Search Results for author: Peng Wang

Found 149 papers, 38 papers with code

A Nearly-Linear Time Algorithm for Exact Community Recovery in Stochastic Block Model

no code implementations ICML 2020 Peng Wang, Zirui Zhou, Anthony Man-Cho So

In this paper, we focus on the problem of exactly recovering the communities in a binary symmetric SBM, where a graph of $n$ vertices is partitioned into two equal-sized communities and the vertices are connected with probability $p = \alpha\log(n)/n$ within communities and $q = \beta\log(n)/n$ across communities for some $\alpha>\beta>0$.

Stochastic Block Model

Space-and-time-synchronized simultaneous vehicle tracking/formation using cascaded prescribed-time control

no code implementations11 Sep 2021 Peng Wang, Ziyin Chen, Xiaobing Zhang

In this paper, we present a space-and-time-synchronized control method with application to the simultaneous tracking/formation.

Continual Neural Mapping: Learning An Implicit Scene Representation from Sequential Observations

no code implementations12 Aug 2021 Zike Yan, Yuxin Tian, Xuesong Shi, Ping Guo, Peng Wang, Hongbin Zha

We introduce an experience replay approach to tackle an exemplary task of continual neural mapping: approximating a continuous signed distance function (SDF) from sequential depth images as a scene geometry representation.

Continual Learning

Simultaneous Semantic and Collision Learning for 6-DoF Grasp Pose Estimation

no code implementations5 Aug 2021 Yiming Li, Tao Kong, Ruihang Chu, Yifeng Li, Peng Wang, Lei LI

In a unified framework, we jointly predict the feasible 6-DoF grasp poses, instance semantic segmentation, and collision information.

Multi-Task Learning Pose Estimation +1

Neural Rays for Occlusion-aware Image-based Rendering

no code implementations28 Jul 2021 YuAn Liu, Sida Peng, Lingjie Liu, Qianqian Wang, Peng Wang, Christian Theobalt, Xiaowei Zhou, Wenping Wang

Experiments demonstrate that NeuRay can quickly generate high-quality novel view images of unseen scenes with little finetuning and can handle complex scenes with severe self-occlusions which previous methods struggle with.

Neural Rendering Novel View Synthesis +1

AdaXpert: Adapting Neural Architecture for Growing Data

1 code implementation1 Jul 2021 Shuaicheng Niu, Jiaxiang Wu, Guanghui Xu, Yifan Zhang, Yong Guo, Peilin Zhao, Peng Wang, Mingkui Tan

To address this, we present a neural architecture adaptation method, namely Adaptation eXpert (AdaXpert), to efficiently adjust previous architectures on the growing data.

Quantum Dynamics Interpretation of Black-box Optimization

no code implementations26 Jun 2021 Peng Wang, Gang Xin, Yuwei Jiao

To achieve this goal, the Schroedinger equation is employed to establish the relationship between the optimization problem and the quantum system, which makes it possible to study the dynamic search behaviors in the evolution process with quantum theory.

NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction

2 code implementations20 Jun 2021 Peng Wang, Lingjie Liu, YuAn Liu, Christian Theobalt, Taku Komura, Wenping Wang

In NeuS, we propose to represent a surface as the zero-level set of a signed distance function (SDF) and develop a new volume rendering method to train a neural SDF representation.

Novel View Synthesis

HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers

1 code implementation CVPR 2021 Mingyu Ding, Xiaochen Lian, Linjie Yang, Peng Wang, Xiaojie Jin, Zhiwu Lu, Ping Luo

Last, we proposed an efficient fine-grained search strategy to train HR-NAS, which effectively explores the search space, and finds optimal architectures given various tasks and computation resources.

Image Classification Neural Architecture Search +2

Fastening the Initial Access in 5G NR Sidelink for 6G V2X Networks

no code implementations10 Jun 2021 Marouan Mizmizi, Francesco Linsalata, Mattia Brambilla, Filippo Morandi, Kai Dong, Maurizio Magarini, Monica Nicoli, Majid Nasiri Khormuji, Peng Wang, Renaud Alexandre Pitaval, Umberto Spagnolini

The ever-increasing demand for intelligent, automated, and connected mobility solutions pushes for the development of an innovative sixth Generation (6G) of cellular networks.


Generative Adversarial Networks: A Survey Towards Private and Secure Applications

no code implementations7 Jun 2021 Zhipeng Cai, Zuobin Xiong, Honghui Xu, Peng Wang, Wei Li, Yi Pan

Generative Adversarial Networks (GAN) have promoted a variety of applications in computer vision, natural language processing, etc.

Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation

no code implementations31 May 2021 Peng Wang, Junyang Lin, An Yang, Chang Zhou, Yichang Zhang, Jingren Zhou, Hongxia Yang

Experimental results demonstrate that our method outperforms the previous state-of-the-art methods in both automatic and human evaluation, especially on coverage and faithfulness.

Table-to-Text Generation

Proposal-free One-stage Referring Expression via Grid-Word Cross-Attention

no code implementations5 May 2021 Wei Suo, Mengyang Sun, Peng Wang, Qi Wu

Referring Expression Comprehension (REC) has become one of the most important tasks in visual reasoning, since it is an essential step for many vision-and-language tasks such as visual question answering.

Question Answering Referring Expression Comprehension +2

Center Prediction Loss for Re-identification

no code implementations30 Apr 2021 Lu Yang, Yunlong Wang, Lingqiao Liu, Peng Wang, Lu Chi, Zehuan Yuan, Changhu Wang, Yanning Zhang

In this paper, we propose a new loss based on center predictivity, that is, a sample must be positioned in a location of the feature space such that from it we can roughly predict the location of the center of same-class samples.

CAT: Cross-Attention Transformer for One-Shot Object Detection

no code implementations30 Apr 2021 Weidong Lin, Yuyan Deng, Yang Gao, Ning Wang, Jinghao Zhou, Lingqiao Liu, Lei Zhang, Peng Wang

Given a query patch from a novel class, one-shot object detection aims to detect all instances of that class in a target image through the semantic similarity comparison.

One-Shot Object Detection Semantic Similarity +1

Chop Chop BERT: Visual Question Answering by Chopping VisualBERT's Heads

no code implementations30 Apr 2021 Chenyu Gao, Qi Zhu, Peng Wang, Qi Wu

Based on this observation, we design a dynamic chopping module that can automatically remove heads and layers of the VisualBERT at an instance level when dealing with different questions.

Question Answering Visual Question Answering +1

PURE: Passive mUlti-peRson idEntification via Deep Footstep Separation and Recognition

no code implementations15 Apr 2021 Chao Cai, Ruinan Jin, Peng Wang, Liyuan Ye, Hongbo Jiang, Jun Luo

Recently, \textit{passive behavioral biometrics} (e. g., gesture or footstep) have become promising complements to conventional user identification methods (e. g., face or fingerprint) under special situations, yet existing sensing technologies require lengthy measurement traces and cannot identify multiple users at the same time.

Person Identification

Residual Gaussian Process: A Tractable Nonparametric Bayesian Emulator for Multi-fidelity Simulations

no code implementations8 Apr 2021 Wei W. Xing, Akeel A. Shah, Peng Wang, Shandian Zhe Qian Fu, Robert. M. Kirby

The resulting model is equipped with a closed-form solution for the predictive posterior, making it applicable to advanced, high-dimensional tasks that require uncertainty estimation.

Active Learning

An Adversarial Human Pose Estimation Network Injected with Graph Structure

no code implementations29 Mar 2021 Lei Tian, Guoqiang Liang, Peng Wang, Chunhua Shen

Because of the invisible human keypoints in images caused by illumination, occlusion and overlap, it is likely to produce unreasonable human pose prediction for most of the current human pose estimation methods.

Pose Estimation Pose Prediction

Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification

no code implementations CVPR 2021 Peng Wang, Kai Han, Xiu-Shen Wei, Lei Zhang, Lei Wang

Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases.

Classification Contrastive Learning +4

Hetero-Modal Learning and Expansive Consistency Constraints for Semi-Supervised Detection from Multi-Sequence Data

no code implementations24 Mar 2021 Bolin Lai, YuHsuan Wu, Xiao-Yun Zhou, Peng Wang, Le Lu, Lingyun Huang, Mei Han, Jing Xiao, Heping Hu, Adam P. Harrison

Lesion detection serves a critical role in early diagnosis and has been well explored in recent years due to methodological advancesand increased data availability.

Instance and Pair-Aware Dynamic Networks for Re-Identification

no code implementations9 Mar 2021 Bingliang Jiao, Xin Tan, Jinghao Zhou, Lu Yang, Yunlong Wang, Peng Wang

The proposed model is composed of three main branches where a self-guided dynamic branch is constructed to strengthen instance-specific features, focusing on every single image.

Pluggable Weakly-Supervised Cross-View Learning for Accurate Vehicle Re-Identification

no code implementations9 Mar 2021 Lu Yang, Hongbang Liu, Jinghao Zhou, Lingqiao Liu, Lei Zhang, Peng Wang, Yanning Zhang

Learning cross-view consistent feature representation is the key for accurate vehicle Re-identification (ReID), since the visual appearance of vehicles changes significantly under different viewpoints.

Vehicle Re-Identification

Scalable Learning With a Structural Recurrent Neural Network for Short-Term Traffic Prediction

1 code implementation3 Mar 2021 Youngjoo Kim, Peng Wang, Lyudmila Mihaylova

With the real traffic speed data measured in the city of Santander, we demonstrate the proposed SRNN outperforms the image-based approaches using the capsule network (CapsNet) by 14. 1% and the convolutional neural network (CNN) by 5. 87%, respectively, in terms of root mean squared error (RMSE).

Semantic Similarity Semantic Textual Similarity +2

M6: A Chinese Multimodal Pretrainer

no code implementations1 Mar 2021 Junyang Lin, Rui Men, An Yang, Chang Zhou, Ming Ding, Yichang Zhang, Peng Wang, Ang Wang, Le Jiang, Xianyan Jia, Jie Zhang, Jianwei Zhang, Xu Zou, Zhikang Li, Xiaodong Deng, Jie Liu, Jinbao Xue, Huiling Zhou, Jianxin Ma, Jin Yu, Yong Li, Wei Lin, Jingren Zhou, Jie Tang, Hongxia Yang

In this work, we construct the largest dataset for multimodal pretraining in Chinese, which consists of over 1. 9TB images and 292GB texts that cover a wide range of domains.

Image Generation

Derive Lovelock Gravity from String Theory in Cosmological Background

no code implementations24 Dec 2020 Peng Wang, Houwen Wu, Haitang Yang, Shuxuan Ying

It was proved more than three decades ago, that the first order $\alpha'$ correction of string effective theory could be written as the Gauss-Bonnet term, which is the quadratic term of Lovelock gravity.

High Energy Physics - Theory General Relativity and Quantum Cosmology High Energy Physics - Phenomenology

Fine-Grained Vehicle Perception via 3D Part-Guided Visual Data Augmentation

1 code implementation15 Dec 2020 Feixiang Lu, Zongdai Liu, Hui Miao, Peng Wang, Liangjun Zhang, Ruigang Yang, Dinesh Manocha, Bin Zhou

For autonomous driving, the dynamics and states of vehicle parts such as doors, the trunk, and the bonnet can provide meaningful semantic information and interaction states, which are essential to ensuring the safety of the self-driving vehicle.

Autonomous Driving Data Augmentation +3

Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps

1 code implementation9 Dec 2020 Qi Zhu, Chenyu Gao, Peng Wang, Qi Wu

Texts appearing in daily scenes that can be recognized by OCR (Optical Character Recognition) tools contain significant information, such as street name, product brand and prices.

Image Captioning Optical Character Recognition +2

Hyperspectral Classification Based on Lightweight 3-D-CNN With Transfer Learning

no code implementations7 Dec 2020 Haokui Zhang, Ying Li, Yenan Jiang, Peng Wang, Qiang Shen, Chunhua Shen

In contrast to previous approaches, we do not impose restrictions over the source data sets, in which they do not have to be collected by the same sensors as the target data sets.

Classification General Classification +1

Quantum Dynamics of Optimization Problems

no code implementations6 Dec 2020 Peng Wang, Gang Xin, Yuwei Jiao

The mathematical relationship between the objective function and the wave function is established, and the quantum interpretation of the optimization problem is realized.

Ferryman as SemEval-2020 Task 5: Optimized BERT for Detecting Counterfactuals

no code implementations SEMEVAL 2020 Weilong Chen, Yan Zhuang, Peng Wang, Feng Hong, Yan Wang, Yanru Zhang

The main purpose of this article is to state the effect of using different methods and models for counterfactual determination and detection of causal knowledge.

Counterfactual Detection

AprilE: Attention with Pseudo Residual Connection for Knowledge Graph Embedding

no code implementations COLING 2020 Yuzhang Liu, Peng Wang, Yingtai Li, Yizhan Shao, Zhongkai Xu

To address this issue, we propose a novel model, AprilE, which employs triple-level self-attention and pseudo residual connection to model relational patterns.

Knowledge Graph Embedding

WikiAsp: A Dataset for Multi-domain Aspect-based Summarization

1 code implementation16 Nov 2020 Hiroaki Hayashi, Prashant Budania, Peng Wang, Chris Ackerson, Raj Neervannan, Graham Neubig

In this paper, we propose WikiAsp, a large-scale dataset for multi-domain aspect-based summarization that attempts to spur research in the direction of open-domain aspect-based summarization.

Few-shot Action Recognition with Implicit Temporal Alignment and Pair Similarity Optimization

no code implementations13 Oct 2020 Congqi Cao, Yajuan Li, Qinyi Lv, Peng Wang, Yanning Zhang

Few-shot learning aims to recognize instances from novel classes with few labeled samples, which has great value in research and application.

Action Recognition Few-Shot Learning +1

Disentangled Neural Architecture Search

no code implementations24 Sep 2020 Xinyue Zheng, Peng Wang, Qigang Wang, Zhongchao shi

However, existing methods rely heavily on a black-box controller to search architectures, which suffers from the serious problem of lacking interpretability.

Neural Architecture Search

Speech2Video Synthesis with 3D Skeleton Regularization and Expressive Body Poses

1 code implementation17 Jul 2020 Miao Liao, Sibo Zhang, Peng Wang, Hao Zhu, Xinxin Zuo, Ruigang Yang

In this paper, we propose a novel approach to convert given speech audio to a photo-realistic speaking video of a specific person, where the output video has synchronized, realistic, and expressive rich body dynamics.

Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks

no code implementations ECCV 2020 Yan Liu, Lingqiao Liu, Peng Wang, Pingping Zhang, Yinjie Lei

Most existing crowd counting systems rely on the availability of the object location annotation which can be expensive to obtain.

Crowd Counting

ODE-CNN: Omnidirectional Depth Extension Networks

no code implementations3 Jul 2020 Xinjing Cheng, Peng Wang, Yanqi Zhou, Chenye Guan, Ruigang Yang

Omnidirectional 360{\deg} camera proliferates rapidly for autonomous robots since it significantly enhances the perception ability by widening the field of view(FoV).

Non-Convex Exact Community Recovery in Stochastic Block Model

no code implementations29 Jun 2020 Peng Wang, Zirui Zhou, Anthony Man-Cho So

In this paper, we focus on the problem of exactly recovering the communities in a binary symmetric SBM, where a graph of $n$ vertices is partitioned into two equal-sized communities and the vertices are connected with probability $p = \alpha\log(n)/n$ within communities and $q = \beta\log(n)/n$ across communities for some $\alpha>\beta>0$.

Stochastic Block Model

A Robust Attentional Framework for License Plate Recognition in the Wild

no code implementations6 Jun 2020 Linjiang Zhang, Peng Wang, Hui Li, Zhen Li, Chunhua Shen, Yanning Zhang

On the other hand, the 2D attentional based license plate recognizer with an Xception-based CNN encoder is capable of recognizing license plates with different patterns under various scenarios accurately and robustly.

Image Generation License Plate Recognition

Structured Multimodal Attentions for TextVQA

no code implementations1 Jun 2020 Chenyu Gao, Qi Zhu, Peng Wang, Hui Li, Yuliang Liu, Anton Van Den Hengel, Qi Wu

Most of the state-of-the-art (SoTA) VQA methods fail to answer these questions because of i) poor text reading ability; ii) lacking of text-visual reasoning capacity; and iii) adopting a discriminative answering mechanism instead of a generative one which is hard to cover both OCR tokens and general text tokens in the final answer.

Graph Attention Optical Character Recognition +3

Vid2Curve: Simultaneous Camera Motion Estimation and Thin Structure Reconstruction from an RGB Video

no code implementations7 May 2020 Peng Wang, Lingjie Liu, Nenglun Chen, Hung-Kuo Chu, Christian Theobalt, Wenping Wang

We propose the first approach that simultaneously estimates camera motion and reconstructs the geometry of complex 3D thin structures in high quality from a color video captured by a handheld camera.

Motion Estimation Occlusion Handling +1

Challenge Closed-book Science Exam: A Meta-learning Based Question Answering System

no code implementations26 Apr 2020 Xinyue Zheng, Peng Wang, Qigang Wang, Zhongchao shi

Prior work in standardized science exams requires support from large text corpus, such as targeted science corpus fromWikipedia or SimpleWikipedia.

Language Modelling Meta-Learning +1

Anisotropic Convolutional Networks for 3D Semantic Scene Completion

1 code implementation CVPR 2020 Jie Li, Kai Han, Peng Wang, Yu Liu, Xia Yuan

In contrast to the standard 3D convolution that is limited to a fixed 3D receptive field, our module is capable of modeling the dimensional anisotropy voxel-wisely.

TEDL: A Text Encryption Method Based on Deep Learning

1 code implementation9 Mar 2020 Xiang Li, Peng Wang

Firstly, both communication parties establish a word vector table by training a deep learning model according to specified hyperparameters.

Toward Interpretability of Dual-Encoder Models for Dialogue Response Suggestions

no code implementations2 Mar 2020 Yitong Li, Dianqi Li, Sushant Prakash, Peng Wang

To improve the interpretability in the dual encoder models, we design a novel regularization loss to minimize the mutual information between unimportant words and desired labels, in addition to the original attention method, so that important words are emphasized while unimportant words are de-emphasized.

Word Embeddings

Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs

1 code implementation CVPR 2020 Shizhe Chen, Qin Jin, Peng Wang, Qi Wu

From the ASG, we propose a novel ASG2Caption model, which is able to recognise user intentions and semantics in the graph, and therefore generate desired captions according to the graph structure.

Image Captioning

Unsupervised Image-generation Enhanced Adaptation for Object Detection in Thermal images

no code implementations17 Feb 2020 Wanyi Li, Fuyu Li, Yongkang Luo, Peng Wang

To reduce the gap between visible domain and thermal domain, the proposed method manages to generate simulated fake thermal images that are similar to the target images, and preserves the annotation information of the visible source domain.

Image-to-Image Translation Object Detection

Using Sampled Network Data With The Autologistic Actor Attribute Model

2 code implementations30 Jan 2020 Alex D. Stivala, H. Colin Gallagher, David A. Rolls, Peng Wang, Garry L. Robins

Social science research increasingly benefits from statistical methods for understanding the structured nature of social life, including for social network data.

Social and Information Networks Methodology

Real-time Segmentation and Facial Skin Tones Grading

1 code implementation30 Dec 2019 Ling Luo, Dingyu Xue, Xinglong Feng, Yichun Yu, Peng Wang

Modern approaches for semantic segmention usually pay too much attention to the accuracy of the model, and therefore it is strongly recommended to introduce cumbersome backbones, which brings heavy computation burden and memory footprint.

To Balance or Not to Balance: A Simple-yet-Effective Approach for Learning with Long-Tailed Distributions

no code implementations10 Dec 2019 Jun-Jie Zhang, Lingqiao Liu, Peng Wang, Chunhua Shen

Such imbalanced distribution causes a great challenge for learning a deep neural network, which can be boiled down into a dilemma: on the one hand, we prefer to increase the exposure of tail class samples to avoid the excessive dominance of head classes in the classifier training.

Auxiliary Learning Self-Supervised Learning

AutoRemover: Automatic Object Removal for Autonomous Driving Videos

1 code implementation28 Nov 2019 Rong Zhang, Wei Li, Peng Wang, Chenye Guan, Jin Fang, Yuhang Song, Jinhui Yu, Baoquan Chen, Weiwei Xu, Ruigang Yang

To deal with shadows, we build up an autonomous driving shadow dataset and design a deep neural network to detect shadows automatically.

Autonomous Driving Video Inpainting

CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion

no code implementations13 Nov 2019 Xinjing Cheng, Peng Wang, Chenye Guan, Ruigang Yang

In this paper, we propose CSPN++, which further improves its effectiveness and efficiency by learning adaptive convolutional kernel sizes and the number of iterations for the propagation, thus the context and computational resources needed at each pixel could be dynamically assigned upon requests.

Depth Completion Stereo-LiDAR Fusion

Attend to the Difference: Cross-Modality Person Re-identification via Contrastive Correlation

no code implementations25 Oct 2019 Shizhou Zhang, Yifei Yang, Peng Wang, Xiuwei Zhang, Yanning Zhang

The problem of cross-modality person re-identification has been receiving increasing attention recently, due to its practical significance.

Person Re-Identification

Efficient Automatic Meta Optimization Search for Few-Shot Learning

no code implementations6 Sep 2019 Xinyue Zheng, Peng Wang, Qigang Wang, Zhongchao shi, Feiyu Xu

NAS automatically generates and evaluates meta-learner's architecture for few-shot learning problems, while the meta-learner uses meta-learning algorithm to optimize its parameters based on the distribution of learning tasks.

Few-Shot Learning Neural Architecture Search

Discriminative and Robust Online Learning for Siamese Visual Tracking

1 code implementation6 Sep 2019 Jinghao Zhou, Peng Wang, Haoyang Sun

The problem of visual object tracking has traditionally been handled by variant tracking paradigms, either learning a model of the object's appearance exclusively online or matching the object with the target in an offline-trained embedding space.

Visual Object Tracking Visual Tracking

Person Re-identification in Aerial Imagery

1 code implementation14 Aug 2019 Shizhou Zhang, Qi Zhang, Yifei Yang, Xing Wei, Peng Wang, Bingliang Jiao, Yanning Zhang

Our method can learn a discriminative and compact feature representation for ReID in aerial imagery and can be trained in an end-to-end fashion efficiently.

Object Detection Person Re-Identification

V-PROM: A Benchmark for Visual Reasoning Using Visual Progressive Matrices

no code implementations29 Jul 2019 Damien Teney, Peng Wang, Jiewei Cao, Lingqiao Liu, Chunhua Shen, Anton Van Den Hengel

One of the primary challenges faced by deep learning is the degree to which current methods exploit superficial statistics and dataset bias, rather than learning to generalise over the specific representations they have experienced.

Visual Reasoning

EPNAS: Efficient Progressive Neural Architecture Search

no code implementations7 Jul 2019 Yanqi Zhou, Peng Wang, Sercan Arik, Haonan Yu, Syed Zawad, Feng Yan, Greg Diamos

In this paper, we propose Efficient Progressive Neural Architecture Search (EPNAS), a neural architecture search (NAS) that efficiently handles large search space through a novel progressive search policy with performance prediction based on REINFORCE~\cite{Williams. 1992. PG}.

Neural Architecture Search

A Performance Evaluation of Correspondence Grouping Methods for 3D Rigid Data Matching

no code implementations5 Jul 2019 Jiaqi Yang, Ke Xian, Peng Wang, Yanning Zhang

Seeking consistent point-to-point correspondences between 3D rigid data (point clouds, meshes, or depth maps) is a fundamental problem in 3D computer vision.

3D Object Recognition Point Cloud Registration

Evaluating Local Geometric Feature Representations for 3D Rigid Data Matching

no code implementations29 Jun 2019 Jiaqi Yang, Siwen Quan, Peng Wang, Yanning Zhang

The outcomes present interesting findings that may shed new light on this community and provide complementary perspectives to existing evaluations on the topic of local geometric feature description.

Object Recognition Point Cloud Registration

Towards End-to-End Text Spotting in Natural Scenes

no code implementations14 Jun 2019 Peng Wang, Hui Li, Chunhua Shen

Text spotting in natural scene images is of great importance for many image understanding tasks.

Image Cropping Text Spotting

Vehicle Re-identification in Aerial Imagery: Dataset and Approach

no code implementations ICCV 2019 Peng Wang, Bingliang Jiao, Lu Yang, Yifei Yang, Shizhou Zhang, Wei Wei, Yanning Zhang

It is capable of explicitly detecting discriminative parts for each specific vehicle and significantly outperforms the evaluated baselines and state-of-the-art vehicle ReID approaches.

Vehicle Re-Identification

Pixel-aware Deep Function-mixture Network for Spectral Super-Resolution

no code implementations24 Mar 2019 Lei Zhang, Zhiqiang Lang, Peng Wang, Wei Wei, Shengcai Liao, Ling Shao, Yanning Zhang

To address this problem, we propose a pixel-aware deep function-mixture network for SSR, which is composed of a new class of modules, termed function-mixture (FM) blocks.


Structural Recurrent Neural Network for Traffic Speed Prediction

1 code implementation18 Feb 2019 Youngjoo Kim, Peng Wang, Lyudmila Mihaylova

We use a graph of a vehicular road network with recurrent neural networks (RNNs) to infer the interaction between adjacent road segments as well as the temporal dynamics.

Time Series Traffic Prediction

Flash: Efficient Dynamic Routing for Offchain Networks

2 code implementations14 Feb 2019 Peng Wang, Hong Xu, Xin Jin, Tao Wang

Mice payments are directly sent by looking up a routing table with a few precomputed paths to reduce probing overhead.

Networking and Internet Architecture

RPC: A Large-Scale Retail Product Checkout Dataset

no code implementations22 Jan 2019 Xiu-Shen Wei, Quan Cui, Lei Yang, Peng Wang, Lingqiao Liu

The main challenge of this problem comes from the large scale and the fine-grained nature of the product categories as well as the difficulty for collecting training images that reflect the realistic checkout scenarios due to continuous update of the products.

Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks

no code implementations CVPR 2019 Peng Wang, Qi Wu, Jiewei Cao, Chunhua Shen, Lianli Gao, Anton Van Den Hengel

Being composed of node attention component and edge attention component, the proposed graph attention mechanism explicitly represents inter-object relationships, and properties with a flexibility and power impossible with competing approaches.

Graph Attention Referring Expression Comprehension

ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving

no code implementations CVPR 2019 Xibin Song, Peng Wang, Dingfu Zhou, Rui Zhu, Chenye Guan, Yuchao Dai, Hao Su, Hongdong Li, Ruigang Yang

Specifically, we first segment each car with a pre-trained Mask R-CNN, and then regress towards its 3D pose and shape based on a deformable 3D car model with or without using semantic keypoints.

3D Car Instance Understanding Autonomous Driving

Visual Question Answering as Reading Comprehension

no code implementations CVPR 2019 Hui Li, Peng Wang, Chunhua Shen, Anton Van Den Hengel

In contrast to struggling on multimodal feature fusion, in this paper, we propose to unify all the input information by natural language so as to convert VQA into a machine reading comprehension problem.

Common Sense Reasoning Machine Reading Comprehension +1

RGB-D Based Action Recognition with Light-weight 3D Convolutional Networks

no code implementations24 Nov 2018 Haokui Zhang, Ying Li, Peng Wang, Yu Liu, Chunhua Shen

Different from RGB videos, depth data in RGB-D videos provide key complementary information for tristimulus visual data which potentially could achieve accuracy improvement for action recognition.

Action Recognition

Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition

5 code implementations2 Nov 2018 Hui Li, Peng Wang, Chunhua Shen, Guyu Zhang

Recognizing irregular text in natural scene images is challenging due to the large variance in text appearance, such as curvature, orientation and distortion.

Irregular Text Recognition Scene Text +1

Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding

1 code implementation14 Oct 2018 Chenxu Luo, Zhenheng Yang, Peng Wang, Yang Wang, Wei Xu, Ram Nevatia, Alan Yuille

Performance on the five tasks of depth estimation, optical flow estimation, odometry, moving object segmentation and scene flow estimation shows that our approach outperforms other SoTA methods.

Depth Estimation Optical Flow Estimation +2

Joint Unsupervised Learning of Optical Flow and Depth by Watching Stereo Videos

1 code implementation8 Oct 2018 Yang Wang, Zhenheng Yang, Peng Wang, Yi Yang, Chenxu Luo, Wei Xu

Then the whole scene is decomposed into moving foreground and static background by compar- ing the estimated optical flow and rigid flow derived from the depth and ego-motion.

Motion Estimation Optical Flow Estimation

Learning Depth with Convolutional Spatial Propagation Network

1 code implementation4 Oct 2018 Xinjing Cheng, Peng Wang, Ruigang Yang

In this paper, we propose a simple yet effective convolutional spatial propagation network (CSPN) to learn the affinity matrix for various depth estimation tasks.

Depth Completion Depth Estimation +2

Towards Effective Deep Embedding for Zero-Shot Learning

no code implementations30 Aug 2018 Lei Zhang, Peng Wang, Lingqiao Liu, Chunhua Shen, Wei Wei, Yannning Zhang, Anton Van Den Hengel

Towards this goal, we present a simple but effective two-branch network to simultaneously map semantic descriptions and visual samples into a joint space, on which visual embeddings are forced to regress to their class-level semantic embeddings and the embeddings crossing classes are required to be distinguishable by a trainable classifier.

Zero-Shot Learning

A Capsule Network for Traffic Speed Prediction in Complex Road Networks

1 code implementation23 Jul 2018 Youngjoo Kim, Peng Wang, Yifei Zhu, Lyudmila Mihaylova

Traffic flow data from induction loop sensors are essentially a time series, which is also spatially related to traffic in different road segments.

Time Series Time Series Forecasting

Every Pixel Counts: Unsupervised Geometry Learning with Holistic 3D Motion Understanding

no code implementations27 Jun 2018 Zhenheng Yang, Peng Wang, Yang Wang, Wei Xu, Ram Nevatia

The four types of information, i. e. 2D flow, camera pose, segment mask and depth maps, are integrated into a differentiable holistic 3D motion parser (HMP), where per-pixel 3D motion for rigid background and moving objects are recovered.

Depth And Camera Motion Optical Flow Estimation +2

Adaptive Importance Learning for Improving Lightweight Image Super-resolution Network

no code implementations5 Jun 2018 Lei Zhang, Peng Wang, Chunhua Shen, Lingqiao Liu, Wei Wei, Yanning Zhang, Anton Van Den Hengel

In this study, we revisit this problem from an orthog- onal view, and propose a novel learning strategy to maxi- mize the pixel-wise fitting capacity of a given lightweight network architecture.

Image Super-Resolution

DeLS-3D: Deep Localization and Segmentation with a 3D Semantic Map

1 code implementation CVPR 2018 Peng Wang, Ruigang Yang, Binbin Cao, Wei Xu, Yuanqing Lin

The uniqueness of our design is a sensor fusion scheme which integrates camera videos, motion sensors (GPS/IMU), and a 3D semantic map in order to achieve robustness and efficiency of the system.

Autonomous Driving Pose Estimation +2

Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examples

no code implementations11 May 2018 Xiu-Shen Wei, Peng Wang, Lingqiao Liu, Chunhua Shen, Jianxin Wu

To solve this problem, we propose an end-to-end trainable deep network which is inspired by the state-of-the-art fine-grained recognition model and is tailored for the FSFG task.

Few-Shot Learning Fine-Grained Image Recognition

SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting

no code implementations9 May 2018 Yuhang Song, Chao Yang, Yeji Shen, Peng Wang, Qin Huang, C. -C. Jay Kuo

In this paper, we focus on image inpainting task, aiming at recovering the missing area of an incomplete image given the context information.

Image Inpainting Interactive Segmentation +1

Training a Binary Weight Object Detector by Knowledge Transfer for Autonomous Driving

no code implementations17 Apr 2018 Jiaolong Xu, Peng Wang, Heng Yang, Antonio M. López

Autonomous driving has harsh requirements of small model size and energy efficiency, in order to enable the embedded system to achieve real-time on-board object detection.

Autonomous Driving Object Detection +1

The ApolloScape Open Dataset for Autonomous Driving and its Application

2 code implementations16 Mar 2018 Xinyu Huang, Peng Wang, Xinjing Cheng, Dingfu Zhou, Qichuan Geng, Ruigang Yang

In this paper, we provide a sensor fusion scheme integrating camera videos, consumer-grade motion sensors (GPS/IMU), and a 3D semantic map in order to achieve robust self-localization and semantic segmentation for autonomous driving.

Autonomous Driving Instance Segmentation +3

LEGO: Learning Edge with Geometry all at Once by Watching Videos

1 code implementation CVPR 2018 Zhenheng Yang, Peng Wang, Yang Wang, Wei Xu, Ram Nevatia

In our framework, the predicted depths, normals and edges are forced to be consistent all the time.

Occlusion Aware Unsupervised Learning of Optical Flow

no code implementations CVPR 2018 Yang Wang, Yi Yang, Zhenheng Yang, Liang Zhao, Peng Wang, Wei Xu

Especially on KITTI dataset where abundant unlabeled samples exist, our unsupervised method outperforms its counterpart trained with supervised learning.

Optical Flow Estimation

Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency

no code implementations10 Nov 2017 Zhenheng Yang, Peng Wang, Wei Xu, Liang Zhao, Ramakant Nevatia

Learning to reconstruct depths in a single image by watching unlabeled videos via deep convolutional network (DCN) is attracting significant attention in recent years.

Depth Estimation

Fine-grained Pattern Matching Over Streaming Time Series

no code implementations27 Oct 2017 Rong Kang, Chen Wang, Peng Wang, Yuting Ding, Jian-Min Wang

Hence, we formulate a new problem, called "fine-grained pattern matching", which allows users to specify varied granularities of matching deviation to different segments of a given pattern, and fuzzy regions for adaptive breakpoints determination between consecutive segments.

Time Series

Towards End-to-End Car License Plates Detection and Recognition with Deep Neural Networks

no code implementations26 Sep 2017 Hui Li, Peng Wang, Chunhua Shen

In contrast to existing approaches which take license plate detection and recognition as two separate tasks and settle them step by step, our method jointly solves these two tasks by a single network.

License Plate Detection

Joint Multi-Person Pose Estimation and Semantic Part Segmentation

no code implementations CVPR 2017 Fangting Xia, Peng Wang, Xianjie Chen, Alan Yuille

To refine part segments, the refined pose and the original part potential are integrated through a Part FCN, where the skeleton feature from pose serves as additional regularization cues for part segments.

Human Detection Multi-Person Pose Estimation

Visual Question Answering with Memory-Augmented Networks

no code implementations CVPR 2018 Chao Ma, Chunhua Shen, Anthony Dick, Qi Wu, Peng Wang, Anton Van Den Hengel, Ian Reid

In this paper, we exploit a memory-augmented neural network to predict accurate answers to visual questions, even when those answers occur rarely in the training set.

Question Answering Visual Question Answering

Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks

no code implementations ICCV 2017 Hui Li, Peng Wang, Chunhua Shen

In this work, we jointly address the problem of text detection and recognition in natural scene images based on convolutional recurrent neural networks.

Image Cropping Text Spotting

Multi-Attention Network for One Shot Learning

no code implementations CVPR 2017 Peng Wang, Lingqiao Liu, Chunhua Shen, Zi Huang, Anton Van Den Hengel, Heng Tao Shen

One-shot learning is a challenging problem where the aim is to recognize a class identified by a single training image.

One-Shot Learning Word Embeddings

Semantic Instance Segmentation via Deep Metric Learning

1 code implementation30 Mar 2017 Alireza Fathi, Zbigniew Wojna, Vivek Rathod, Peng Wang, Hyun Oh Song, Sergio Guadarrama, Kevin P. Murphy

We propose a new method for semantic instance segmentation, by first computing how likely two pixels are to belong to the same object, and then by grouping similar pixels together.

Instance Segmentation Metric Learning +2

Verified Low-Level Programming Embedded in F*

3 code implementations28 Feb 2017 Jonathan Protzenko, Jean-Karim Zinzindohoué, Aseem Rastogi, Tahina Ramananandro, Peng Wang, Santiago Zanella-Béguelin, Antoine Delignat-Lavaud, Catalin Hritcu, Karthikeyan Bhargavan, Cédric Fournet, Nikhil Swamy

Low* is a shallow embedding of a small, sequential, well-behaved subset of C in F*, a dependently-typed variant of ML aimed at program verification.

Programming Languages Cryptography and Security

A Fast and Compact Saliency Score Regression Network Based on Fully Convolutional Network

no code implementations2 Feb 2017 Xuanyang Xi, Yongkang Luo, Fengfu Li, Peng Wang, Hong Qiao

In this paper, we tackle this problem by proposing a fast and compact saliency score regression network which employs fully convolutional network, a special deep convolutional neural network, to estimate the saliency of objects in images.

Saliency Detection

Deep Learning and Its Applications to Machine Health Monitoring: A Survey

1 code implementation16 Dec 2016 Rui Zhao, Ruqiang Yan, Zhenghua Chen, Kezhi Mao, Peng Wang, Robert X. Gao

Since 2006, deep learning (DL) has become a rapidly growing research direction, redefining state-of-the-art performances in a wide range of areas such as object recognition, image segmentation, speech recognition and machine translation.

Machine Translation Object Recognition +2

The VQA-Machine: Learning How to Use Existing Vision Algorithms to Answer New Questions

no code implementations CVPR 2017 Peng Wang, Qi Wu, Chunhua Shen, Anton Van Den Hengel

To train a method to perform even one of these operations accurately from {image, question, answer} tuples would be challenging, but to aim to achieve them all with a limited set of such training data seems ambitious at best.

Question Answering Visual Question Answering

SURGE: Surface Regularized Geometry Estimation from a Single Image

no code implementations NeurIPS 2016 Peng Wang, Xiaohui Shen, Bryan Russell, Scott Cohen, Brian Price, Alan L. Yuille

This paper introduces an approach to regularize 2. 5D surface normal and depth predictions at each pixel given a single input image.

Exploiting Temporal Information for DCNN-based Fine-Grained Object Classification

no code implementations1 Aug 2016 ZongYuan Ge, Chris McCool, Conrad Sanderson, Peng Wang, Lingqiao Liu, Ian Reid, Peter Corke

Fine-grained classification is a relatively new field that has concentrated on using information from a single image, while ignoring the enormous potential of using video data to improve classification.

Classification General Classification +1

Visual Question Answering: A Survey of Methods and Datasets

1 code implementation20 Jul 2016 Qi Wu, Damien Teney, Peng Wang, Chunhua Shen, Anthony Dick, Anton Van Den Hengel

Visual Question Answering (VQA) is a challenging task that has received increasing attention from both the computer vision and the natural language processing communities.

Visual Question Answering

Where to Focus: Query Adaptive Matching for Instance Retrieval Using Convolutional Feature Maps

no code implementations22 Jun 2016 Jiewei Cao, Lingqiao Liu, Peng Wang, Zi Huang, Chunhua Shen, Heng Tao Shen

Instance retrieval requires one to search for images that contain a particular object within a large corpus.

FVQA: Fact-based Visual Question Answering

no code implementations17 Jun 2016 Peng Wang, Qi Wu, Chunhua Shen, Anton Van Den Hengel, Anthony Dick

We evaluate several baseline models on the FVQA dataset, and describe a novel model which is capable of reasoning about an image on the basis of supporting facts.

Common Sense Reasoning Question Answering +1

What's Wrong With That Object? Identifying Images of Unusual Objects by Modelling the Detection Score Distribution

no code implementations CVPR 2016 Peng Wang, Lingqiao Liu, Chunhua Shen, Zi Huang, Anton Van Den Hengel, Heng Tao Shen

The key observation motivating our approach is that "regular object" images, "unusual object" images and "other objects" images exhibit different region-level scores in terms of both the score values and the spatial distributions.

Gaussian Processes Object Detection

Pushing the Limits of Deep CNNs for Pedestrian Detection

no code implementations15 Mar 2016 Qichang Hu, Peng Wang, Chunhua Shen, Anton Van Den Hengel, Fatih Porikli

In this work, we show that by re-using the convolutional feature maps (CFMs) of a deep convolutional neural network (DCNN) model as image features to train an ensemble of boosted decision models, we are able to achieve the best reported accuracy without using specially designed learning algorithms.

Occlusion Handling Optical Flow Estimation +1

Hi Detector, What's Wrong with that Object? Identifying Irregular Object From Images by Modelling the Detection Score Distribution

no code implementations14 Feb 2016 Peng Wang, Lingqiao Liu, Chunhua Shen, Anton Van Den Hengel, Heng Tao Shen

To address this problem, we propose a novel approach by inspecting the distribution of the detection scores at multiple image regions based on the detector trained from the "regular object" and "other objects".

Gaussian Processes

Order-aware Convolutional Pooling for Video Based Action Recognition

no code implementations31 Jan 2016 Peng Wang, Lingqiao Liu, Chunhua Shen, Heng Tao Shen

Most video based action recognition approaches create the video-level representation by temporally pooling the features extracted at each frame.

Action Recognition

Compositional Model based Fisher Vector Coding for Image Classification

no code implementations16 Jan 2016 Lingqiao Liu, Peng Wang, Chunhua Shen, Lei Wang, Anton Van Den Hengel, Chao Wang, Heng Tao Shen

To handle this limitation, in this paper we break the convention which assumes that a local feature is drawn from one of few Gaussian distributions.

Classification General Classification +1

Ask Me Anything: Free-form Visual Question Answering Based on Knowledge from External Sources

no code implementations CVPR 2016 Qi Wu, Peng Wang, Chunhua Shen, Anthony Dick, Anton Van Den Hengel

Priming a recurrent neural network with this combined information, and the submitted question, leads to a very flexible visual question answering approach.

Question Answering Visual Question Answering

Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net

no code implementations21 Nov 2015 Fangting Xia, Peng Wang, Liang-Chieh Chen, Alan L. Yuille

To tackle these difficulties, we propose a "Hierarchical Auto-Zoom Net" (HAZN) for object part parsing which adapts to the local scales of objects and parts.

DOC: Deep OCclusion Estimation From a Single Image

no code implementations20 Nov 2015 Peng Wang, Alan Yuille

In this paper we propose a deep network architecture, called DOC, which acts on a single image, detects object boundaries and estimates the border ownership (i. e. which side of the boundary is foreground and which is background).

Occlusion Estimation

Explicit Knowledge-based Reasoning for Visual Question Answering

no code implementations9 Nov 2015 Peng Wang, Qi Wu, Chunhua Shen, Anton Van Den Hengel, Anthony Dick

We describe a method for visual question answering which is capable of reasoning about contents of an image on the basis of information extracted from a large-scale knowledge base.

Question Answering Visual Question Answering

Pose-Guided Human Parsing with Deep Learned Features

no code implementations17 Aug 2015 Fangting Xia, Jun Zhu, Peng Wang, Alan Yuille

Parsing human body into semantic regions is crucial to human-centric analysis.

Human Parsing

Implementation of Training Convolutional Neural Networks

no code implementations3 Jun 2015 Tianyi Liu, Shuangsang Fang, Yuehui Zhao, Peng Wang, Jun Zhang

Deep learning refers to the shining branch of machine learning that is based on learning levels of representations.

Face Recognition

Towards Unified Depth and Semantic Prediction From a Single Image

no code implementations CVPR 2015 Peng Wang, Xiaohui Shen, Zhe Lin, Scott Cohen, Brian Price, Alan L. Yuille

By allowing for interactions between the depth and semantic information, the joint network provides more accurate depth prediction than a state-of-the-art CNN trained solely for depth prediction [5].

Depth Estimation Semantic Segmentation

Joint Object and Part Segmentation using Deep Learned Potentials

no code implementations ICCV 2015 Peng Wang, Xiaohui Shen, Zhe Lin, Scott Cohen, Brian Price, Alan Yuille

Segmenting semantic objects from images and parsing them into their respective semantic parts are fundamental steps towards detailed object understanding in computer vision.

Semantic Segmentation

Temporal Pyramid Pooling Based Convolutional Neural Networks for Action Recognition

no code implementations4 Mar 2015 Peng Wang, Yuanzhouhan Cao, Chunhua Shen, Lingqiao Liu, Heng Tao Shen

One challenge is that video contains a varying number of frames which is incompatible to the standard input format of CNNs.

Action Recognition Image Classification

Large-scale Binary Quadratic Optimization Using Semidefinite Relaxation and Applications

no code implementations27 Nov 2014 Peng Wang, Chunhua Shen, Anton Van Den Hengel, Philip H. S. Torr

Two standard relaxation methods are widely used for solving general BQPs--spectral methods and semidefinite programming (SDP), each with their own advantages and disadvantages.

Scene Parsing Semantic Segmentation

Link Prediction in Social Networks: the State-of-the-Art

1 code implementation19 Nov 2014 Peng Wang, Baowen Xu, Yurong Wu, Xiaoyu Zhou

Finally, some future challenges of the link prediction in social networks are discussed.

Social and Information Networks Physics and Society

Efficient Semidefinite Branch-and-Cut for MAP-MRF Inference

no code implementations20 Apr 2014 Peng Wang, Chunhua Shen, Anton Van Den Hengel, Philip Torr

We propose a Branch-and-Cut (B&C) method for solving general MAP-MRF inference problems.

A Fast Semidefinite Approach to Solving Binary Quadratic Problems

1 code implementation CVPR 2013 Peng Wang, Chunhua Shen, Anton Van Den Hengel

Second, compared with conventional SDP methods, the new SDP formulation leads to a significantly more efficient and scalable dual optimization approach, which has the same degree of complexity as spectral methods.

Semantic Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.