Song, Tianyu Yang, Wenhao Jiang, Wei Liu

By empowering the temporal robustness of the encoder and modeling the temporal decay of the keys, our VideoMoCo improves MoCo temporally based on contrastive learning.

Action Recognition Contrastive Learning +1

Parser-Free Virtual Try-on via Distilling Appearance Flows

2 code implementations CVPR 2021 Yuying Ge, Yibing Song, Ruimao Zhang, Chongjian Ge, Wei Liu, Ping Luo

A recent pioneering work employed knowledge distillation to reduce the dependency of human parsing, where the try-on images produced by a parser-based method are used as supervisions to train a "student" network without relying on segmentation, making the student mimic the try-on ability of the parser-based model.

Human Parsing Knowledge Distillation +1

Learning Discriminative Features using Multi-label Dual Space

no code implementations25 Feb 2021 Ali Braytee, Wei Liu

We show that the learned projection matrix identifies a subset of discriminative features across multiple semantic labels.

Multi-Label Learning

Analogue cosmological particle creation in an ultracold quantum fluid of light

no code implementations16 Feb 2021 Jeff Steinhauer, Murad Abuzarli, Tangui Aladjidi, Tom Bienaimé, Clara Piekarski, Wei Liu, Elisabeth Giacobino, Alberto Bramati, Quentin Glorieux

In inflationary cosmology, the rapid expansion of the early universe resulted in the spontaneous production of cosmological particles from vacuum fluctuations, observable today in the cosmic microwave background anisotropies.

Quantum Gases Optics Quantum Physics

PSA-Net: Deep Learning based Physician Style-Aware Segmentation Network for Post-Operative Prostate Cancer Clinical Target Volume

no code implementations15 Feb 2021 Anjali Balagopal, Howard Morgan, Michael Dohopoloski, Ramsey Timmerman, Jie Shan, Daniel F. Heitjan, Wei Liu, Dan Nguyen, Raquibul Hannan, Aurelie Garant, Neil Desai, Steve Jiang

A classifier is trained to identify which physician has contoured the CTV from just the contour and corresponding CT scan, to determine if physician styles are consistent and learnable.

Rescattering mechanism of weak decays of double-charm baryons

no code implementations28 Jan 2021 Jia-Jie Han, Hua-Yu Jiang, Wei Liu, Zhen-Jun Xiao, Fu-Sheng Yu

The doubly charmed baryon $\Xi_{cc}^{++}$ was recently observed by LHCb via the decay processes of $\Xi_{cc}^{++}\to \Lambda_c^+ K^-\pi^+\pi^+$ and $\Xi_c^+\pi^+$.

High Energy Physics - Phenomenology High Energy Physics - Experiment

Global-Local Propagation Network for RGB-D Semantic Segmentation

no code implementations26 Jan 2021 Sihan Chen, Xinxin Zhu, Wei Liu, Xingjian He, Jing Liu

Depth information matters in RGB-D semantic segmentation task for providing additional geometric information to color images.

Scene Segmentation

Phonon Scattering in the Complex Strain Field of a Dislocation

no code implementations26 Jan 2021 Yandong Sun, Yanguang Zhou, Ramya Gurunathan, Jin-Yu Zhang, Ming Hu, Wei Liu, Ben Xu, G. Jeffrey Snyder

Strain engineering is critical to the performance enhancement of electronic and thermoelectric devices because of its influence on the material thermal conductivity.

Materials Science

CPTR: Full Transformer Network for Image Captioning

no code implementations26 Jan 2021 Wei Liu, Sihan Chen, Longteng Guo, Xinxin Zhu, Jing Liu

Besides, we provide detailed visualizations of the self-attention between patches in the encoder and the "words-to-patches" attention in the decoder thanks to the full Transformer architecture.

Image Captioning

A Closer Look at Temporal Sentence Grounding in Videos: Datasets and Metrics

1 code implementation22 Jan 2021 Yitian Yuan, Xiaohan Lan, Long Chen, Wei Liu, Xin Wang, Wenwu Zhu

Despite Temporal Sentence Grounding in Videos (TSGV) has realized impressive progress over the last few years, current TSGV models tend to capture the moment annotation biases and fail to take full advantage of multi-modal inputs.

Bayesian Optimization Assisted Meal Bolus Decision Based on Gaussian Processes Learning and Risk-Sensitive Control

no code implementations20 Jan 2021 Deheng Cai, Wei Liu, Linong Ji, Dawei Shi

For the case of announced meals, the proposed method achieves satisfactory and similar performance in terms of mean glucose and percentage time in [70, 180] mg/dL without increasing the risk of hypoglycemia.

Gaussian Processes

Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration

no code implementations14 Jan 2021 Congliang Chen, Li Shen, Fangyu Zou, Wei Liu

Adam is one of the most influential adaptive stochastic algorithms for training deep neural networks, which has been pointed out to be divergent even in the simple convex setting via a few simple counterexamples.

Stochastic Optimization

Far-Field Super-Resolution Imaging By Nonlinear Excited Evanescent Waves

no code implementations14 Jan 2021 ZhiHao Zhou, Wei Liu, Jiajing He, Lei Chen, Xin Luo, Dongyi Shen, Jianjun Cao, Yaping Dan, Xianfeng Chen, Wenjie Wan

Abbe's resolution limit, one of the best-known physical limitations, poses a great challenge for any wave systems in imaging, wave transport, and dynamics.

Super-Resolution Optics

Extremize Optical Chiralities through Polarization Singularities

no code implementations11 Jan 2021 Weijin Chen, Qingdong Yang, Yuntian Chen, Wei Liu

Chiral optical effects are generally quantified along some specific incident directions of exciting waves (especially for extrinsic chiralities of achiral structures) or defined as direction-independent properties by averaging the responses among all structure orientations.

Optics

Graph Deformer Network

no code implementations1 Jan 2021 Wenting Zhao, Yuan Fang, Zhen Cui, Tong Zhang, Jian Yang, Wei Liu

In this paper, we propose a simple yet effective graph deformer network (GDN) to fulfill anisotropic convolution filtering on graphs, analogous to the standard convolution operation on images.

Deep-Learning-Enabled Inverse Engineering of Multi-Wavelength Invisibility-to-Superscattering Switching with Phase-Change Materials

1 code implementation25 Dec 2020 Jie Luo, Xun Li, Xinyuan Zhang, Jiajie Guo, Wei Liu, Yun Lai, Yaohui Zhan, Min Huang

Inverse design of nanoparticles for desired scattering spectra and dynamic switching between the two opposite scattering anomalies, i. e. superscattering and invisibility, is important in realizing cloaking, sensing and functional devices.

Optics

LCEval: Learned Composite Metric for Caption Evaluation

1 code implementation24 Dec 2020 Naeha Sharif, Lyndon White, Mohammed Bennamoun, Wei Liu, Syed Afaq Ali Shah

Automatic evaluation metrics hold a fundamental importance in the development and fine-grained analysis of captioning systems.

WEmbSim: A Simple yet Effective Metric for Image Captioning

no code implementations24 Dec 2020 Naeha Sharif, Lyndon White, Mohammed Bennamoun, Wei Liu, Syed Afaq Ali Shah

The area of automatic image caption evaluation is still undergoing intensive research to address the needs of generating captions which can meet adequacy and fluency requirements.

Image Captioning Word Embeddings

SubICap: Towards Subword-informed Image Captioning

no code implementations24 Dec 2020 Naeha Sharif, Mohammed Bennamoun, Wei Liu, Syed Afaq Ali Shah

In this work we address this common limitation of IC systems in dealing with rare words in the corpora.

Image Captioning Language Modelling

Adversarial Learning for Robust Deep Clustering

1 code implementation NeurIPS 2020 Xu Yang, Cheng Deng, Kun Wei, Junchi Yan, Wei Liu

Meanwhile, we devise an adversarial attack strategy to explore samples that easily fool the clustering layers but do not impact the performance of the deep embedding.

Adversarial Attack Deep Clustering

Towards Playing Full MOBA Games with Deep Reinforcement Learning

no code implementations NeurIPS 2020 Deheng Ye, Guibin Chen, Wen Zhang, Sheng Chen, Bo Yuan, Bo Liu, Jia Chen, Zhao Liu, Fuhao Qiu, Hongsheng Yu, Yinyuting Yin, Bei Shi, Liang Wang, Tengfei Shi, Qiang Fu, Wei Yang, Lanxiao Huang, Wei Liu

However, existing work falls short in handling the raw game complexity caused by the explosion of agent combinations, i. e., lineups, when expanding the hero pool in case that OpenAI's Dota AI limits the play to a pool of only 17 heroes.

Dota 2 League of Legends

Towards Dark Jargon Interpretation in Underground Forums

no code implementations5 Nov 2020 Dominic Seyler, Wei Liu, XiaoFeng Wang, ChengXiang Zhai

Dark jargons are benign-looking words that have hidden, sinister meanings and are used by participants of underground forums for illicit behavior.

Defense-friendly Images in Adversarial Attacks: Dataset and Metrics for Perturbation Difficulty

1 code implementation5 Nov 2020 Camilo Pestana, Wei Liu, David Glance, Ajmal Mian

We propose three metrics to determine the proportion of robust images in a dataset and provide scoring to determine the dataset bias.

Adversarial Attack

GAIN: Graph Attention & Interaction Network for Inductive Semi-Supervised Learning over Large-scale Graphs

no code implementations3 Nov 2020 Yunpeng Weng, Xu Chen, Liang Chen, Wei Liu

Most existing GNN models exploit a single type of aggregator (e. g., mean-pooling) to aggregate neighboring nodes information, and then add or concatenate the output of aggregator to the current representation vector of the center node.

Graph Attention Link Prediction +1

Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies

1 code implementation NeurIPS 2020 Yuehua Zhu, Muli Yang, Cheng Deng, Wei Liu

In this paper, we propose a novel Proxy-based deep Graph Metric Learning (ProxyGML) approach from the perspective of graph classification, which uses fewer proxies yet achieves better comprehensive performance.

General Classification Graph Classification +1

Face Hallucination via Split-Attention in Split-Attention Network

1 code implementation22 Oct 2020 Tao Lu, Yuanzhi Wang, Yanduo Zhang, Yu Wang, Wei Liu, Zhongyuan Wang, Junjun Jiang

However, most of them fail to take into account the overall facial profile and fine texture details simultaneously, resulting in reduced naturalness and fidelity of the reconstructed face, and further impairing the performance of downstream tasks (e. g., face detection, facial recognition).

Face Detection Face Hallucination +3

Probing the Phonon Mean Free Paths in Dislocation Core by Molecular Dynamics Simulation

no code implementations18 Oct 2020 Yandong Sun, Yanguang Zhou, Ming Hu, G. Jeffrey Snyder, Ben Xu, Wei Liu

In this study, the 1D McKelvey-Shockley phonon BTE method was extended to model inhomogeneous materials, where the effect of defects on the phonon MFPs is explicitly obtained.

Materials Science Computational Physics 80A05 I.6.0

Deep-HOSeq: Deep Higher Order Sequence Fusion for Multimodal Sentiment Analysis

1 code implementation16 Oct 2020 Sunny Verma, Jiwei Wang, Zhefeng Ge, Rujia Shen, Fan Jin, Yang Wang, Fang Chen, Wei Liu

In this research, we first propose a common network to discover both intra-modal and inter-modal dynamics by utilizing basic LSTMs and tensor based convolution networks.

Multimodal Sentiment Analysis

Parsimonious Quantile Regression of Financial Asset Tail Dynamics via Sequential Learning

no code implementations NeurIPS 2018 Xing Yan, Weizhong Zhang, Lin Ma, Wei Liu, Qi Wu

We propose a parsimonious quantile regression framework to learn the dynamic tail behaviors of financial asset returns.

Time Series

Attn-HybridNet: Improving Discriminability of Hybrid Features with Attention Fusion

2 code implementations13 Oct 2020 Sunny Verma, Chen Wang, Liming Zhu, Wei Liu

The principal component analysis network (PCANet) is an unsupervised parsimonious deep network, utilizing principal components as filters in its convolution layers.

Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework

no code implementations10 Oct 2020 Wenxiao Wang, Minghao Chen, Shuai Zhao, Long Chen, Jinming Hu, Haifeng Liu, Deng Cai, Xiaofei He, Wei Liu

Specifically, it first casts the relationships between a certain model's accuracy and depth/width/resolution into a polynomial regression and then maximizes the polynomial to acquire the optimal values for the three dimensions.

Network Pruning Neural Architecture Search

Targeted Attention Attack on Deep Learning Models in Road Sign Recognition

1 code implementation9 Oct 2020 Xinghao Yang, Weifeng Liu, Shengli Zhang, Wei Liu, DaCheng Tao

To alleviate these problems, this paper proposes the targeted attention attack (TAA) method for real world road sign attack.

Traffic Sign Recognition

Knowledge Adaption for Demand Prediction based on Multi-task Memory Neural Network

no code implementations12 Sep 2020 Can Li, Lei Bai, Wei Liu, Lina Yao, S Travis Waller

Accurate demand forecasting of different public transport modes(e. g., buses and light rails) is essential for public service operation. However, the development level of various modes often varies sig-nificantly, which makes it hard to predict the demand of the modeswith insufficient knowledge and sparse station distribution (i. e., station-sparse mode).

Multi-Task Learning

Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics

2 code implementations31 Aug 2020 Jiangliu Wang, Jianbo Jiao, Linchao Bao, Shengfeng He, Wei Liu, Yun-hui Liu

Specifically, given an unlabeled video clip, we compute a series of spatio-temporal statistical summaries, such as the spatial location and dominant direction of the largest motion, the spatial location and dominant color of the largest color diversity along the temporal axis, etc.

Action Recognition Representation Learning +2

Unravelling the Architecture of Membrane Proteins with Conditional Random Fields

no code implementations6 Aug 2020 Lior Lukov, Sanjay Chawla, Wei Liu, Brett Church, Gaurav Pandey

In this paper, we will show that the recently introduced graphical model: Conditional Random Fields (CRF) provides a template to integrate micro-level information about biological entities into a mathematical model to understand their macro-level behavior.

Learning Modality Interaction for Temporal Sentence Localization and Event Captioning in Videos

no code implementations ECCV 2020 Shaoxiang Chen, Wenhao Jiang, Wei Liu, Yu-Gang Jiang

Inspired by the fact that there exist cross-modal interactions in the human brain, we propose a novel method for learning pairwise modality interactions in order to better exploit complementary information for each pair of modalities in videos and thus improve performances on both tasks.

Face Super-Resolution Guided by 3D Facial Priors

1 code implementation ECCV 2020 Xiaobin Hu, Wenqi Ren, John LaMaster, Xiaochun Cao, Xiaoming Li, Zechao Li, Bjoern Menze, Wei Liu

State-of-the-art face super-resolution methods employ deep convolutional neural networks to learn a mapping between low- and high- resolution facial patterns by exploring local appearance knowledge.

Super-Resolution

Attention-based Residual Speech Portrait Model for Speech to Face Generation

no code implementations9 Jul 2020 Jianrong Wang, Xiaosheng Hu, Li Liu, Wei Liu, Mei Yu, Tianyi Xu

Given a speaker's speech, it is interesting to see if it is possible to generate this speaker's face.

Face Generation

Low-Resource Generation of Multi-hop Reasoning Questions

no code implementations ACL 2020 Jianxing Yu, Wei Liu, Shuang Qiu, Qinliang Su, Kai Wang, Xiaojun Quan, Jian Yin

Specifically, we first build a multi-hop generation model and guide it to satisfy the logical rationality by the reasoning chain extracted from a given text.

Machine Reading Comprehension

AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networks

1 code implementation16 Jun 2020 Yuesong Tian, Li Shen, Guinan Su, Zhifeng Li, Wei Liu

To this end, we propose a fully differentiable search framework for generative adversarial networks, dubbed alphaGAN.

Real-time Universal Style Transfer on High-resolution Images via Zero-channel Pruning

no code implementations16 Jun 2020 Jie An, Tao Li, Hao-Zhi Huang, Li Shen, Xuan Wang, Yongyi Tang, Jinwen Ma, Wei Liu, Jiebo Luo

Extracting effective deep features to represent content and style information is the key to universal style transfer.

Style Transfer

DFraud3- Multi-Component Fraud Detection freeof Cold-start

no code implementations10 Jun 2020 Saeedreza Shehnepoor, Roberto Togneri, Wei Liu, Mohammed Bennamoun

In this research, instead of focusing only on one component, detecting either fraud reviews or fraud users (fraudsters), vector representations are learnt for each component, enabling multi-component classification.

Component Classification Fraud Detection +1

TCDesc: Learning Topology Consistent Descriptors

no code implementations5 Jun 2020 Honghu Pan, Fanyang Meng, Zhenyu He, Yongsheng Liang, Wei Liu

Then we define topology distance between descriptors as the difference of their topology vectors.

CPOT: Channel Pruning via Optimal Transport

no code implementations21 May 2020 Yucong Shen, Li Shen, Hao-Zhi Huang, Xuan Wang, Wei Liu

Recent advances in deep neural networks (DNNs) lead to tremendously growing network parameters, making the deployments of DNNs on platforms with limited resources extremely difficult.

Image-to-Image Translation

Hierarchical Regression Network for Spectral Reconstruction from RGB Images

1 code implementation10 May 2020 Yuzhi Zhao, Lai-Man Po, Qiong Yan, Wei Liu, Tingyu Lin

Hyperspectral reconstruction from RGB images denotes a reverse process of hyperspectral imaging by discovering an inverse response function.

Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation

6 code implementations7 May 2020 Zhaohui Zheng, Ping Wang, Dongwei Ren, Wei Liu, Rongguang Ye, QinGhua Hu, WangMeng Zuo

In this paper, we propose Complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding box regression and Non-Maximum Suppression (NMS), leading to notable gains of average precision (AP) and average recall (AR), without the sacrifice of inference efficiency.

Instance Segmentation Object Detection +1

Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks

1 code implementation ICML 2020 Zhishuai Guo, Mingrui Liu, Zhuoning Yuan, Li Shen, Wei Liu, Tianbao Yang

In this paper, we study distributed algorithms for large-scale AUC maximization with a deep neural network as a predictive model.

Distributed Optimization

Energy Efficient User Clustering, Hybrid Precoding and Power Optimization in Terahertz MIMO-NOMA Systems

no code implementations3 May 2020 Haijun Zhang, Haisen Zhang, Wei Liu, Keping Long, Jiangbo Dong, Victor C. M. Leung

Considering the power consumption and implementation complexity, the hybrid precoding scheme based on the sub-connection structure is adopted.

Quantized Adam with Error Feedback

no code implementations29 Apr 2020 Congliang Chen, Li Shen, Hao-Zhi Huang, Wei Liu

In this paper, we present a distributed variant of adaptive stochastic gradient method for training deep neural networks in the parameter-server model.

Quantization

Knowledge-guided Deep Reinforcement Learning for Interactive Recommendation

no code implementations17 Apr 2020 Xiaocong Chen, Chaoran Huang, Lina Yao, Xianzhi Wang, Wei Liu, Wenjie Zhang

Interactive recommendation aims to learn from dynamic interactions between items and users to achieve responsiveness and accuracy.

Decision Making Knowledge Graphs

Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation

1 code implementation EMNLP 2020 Dayiheng Liu, Yeyun Gong, Jie Fu, Wei Liu, Yu Yan, Bo Shao, Daxin Jiang, Jiancheng Lv, Nan Duan

Furthermore, we propose a simple and effective method to mine the keyphrases of interest in the news article and build a first large-scale keyphrase-aware news headline corpus, which contains over 180K aligned triples of $<$news article, headline, keyphrase$>$.

Deblurring by Realistic Blurring

1 code implementation CVPR 2020 Kaihao Zhang, Wenhan Luo, Yiran Zhong, Lin Ma, Bjorn Stenger, Wei Liu, Hongdong Li

To address this problem, we propose a new method which combines two GAN models, i. e., a learning-to-Blur GAN (BGAN) and learning-to-DeBlur GAN (DBGAN), in order to learn a better model for image deblurring by primarily learning how to blur images.

Deblurring

Progressive Multi-Stage Learning for Discriminative Tracking

no code implementations1 Apr 2020 Weichao Li, Xi Li, Omar Elfarouk Bourahla, Fuxian Huang, Fei Wu, Wei Liu, Zhiheng Wang, Hongmin Liu

Visual tracking is typically solved as a discriminative learning problem that usually requires high-quality samples for online model adaptation.

Visual Tracking

E2EET: From Pipeline to End-to-end Entity Typing via Transformer-Based Embeddings

no code implementations23 Mar 2020 Michael Stewart, Wei Liu

They are therefore sensitive to window size selection and are unable to incorporate the context of the entire document.

Entity Typing Named Entity Recognition

Towards Photo-Realistic Virtual Try-On by Adaptively Generating$\leftrightarrow$Preserving Image Content

1 code implementation12 Mar 2020 Han Yang, Ruimao Zhang, Xiaobao Guo, Wei Liu, WangMeng Zuo, Ping Luo

First, a semantic layout generation module utilizes semantic segmentation of the reference image to progressively predict the desired semantic layout after try-on.

Semantic Segmentation Virtual Try-on

An Improved DOA Estimation Method for a Mixture of Circular and Non-Circular Signals Based on Sparse Arrays

no code implementations11 Mar 2020 Jingjing Cai, Wei Liu, Ru Zong, Yangyang Dong

Sparse arrays have attracted a lot of interests recently for their capability of providing more degrees of freedom than traditional uniform linear arrays.

Adversarial Perturbations Prevail in the Y-Channel of the YCbCr Color Space

no code implementations25 Feb 2020 Camilo Pestana, Naveed Akhtar, Wei Liu, David Glance, Ajmal Mian

Our results show that our approach achieves the best balance between defence against adversarial attacks such as FGSM, PGD and DDN and maintaining the original accuracies of VGG-16, ResNet50 and DenseNet121 on clean images.

Optimal Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization

no code implementations NeurIPS 2020 Yan Yan, Yi Xu, Qihang Lin, Wei Liu, Tianbao Yang

In this paper, we bridge this gap by providing a sharp analysis of epoch-wise stochastic gradient descent ascent method (referred to as Epoch-GDA) for solving strongly convex strongly concave (SCSC) min-max problems, without imposing any additional assumption about smoothness or the function's structure.

Graph Inference Learning for Semi-supervised Classification

no code implementations ICLR 2020 Chunyan Xu, Zhen Cui, Xiaobin Hong, Tong Zhang, Jian Yang, Wei Liu

In this work, we address semi-supervised classification of graph data, where the categories of those unlabeled nodes are inferred from labeled nodes as well as graph structures.

General Classification Node Classification

Potential Passenger Flow Prediction: A Novel Study for Urban Transportation Development

no code implementations7 Dec 2019 Yongshun Gong, Zhibin Li, Jian Zhang, Wei Liu, Jin-Feng Yi

In this paper, this specific problem is termed as potential passenger flow (PPF) prediction, which is a novel and important study connected with urban computing and intelligent transportation systems.

MULTI-VIEW LEARNING Recommendation Systems

Fast Stochastic Ordinal Embedding with Variance Reduction and Adaptive Step Size

no code implementations1 Dec 2019 Ke Ma, Jinshan Zeng, Qianqian Xu, Xiaochun Cao, Wei Liu, Yuan YAO

Learning representation from relative similarity comparisons, often called ordinal embedding, gains rising attention in recent years.

Cross-Modal Learning with Adversarial Samples

1 code implementation NeurIPS 2019 Chao Li, Shangqian Gao, Cheng Deng, De Xie, Wei Liu

Extensive experiments on two cross-modal benchmark datasets show that the adversarial examples produced by our CMLA are efficient in fooling a target deep cross-modal hashing network.

Learning Multi-level Weight-centric Features for Few-shot Learning

no code implementations28 Nov 2019 Mingjiang Liang, Shaoli Huang, Shirui Pan, Mingming Gong, Wei Liu

Few-shot learning is currently enjoying a considerable resurgence of interest, aided by the recent advance of deep learning.

Few-Shot Learning

PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point Clouds

1 code implementation27 Nov 2019 Wenxuan Wu, Zhiyuan Wang, Zhuwen Li, Wei Liu, Li Fuxin

We propose a novel end-to-end deep scene flow model, called PointPWC-Net, on 3D point clouds in a coarse-to-fine fashion.

Scene Flow Estimation

Multi-Task Driven Feature Models for Thermal Infrared Tracking

1 code implementation26 Nov 2019 Qiao Liu, Xin Li, Zhenyu He, Nana Fan, Di Yuan, Wei Liu, Yonsheng Liang

These two feature models are learned using a multi-task matching framework and are jointly optimized on the TIR tracking task.

Thermal Infrared Object Tracking

Empirical Autopsy of Deep Video Captioning Frameworks

no code implementations21 Nov 2019 Nayyer Aafaq, Naveed Akhtar, Wei Liu, Ajmal Mian

We perform extensive experiments by varying the constituent components of the video captioning framework, and quantify the performance gains that are possible by mere component selection.

Language Modelling Video Captioning +1

Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression

17 code implementations19 Nov 2019 Zhaohui Zheng, Ping Wang, Wei Liu, Jinze Li, Rongguang Ye, Dongwei Ren

By incorporating DIoU and CIoU losses into state-of-the-art object detection algorithms, e. g., YOLO v3, SSD and Faster RCNN, we achieve notable performance gains in terms of not only IoU metric but also GIoU metric.

Object Detection

Word-level Lexical Normalisation using Context-Dependent Embeddings

no code implementations13 Nov 2019 Michael Stewart, Wei Liu, Rachel Cardell-Oliver

In this paper we introduce a word-level GRU-based LN model and investigate the effectiveness of recent embedding techniques on word-level LN.

Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos

1 code implementation NeurIPS 2019 Yitian Yuan, Lin Ma, Jingwen Wang, Wei Liu, Wenwu Zhu

Temporal sentence grounding in videos aims to detect and localize one target video segment, which semantically corresponds to a given sentence.

Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation

1 code implementation NeurIPS 2019 Qiming Zhang, Jing Zhang, Wei Liu, DaCheng Tao

Although there has been a progress in matching the marginal distributions between two domains, the classifier favors the source domain features and makes incorrect predictions on the target domain due to category-agnostic feature alignment.

Semantic Segmentation Synthetic-to-Real Translation +1

Diversifying Topic-Coherent Response Generation for Natural Multi-turn Conversations

no code implementations24 Oct 2019 Fei Hu, Wei Liu, Ajmal Saeed Mian, Li Li

In this paper, we propose the Topic-coherent Hierarchical Recurrent Encoder-Decoder model (THRED) to diversify the generated responses without deviating the contextual topics for multi-turn conversations.

Vatex Video Captioning Challenge 2020: Multi-View Features and Hybrid Reward Strategies for Video Captioning

no code implementations17 Oct 2019 Xinxin Zhu, Longteng Guo, Peng Yao, Shichen Lu, Wei Liu, Jing Liu

This report describes our solution for the VATEX Captioning Challenge 2020, which requires generating descriptions for the videos in both English and Chinese languages.

Video Captioning

Context-Gated Convolution

1 code implementation ECCV 2020 Xudong Lin, Lin Ma, Wei Liu, Shih-Fu Chang

As such, being aware of the global context, the modulated convolution kernel of our proposed CGC can better extract representative local patterns and compose discriminative features.

Action Recognition Image Classification +1

Deep Multiphase Level Set for Scene Parsing

no code implementations8 Oct 2019 Pingping Zhang, Wei Liu, Yinjie Lei, Hongyu Wang, Huchuan Lu

The proposed method consists of three modules, i. e., recurrent FCNs, adaptive multiphase level set, and deeply supervised learning.

Scene Parsing Semantic Segmentation

Accelerating Federated Learning via Momentum Gradient Descent

no code implementations8 Oct 2019 Wei Liu, Li Chen, Yunfei Chen, Wenyi Zhang

The proposed momentum federated learning (MFL) uses momentum gradient descent (MGD) in the local update step of FL system.

Federated Learning

Spatiotemporal Co-attention Recurrent Neural Networks for Human-Skeleton Motion Prediction

no code implementations29 Sep 2019 Xiangbo Shu, Liyan Zhang, Guo-Jun Qi, Wei Liu, Jinhui Tang

To this end, we propose a novel Skeleton-joint Co-attention Recurrent Neural Networks (SC-RNN) to capture the spatial coherence among joints, and the temporal evolution among skeletons simultaneously on a skeleton-joint co-attention feature map in spatiotemporal space.

Human motion prediction motion prediction

Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning

no code implementations ICCV 2019 Yipeng Sun, Jiaming Liu, Wei Liu, Junyu Han, Errui Ding, Jingtuo Liu

Most existing text reading benchmarks make it difficult to evaluate the performance of more advanced deep learning models in large vocabularies due to the limited amount of training data.

ICDM 2019 Knowledge Graph Contest: Team UWA

2 code implementations4 Sep 2019 Michael Stewart, Majigsuren Enkhsaikhan, Wei Liu

We present an overview of our triple extraction system for the ICDM 2019 Knowledge Graph Contest.

graph construction

Multi-lingual Wikipedia Summarization and Title Generation On Low Resource Corpus

no code implementations RANLP 2019 Wei Liu, Lei LI, Zuying Huang, Yinan Liu

MultiLing 2019 Headline Generation Task on Wikipedia Corpus raised a critical and practical problem: multilingual task on low resource corpus.

Extractive Summarization Language Modelling +1

DV3+HED+: A DCNNs-based Framework to Monitor Temporary Works and ESAs in Railway Construction Project Using VHR Satellite Images

1 code implementation29 Aug 2019 Rui Guo, Ronghua Liu, Na Li, Wei Liu

Current VHR(Very High Resolution) satellite images enable the detailed monitoring of the earth and can capture the ongoing works of railway construction.

Edge Detection Semantic Segmentation

Controllable Video Captioning with POS Sequence Guidance Based on Gated Fusion Network

1 code implementation ICCV 2019 Bairui Wang, Lin Ma, Wei zhang, Wenhao Jiang, Jingwen Wang, Wei Liu

In this paper, we propose to guide the video caption generation with Part-of-Speech (POS) information, based on a gated fusion of multiple representations of input videos.

Video Captioning

From Text to Sound: A Preliminary Study on Retrieving Sound Effects to Radio Stories

no code implementations20 Aug 2019 Songwei Ge, Curtis Xuan, Ruihua Song, Chao Zou, Wei Liu, Jin Zhou

In this paper, we address the problem of automatically adding sound effects to radio stories with a retrieval-based model.

Multimodal Emotion Recognition Using Deep Canonical Correlation Analysis

1 code implementation13 Aug 2019 Wei Liu, Jie-Lin Qiu, Wei-Long Zheng, Bao-liang Lu

We evaluate the performance of DCCA on five multimodal datasets: the SEED, SEED-IV, SEED-V, DEAP, and DREAMER datasets.

General Classification Multimodal Emotion Recognition

Multi-Frame Content Integration with a Spatio-Temporal Attention Mechanism for Person Video Motion Transfer

no code implementations12 Aug 2019 Kun Cheng, Hao-Zhi Huang, Chun Yuan, Lingyiqing Zhou, Wei Liu

Specifically, we transfer the motion of one person in a target video to another person in a source video, while preserving the appearance of the source person.

Video Generation

Central Similarity Quantization for Efficient Image and Video Retrieval

1 code implementation CVPR 2020 Li Yuan, Tao Wang, Xiaopeng Zhang, Francis EH Tay, Zequn Jie, Wei Liu, Jiashi Feng

In this work, we propose a new \emph{global} similarity metric, termed as \emph{central similarity}, with which the hash codes of similar data pairs are encouraged to approach a common center and those for dissimilar pairs to converge to different centers, to improve hash learning efficiency and retrieval accuracy.

Quantization Video Retrieval

Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion

no code implementations ICCV 2019 Pingping Zhang, Wei Liu, Yinjie Lei, Huchuan Lu, Xiaoyun Yang

To address these issues, in this work we propose a novel deep learning framework, named Cascaded Context Pyramid Network (CCPNet), to jointly infer the occupancy and semantic labels of a volumetric 3D scene from a single depth image.

A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing

no code implementations23 Jul 2019 Wei Liu, Pingping Zhang, Yinjie Lei, Xiaolin Huang, Jie Yang, Ian Reid

In this paper, a non-convex non-smooth optimization framework is proposed to achieve diverse smoothing natures where even contradictive smoothing behaviors can be achieved.

image smoothing

Global injectivity of differentiable maps via W-condition in R^2

no code implementations25 Jun 2019 Wei Liu

In this paper, we study the intrinsic relation between the global injectivity of differentiable local homeomorphisms $F$ and the rate that tends to zero of $Spec(F)$ in $\mathbb{R}^2$, where $Spec(F)$ denotes the set of all (complex) eigenvalues of $DF(x)$, for all $x\in \mathbb{R}^2$.

Functional Analysis Operator Algebras 14R15, 14E07, 14E09

Understanding Distributional Ambiguity via Non-robust Chance Constraint

no code implementations3 Jun 2019 Qi Wu, Shumin Ma, Cheuk Hang Leung, Wei Liu, Nanbo Peng

Without the boundedness constraint, the CCO problem is shown to perform uniformly better than the DRO problem, irrespective of the radius of the ambiguity set, the choice of the divergence measure, or the tail heaviness of the center distribution.

Portfolio Optimization

Reconstruct and Represent Video Contents for Captioning via Reinforcement Learning

no code implementations3 Jun 2019 Wei Zhang, Bairui Wang, Lin Ma, Wei Liu

Unlike previous video captioning work mainly exploiting the cues of video contents to make a language description, we propose a reconstruction network (RecNet) in a novel encoder-decoder-reconstructor architecture, which leverages both forward (video to sentence) and backward (sentence to video) flows for video captioning.

Video Captioning

An Encoding Strategy Based Word-Character LSTM for Chinese NER

1 code implementation NAACL 2019 Wei Liu, Tongge Xu, Qinghua Xu, Jiayu Song, Yueran Zu

A recently proposed lattice model has demonstrated that words in character sequence can provide rich word boundary information for character-based Chinese NER model.

NER

High-Level Semantic Feature Detection: A New Perspective for Pedestrian Detection

1 code implementation CVPR 2019 Wei Liu, Shengcai Liao, Weiqiang Ren, Weidong Hu, Yinan Yu

Like edges, corners, blobs and other feature detectors, the proposed detector scans for feature points all over the image, for which the convolution is naturally suited.

Object Detection Pedestrian Detection

Electronic structure and $H$-$T$ phase diagram of Eu(Fe$_{1-x}$Rh$_x$)$_2$As$_2$

no code implementations28 May 2019 Shaozhu Xiao, Darren C. Peets, Wei Liu, Shiju Zhang, Ya Feng, Wen-He Jiao, Guang-Han Cao, Eike F. Schwier, Kenya Shimada, Cong Li, Xingjiang Zhou, Shaolong He

The iron-based superconductors represent a promising platform for high-temperature superconductivity, but the interactions underpinning their pairing present a puzzle.

Superconductivity Strongly Correlated Electrons

Spatio-temporal Video Re-localization by Warp LSTM

no code implementations CVPR 2019 Yang Feng, Lin Ma, Wei Liu, Jiebo Luo

The need for efficiently finding the video content a user wants is increasing because of the erupting of user-generated videos on the Web.

Video Retrieval

Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables

1 code implementation CVPR 2019 Yan Xu, Baoyuan Wu, Fumin Shen, Yanbo Fan, Yong Zhang, Heng Tao Shen, Wei Liu

Due to the sequential dependencies among words in a caption, we formulate the generation of adversarial noises for targeted partial captions as a structured output learning problem with latent variables.

Adversarial Attack Image Captioning

DistillHash: Unsupervised Deep Hashing by Distilling Data Pairs

no code implementations CVPR 2019 Erkun Yang, Tongliang Liu, Cheng Deng, Wei Liu, DaCheng Tao

To address this issue, we propose a novel deep unsupervised hashing model, dubbed DistillHash, which can learn a distilled data set consisted of data pairs, which have confidence similarity signals.

Semantic Similarity Semantic Textual Similarity

FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing

no code implementations6 May 2019 Sen-Zhe Xu, Hao-Zhi Huang, Shi-Min Hu, Wei Liu

On the basis of the FaceShapeGene, a novel part-wise face image editing system is developed, which contains a shape-remix network and a conditional label-to-face transformer.

Image Manipulation

Shared Predictive Cross-Modal Deep Quantization

no code implementations16 Apr 2019 Erkun Yang, Cheng Deng, Chao Li, Wei Liu, Jie Li, DaCheng Tao

In this paper, we propose a deep quantization approach, which is among the early attempts of leveraging deep neural networks into quantization-based cross-modal similarity search.

Quantization

Decorrelated Adversarial Learning for Age-Invariant Face Recognition

1 code implementation CVPR 2019 Hao Wang, Dihong Gong, Zhifeng Li, Wei Liu

To reduce such a discrepancy, in this paper we propose a novel algorithm to remove age-related components from features mixed with both identity and age information.

Age-Invariant Face Recognition

Efficient Decision-based Black-box Adversarial Attacks on Face Recognition

no code implementations CVPR 2019 Yinpeng Dong, Hang Su, Baoyuan Wu, Zhifeng Li, Wei Liu, Tong Zhang, Jun Zhu

In this paper, we evaluate the robustness of state-of-the-art face recognition models in the decision-based black-box attack setting, where the attackers have no access to the model parameters and gradients, but can only acquire hard-label predictions by sending queries to the target model.

Face Recognition

MVF-Net: Multi-View 3D Face Morphable Model Regression

no code implementations CVPR 2019 Fanzi Wu, Linchao Bao, Yajing Chen, Yonggen Ling, Yibing Song, Songnan Li, King Ngi Ngan, Wei Liu

The main ingredient of the view alignment loss is a differentiable dense optical flow estimator that can backpropagate the alignment errors between an input view and a synthetic rendering from another input view, which is projected to the target view through the 3D shape to be inferred.

Optical Flow Estimation

Center and Scale Prediction: A Box-free Approach for Pedestrian and Face Detection

no code implementations CVPR 2019 Wei Liu, Irtiza Hasan, Shengcai Liao

Like edges, corners, blobs and other feature detectors, the proposed detector scans for feature points all over the image, for which the convolution is naturally suited.

Ranked #3 on Pedestrian Detection on Caltech (using extra training data)

Face Detection Object Detection +1

Stacked Semantic-Guided Network for Zero-Shot Sketch-Based Image Retrieval

no code implementations3 Apr 2019 Hao Wang, Cheng Deng, Xinxu Xu, Wei Liu, Xinbo Gao, DaCheng Tao

Previous works mostly focus on a generative approach that takes a highly abstract and sparse sketch as input and then synthesizes the corresponding natural image.

Sketch-Based Image Retrieval Transfer Learning

PFLD: A Practical Facial Landmark Detector

15 code implementations28 Feb 2019 Xiaojie Guo, Siyuan Li, Jinke Yu, Jiawan Zhang, Jiayi Ma, Lin Ma, Wei Liu, Haibin Ling

Being accurate, efficient, and compact is essential to a facial landmark detector for practical use.

Face Alignment Facial Landmark Detection

Fully-Featured Attribute Transfer

no code implementations17 Feb 2019 De Xie, Muli Yang, Cheng Deng, Wei Liu, DaCheng Tao

Image attribute transfer aims to change an input image to a target one with expected attributes, which has received significant attention in recent years.

Image Generation

End-to-End Single Image Fog Removal using Enhanced Cycle Consistent Adversarial Networks

no code implementations4 Feb 2019 Wei Liu, Xianxu Hou, Jiang Duan, Guoping Qiu

In addition, we also contribute the first real world nature fog-fogfree image dataset for defogging research.

Salient Object Detection with Lossless Feature Reflection and Weighted Structural Loss

no code implementations21 Jan 2019 Pingping Zhang, Wei Liu, Huchuan Lu, Chunhua Shen

Inspired by the intrinsic reflection of natural images, in this paper we propose a novel feature learning framework for large-scale salient object detection.

RGB Salient Object Detection Saliency Detection +1

SAFE: Scale Aware Feature Encoder for Scene Text Recognition

no code implementations17 Jan 2019 Wei Liu, Chaofeng Chen, Kwan-Yee K. Wong

We propose a novel scale aware feature encoder (SAFE) that is designed specifically for encoding characters with different scales.

Scene Text Scene Text Recognition

Hierarchical Macro Strategy Model for MOBA Game AI

no code implementations19 Dec 2018 Bin Wu, Qiang Fu, Jing Liang, Peng Qu, Xiaoqian Li, Liang Wang, Wei Liu, Wei Yang, Yongsheng Liu

In this paper, we propose a novel learning-based Hierarchical Macro Strategy model for mastering MOBA games, a sub-genre of RTS games.

Semi-Supervised Learning for Face Sketch Synthesis in the Wild

1 code implementation12 Dec 2018 Chaofeng Chen, Wei Liu, Xiao Tan, Kwan-Yee K. Wong

Instead of supervising the network with ground truth sketches, we first perform patch matching in feature space between the input photo and photos in a small reference set of photo-sketch pairs.

Face Sketch Synthesis Patch Matching

Real-Time Referring Expression Comprehension by Single-Stage Grounding Network

no code implementations9 Dec 2018 Xinpeng Chen, Lin Ma, Jingyuan Chen, Zequn Jie, Wei Liu, Jiebo Luo

Experiments on RefCOCO, RefCOCO+, and RefCOCOg datasets demonstrate that our proposed SSG without relying on any region proposals can achieve comparable performance with other advanced models.

Referring Expression Comprehension

Learning to Compose Dynamic Tree Structures for Visual Contexts

5 code implementations CVPR 2019 Kaihua Tang, Hanwang Zhang, Baoyuan Wu, Wenhan Luo, Wei Liu

We propose to compose dynamic tree structures that place the objects in an image into a visual context, helping visual reasoning tasks such as scene graph generation and visual Q&A.

Graph Generation Scene Graph Generation +2

Generalizing Graph Matching beyond Quadratic Assignment Model

no code implementations NeurIPS 2018 Tianshu Yu, Junchi Yan, Yilin Wang, Wei Liu, Baoxin Li

Graph matching has received persistent attention over decades, which can be formulated as a quadratic assignment problem (QAP).

Graph Matching

Deep Non-Blind Deconvolution via Generalized Low-Rank Approximation

no code implementations NeurIPS 2018 Wenqi Ren, Jiawei Zhang, Lin Ma, Jinshan Pan, Xiaochun Cao, WangMeng Zuo, Wei Liu, Ming-Hsuan Yang

In this paper, we present a deep convolutional neural network to capture the inherent properties of image degradation, which can handle different kernels and saturated pixels in a unified framework.

Deblurring

Multi-granularity Generator for Temporal Action Proposal

no code implementations CVPR 2019 Yuan Liu, Lin Ma, Yifeng Zhang, Wei Liu, Shih-Fu Chang

In this paper, we propose a multi-granularity generator (MGG) to perform the temporal action proposal from different granularity perspectives, relying on the video visual features equipped with the position embedding information.

Action Recognition Temporal Action Proposal Generation

Unsupervised Image Captioning

1 code implementation CVPR 2019 Yang Feng, Lin Ma, Wei Liu, Jiebo Luo

Instead of relying on manually labeled image-sentence pairs, our proposed model merely requires an image set, a sentence corpus, and an existing visual concept detector.

Image Captioning

A Sufficient Condition for Convergences of Adam and RMSProp

no code implementations CVPR 2019 Fangyu Zou, Li Shen, Zequn Jie, Weizhong Zhang, Wei Liu

Adam and RMSProp are two of the most influential adaptive stochastic algorithms for training deep neural networks, which have been pointed out to be divergent even in the convex setting via a few simple counterexamples.

Stochastic Optimization

Super-Identity Convolutional Neural Network for Face Hallucination

no code implementations ECCV 2018 Kaipeng Zhang, Zhanpeng Zhang, Chia-Wen Cheng, Winston H. Hsu, Yu Qiao, Wei Liu, Tong Zhang

Face hallucination is a generative task to super-resolve the facial image with low resolution while human perception of face heavily relies on identity information.

Face Generation Face Hallucination

Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance

1 code implementation4 Nov 2018 Zechun Liu, Wenhan Luo, Baoyuan Wu, Xin Yang, Wei Liu, Kwang-Ting Cheng

To address the training difficulty, we propose a training algorithm using a tighter approximation to the derivative of the sign function, a magnitude-aware gradient for weight updating, a better initialization method, and a two-step scheme for training a deep network.

Depth Estimation

Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition

no code implementations1 Nov 2018 Xiangbo Shu, Jinhui Tang, Guo-Jun Qi, Wei Liu, Jian Yang

In a Co-LSTM unit, each sub-memory unit stores individual motion information, while this Co-LSTM unit selectively integrates and stores inter-related motion information between multiple interacting persons from multiple sub-memory units via the cell gate and co-memory cell, respectively.

Action Recognition Human Interaction Recognition

Orthogonal Deep Features Decomposition for Age-Invariant Face Recognition

no code implementations ECCV 2018 Yitong Wang, Dihong Gong, Zheng Zhou, Xing Ji, Hao Wang, Zhifeng Li, Wei Liu, Tong Zhang

Extensive experiments conducted on the three public domain face aging datasets (MORPH Album 2, CACD-VS and FG-NET) have shown the effectiveness of the proposed approach and the value of the constructed CAF dataset on AIFR.

Age-Invariant Face Recognition

Distilled Wasserstein Learning for Word Embedding and Topic Modeling

no code implementations NeurIPS 2018 Hongteng Xu, Wenlin Wang, Wei Liu, Lawrence Carin

When learning the topic model, we leverage a distilled underlying distance matrix to update the topic distributions and smoothly calculate the corresponding optimal transports.

Mortality Prediction Word Embeddings

Temporally Coherent Video Harmonization Using Adversarial Networks

no code implementations5 Sep 2018 Hao-Zhi Huang, Senzhe Xu, Junxiong Cai, Wei Liu, Shi-Min Hu

Since existing video datasets which have ground-truth foreground masks and optical flows are not sufficiently large, we propose a simple yet efficient method to build up a synthetic dataset supporting supervised training of the proposed adversarial network.

Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization Fitting

1 code implementation ECCV 2018 Wei Liu, Shengcai Liao, Weidong Hu, Xuezhi Liang, Xiao Chen

However, current single-stage detectors (e. g. SSD) have not presented competitive accuracy on common pedestrian detection benchmarks.

Ranked #6 on Pedestrian Detection on Caltech (using extra training data)

Pedestrian Detection

Incremental Multi-graph Matching via Diversity and Randomness based Graph Clustering

no code implementations ECCV 2018 Tianshu Yu, Junchi Yan, Wei Liu, Baoxin Li

In this paper, we present an incremental multi-graph matching approach, which deals with the arriving graph utilizing the previous matching results under the global consistency constraint.

Graph Clustering Graph Matching

Contour Knowledge Transfer for Salient Object Detection

1 code implementation ECCV 2018 Xin Li, Fan Yang, Hong Cheng, Wei Liu, Dinggang Shen

Our goal is to overcome this limitation by automatically converting an existing deep c