Search Results for author: Wei Yang

Found 106 papers, 32 papers with code

Learning to Reverse DNNs from AI Programs Automatically

no code implementations20 May 2022 Simin Chen, Hamed Khanpour, Cong Liu, Wei Yang

With the privatization deployment of DNNs on edge devices, the security of on-device DNNs has raised significant concern.

Transformer Tracking with Cyclic Shifting Window Attention

1 code implementation8 May 2022 Zikai Song, Junqing Yu, Yi-Ping Phoebe Chen, Wei Yang

Transformer architecture has been showing its great strength in visual object tracking, for its effective attention mechanism.

Visual Object Tracking

Detecting Topology Attacks against Graph Neural Networks

no code implementations21 Apr 2022 Senrong Xu, Yuan YAO, Liangyue Li, Wei Yang, Feng Xu, Hanghang Tong

In this work, we study the victim node detection problem under topology attacks against GNNs.

Node Classification

CorrGAN: Input Transformation Technique Against Natural Corruptions

no code implementations19 Apr 2022 Mirazul Haque, Christof J. Budnik, Wei Yang

These DNNs are vulnerable to adversarial perturbations and corruptions.

Pan-cancer computational histopathology reveals tumor mutational burden status through weakly-supervised deep learning

no code implementations7 Apr 2022 Siteng Chen, Jinxi Xiang, Xiyue Wang, Jun Zhang, Sen yang, Junzhou Huang, Wei Yang, Junhua Zheng, Xiao Han

In comparison with the state-of-the-art TMB prediction model from previous publications, our multiscale model achieved better performance over previously reported models.

whole slide images

Model Predictive Control for Fluid Human-to-Robot Handovers

no code implementations31 Mar 2022 Wei Yang, Balakumar Sundaralingam, Chris Paxton, Iretiayo Akinola, Yu-Wei Chao, Maya Cakmak, Dieter Fox

However, how to responsively generate smooth motions to take an object from a human is still an open question.

NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models

1 code implementation29 Mar 2022 Simin Chen, Zihe Song, Mirazul Haque, Cong Liu, Wei Yang

To further understand such efficiency-oriented threats, we propose a new attack approach, NICGSlowDown, to evaluate the efficiency robustness of NICG models.

NeReF: Neural Refractive Field for Fluid Surface Reconstruction and Implicit Representation

no code implementations8 Mar 2022 Ziyu Wang, Wei Yang, Junming Cao, Lan Xu, Junqing Yu, Jingyi Yu

We present a novel neural refractive field(NeReF) to recover wavefront of transparent fluids by simultaneously estimating the surface position and normal of the fluid front.

Surface Reconstruction

MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned

no code implementations17 Feb 2022 Anssi Kanervisto, Stephanie Milani, Karolis Ramanauskas, Nicholay Topin, Zichuan Lin, Junyou Li, Jianing Shi, Deheng Ye, Qiang Fu, Wei Yang, Weijun Hong, Zhongyue Huang, Haicheng Chen, Guangjun Zeng, Yue Lin, Vincent Micheli, Eloi Alonso, François Fleuret, Alexander Nikulin, Yury Belousov, Oleg Svidchenko, Aleksei Shpilman

With this in mind, we hosted the third edition of the MineRL ObtainDiamond competition, MineRL Diamond 2021, with a separate track in which we permitted any solution to promote the participation of newcomers.

EREBA: Black-box Energy Testing of Adaptive Neural Networks

no code implementations12 Feb 2022 Mirazul Haque, Yaswanth Yadlapalli, Wei Yang, Cong Liu

The test inputs generated by EREBA can increase the energy consumption of AdNNs by 2, 000% compared to the original inputs.

NeuVV: Neural Volumetric Videos with Immersive Rendering and Editing

no code implementations12 Feb 2022 Jiakai Zhang, Liao Wang, Xinhang Liu, Fuqiang Zhao, Minzhang Li, Haizhao Dai, Boyuan Zhang, Wei Yang, Lan Xu, Jingyi Yu

We further develop a hybrid neural-rasterization rendering framework to support consumer-level VR headsets so that the aforementioned volumetric video viewing and editing, for the first time, can be conducted immersively in virtual 3D space.

3D Reconstruction

Video-driven Neural Physically-based Facial Asset for Production

no code implementations11 Feb 2022 Longwen Zhang, Chuxiao Zeng, Qixuan Zhang, Hongyang Lin, Ruixiang Cao, Wei Yang, Lan Xu, Jingyi Yu

We then model the facial expression, geometry and physically-based textures using separate VAEs with a global MLP-based expression mapping across the latent spaces, to preserve characteristics across respective attributes while maintaining explicit controls over geometry and texture.

motion retargeting Texture Synthesis

Artemis: Articulated Neural Pets with Appearance and Motion synthesis

1 code implementation11 Feb 2022 Haimin Luo, Teng Xu, Yuheng Jiang, Chenglin Zhou, QIwei Qiu, Yingliang Zhang, Wei Yang, Lan Xu, Jingyi Yu

Our ARTEMIS enables interactive motion control, real-time animation, and photo-realistic rendering of furry animals.

motion synthesis

JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning

no code implementations7 Dec 2021 Zichuan Lin, Junyou Li, Jianing Shi, Deheng Ye, Qiang Fu, Wei Yang

To address this, we propose JueWu-MC, a sample-efficient hierarchical RL approach equipped with representation learning and imitation learning to deal with perception and exploration.

Efficient Exploration Hierarchical Reinforcement Learning +3

HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputs

no code implementations6 Dec 2021 Fuqiang Zhao, Wei Yang, Jiakai Zhang, Pei Lin, Yingliang Zhang, Jingyi Yu, Lan Xu

The raw HumanNeRF can already produce reasonable rendering on sparse video inputs of unseen subjects and camera settings.

Frame

Hierarchical Neural Data Synthesis for Semantic Parsing

no code implementations4 Dec 2021 Wei Yang, Peng Xu, Yanshuai Cao

Moreover, even the questions pertinent to a given domain, which are the input of a semantic parsing system, might not be readily available, especially in cross-domain semantic parsing.

Data Augmentation Semantic Parsing +1

Learning Perceptual Concepts by Bootstrapping from Human Queries

no code implementations9 Nov 2021 Andreea Bobu, Chris Paxton, Wei Yang, Balakumar Sundaralingam, Yu-Wei Chao, Maya Cakmak, Dieter Fox

To address this challenge, we propose a new approach whereby the robot learns a low-dimensional variant of the concept and uses it to generate a larger data set for learning the concept in the high-dimensional space.

Motion Planning

Learning Diverse Policies in MOBA Games via Macro-Goals

no code implementations NeurIPS 2021 Yiming Gao, Bei Shi, Xueying Du, Liang Wang, Guangwei Chen, Zhenjie Lian, Fuhao Qiu, Guoan Han, Weixuan Wang, Deheng Ye, Qiang Fu, Wei Yang, Lanxiao Huang

Recently, many researchers have made successful progress in building the AI systems for MOBA-game-playing with deep reinforcement learning, such as on Dota 2 and Honor of Kings.

Dota 2

NODEAttack: Adversarial Attack on the Energy Consumption of Neural ODEs

no code implementations29 Sep 2021 Mirazul Haque, Simin Chen, Wasif Arman Haque, Cong Liu, Wei Yang

Unlike the memory cost, the energy consumption of the Neural ODEs during inference can be adaptive because of the adaptive nature of the ODE solvers.

Adversarial Attack Object Recognition

TransSlowDown: Efficiency Attacks on Neural Machine Translation Systems

no code implementations29 Sep 2021 Simin Chen, Mirazul Haque, Zihe Song, Cong Liu, Wei Yang

To further the understanding of such efficiency-oriented threats and raise the community’s concern on the efficiency robustness of NMT systems, we propose a new attack approach, TranSlowDown, to test the efficiency robustness of NMT systems.

Machine Translation Translation

Estimating Predictive Uncertainty Under Program Data Distribution Shift

1 code implementation23 Jul 2021 Yufei Li, Simin Chen, Wei Yang

Experiments show that program distribution shift does degrade the DL model performance to varying degrees and that existing uncertainty methods all present certain limitations in quantifying uncertainty on program dataset.

Boosting Offline Reinforcement Learning with Residual Generative Modeling

no code implementations19 Jun 2021 Hua Wei, Deheng Ye, Zhao Liu, Hao Wu, Bo Yuan, Qiang Fu, Wei Yang, Zhenhui Li

While most research focuses on the state-action function part through reducing the bootstrapping error in value function approximation induced by the distribution shift of training data, the effects of error propagation in generative modeling have been neglected.

Offline RL Q-Learning +1

GLIB: Towards Automated Test Oracle for Graphically-Rich Applications

1 code implementation19 Jun 2021 Ke Chen, Yufei Li, Yingfeng Chen, Changjie Fan, Zhipeng Hu, Wei Yang

We perform an evaluation of \texttt{GLIB} on 20 real-world game apps (with bug reports available) and the result shows that \texttt{GLIB} can achieve 100\% precision and 99. 5\% recall in detecting non-crashing bugs such as game GUI glitches.

14 Data Augmentation

SynthASR: Unlocking Synthetic Data for Speech Recognition

no code implementations14 Jun 2021 Amin Fazel, Wei Yang, YuLan Liu, Roberto Barra-Chicote, Yixiong Meng, Roland Maas, Jasha Droppo

Our observations show that SynthASR holds great promise in training the state-of-the-art large-scale E2E ASR models for new applications while reducing the costs and dependency on production data.

Automatic Speech Recognition Continual Learning +1

A Globally Normalized Neural Model for Semantic Parsing

no code implementations ACL (spnlp) 2021 Chenyang Huang, Wei Yang, Yanshuai Cao, Osmar Zaïane, Lili Mou

In this paper, we propose a globally normalized model for context-free grammar (CFG)-based semantic parsing.

Semantic Parsing

MapGo: Model-Assisted Policy Optimization for Goal-Oriented Tasks

1 code implementation13 May 2021 Menghui Zhu, Minghuan Liu, Jian Shen, Zhicheng Zhang, Sheng Chen, Weinan Zhang, Deheng Ye, Yong Yu, Qiang Fu, Wei Yang

In Goal-oriented Reinforcement learning, relabeling the raw goals in past experience to provide agents with hindsight ability is a major solution to the reward sparsity problem.

reinforcement-learning

SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos

1 code implementation23 Apr 2021 Xin Chen, Anqi Pang, Wei Yang, Yuexin Ma, Lan Xu, Jingyi Yu

In this paper, we propose SportsCap -- the first approach for simultaneously capturing 3D human motions and understanding fine-grained actions from monocular challenging sports video input.

Action Assessment Markerless Motion Capture

Wide-Beam Array Antenna Power Gain Maximization via ADMM Framework

no code implementations21 Apr 2021 Shiwen Lei, Jing Tian, Zhipeng Lin, Haoquan Hu, Bo Chen, Wei Yang, Pu Tang, Xiangdong Qiu

This paper proposes two algorithms to maximize the minimum array power gain in a wide-beam mainlobe by solving the power gain pattern synthesis (PGPS) problem with and without sidelobe constraints.

F3SNet: A Four-Step Strategy for QIM Steganalysis of Compressed Speech Based on Hierarchical Attention Network

1 code implementation13 Jan 2021 Chuanpeng Guo, Wei Yang, Liusheng Huang

Traditional machine learning-based steganalysis methods on compressed speech have achieved great success in the field of communication security.

Cryptography and Security

AttackDist: Characterizing Zero-day Adversarial Samples by Counter Attack

no code implementations1 Jan 2021 Simin Chen, Zihe Song, Lei Ma, Cong Liu, Wei Yang

We first theoretically clarify under which condition AttackDist can provide a certified detecting performance, then show that a potential application of AttackDist is distinguishing zero-day adversarial examples without knowing the mechanisms of new attacks.

Revealing the Reciprocal Relations Between Self-Supervised Stereo and Monocular Depth Estimation

no code implementations ICCV 2021 Zhi Chen, Xiaoqing Ye, Wei Yang, Zhenbo Xu, Xiao Tan, Zhikang Zou, Errui Ding, Xinming Zhang, Liusheng Huang

Second, we introduce an occlusion-aware distillation (OA Distillation) module, which leverages the predicted depths from StereoNet in non-occluded regions to train our monocular depth estimation network named SingleNet.

Monocular Depth Estimation Stereo Matching

Optimizing Deeper Transformers on Small Datasets

1 code implementation ACL 2021 Peng Xu, Dhruv Kumar, Wei Yang, Wenjie Zi, Keyi Tang, Chenyang Huang, Jackie Chi Kit Cheung, Simon J. D. Prince, Yanshuai Cao

This work shows that this does not always need to be the case: with proper initialization and optimization, the benefits of very deep transformers can carry over to challenging tasks with small datasets, including Text-to-SQL semantic parsing and logical reading comprehension.

Reading Comprehension Semantic Parsing +2

Which Heroes to Pick? Learning to Draft in MOBA Games with Neural Networks and Tree Search

no code implementations18 Dec 2020 Sheng Chen, Menghui Zhu, Deheng Ye, Weinan Zhang, Qiang Fu, Wei Yang

Hero drafting is essential in MOBA game playing as it builds the team of each side and directly affects the match outcome.

RaP-Net: A Region-wise and Point-wise Weighting Network to Extract Robust Features for Indoor Localization

1 code implementation1 Dec 2020 Dongjiang Li, Jinyu Miao, Xuesong Shi, Yuxin Tian, Qiwei Long, Tianyu Cai, Ping Guo, Hongfei Yu, Wei Yang, Haosong Yue, Qi Wei, Fei Qiao

Experimental results show that the proposed RaP-Net trained with OpenLORIS-Location dataset achieves excellent performance in the feature matching task and significantly outperforms state-of-the-arts feature algorithms in indoor localization.

Indoor Localization Visual Localization

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 +1

Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings

no code implementations25 Nov 2020 Deheng Ye, Guibin Chen, Peilin Zhao, Fuhao Qiu, Bo Yuan, Wen Zhang, Sheng Chen, Mingfei Sun, Xiaoqian Li, Siqin Li, Jing Liang, Zhenjie Lian, Bei Shi, Liang Wang, Tengfei Shi, Qiang Fu, Wei Yang, Lanxiao Huang

Unlike prior attempts, we integrate the macro-strategy and the micromanagement of MOBA-game-playing into neural networks in a supervised and end-to-end manner.

Reactive Human-to-Robot Handovers of Arbitrary Objects

no code implementations17 Nov 2020 Wei Yang, Chris Paxton, Arsalan Mousavian, Yu-Wei Chao, Maya Cakmak, Dieter Fox

We demonstrate the generalizability, usability, and robustness of our approach on a novel benchmark set of 26 diverse household objects, a user study with naive users (N=6) handing over a subset of 15 objects, and a systematic evaluation examining different ways of handing objects.

Grasp Generation Motion Planning

Emergence of Chern insulating states in non-Magic angle twisted bilayer graphene

no code implementations8 Oct 2020 Cheng Shen, Jianghua Ying, Le Liu, Jianpeng Liu, Na Li, Shuopei Wang, Jian Tang, Yanchong Zhao, Yanbang Chu, Kenji Watanabe, Takashi Taniguchi, Rong Yang, Dongxia Shi, Fanming Qu, Li Lu, Wei Yang, Guangyu Zhang

For {\theta}=1. 25{\deg}, we observe an emergence of topological insulating states at hole side with a sequence of Chern number |C|=4-|v|, where v is the number of electrons (holes) in moir\'e unite cell.

Mesoscale and Nanoscale Physics Materials Science

Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds

1 code implementation2 Oct 2020 Lirui Wang, Yu Xiang, Wei Yang, Arsalan Mousavian, Dieter Fox

We demonstrate that our learned policy can be integrated into a tabletop 6D grasping system and a human-robot handover system to improve the grasping performance of unseen objects.

Imitation Learning Motion Planning +1

SpineParseNet: Spine Parsing for Volumetric MR Image by a Two-Stage Segmentation Framework with Semantic Image Representation

1 code implementation IEEE Transactions on Medical Imaging 2020 Shumao Pang, Chunlan Pang, Lei Zhao, Yangfan Chen, Zhihai Su, Yujia Zhou, Meiyan Huang, Wei Yang, Hai Lu, Qianjin Feng

The SpineParseNet consists of a 3D graph convolutional segmentation network (GCSN) for 3D coarse segmentation and a 2D residual U-Net (ResUNet) for 2D segmentation refinement.

DXSLAM: A Robust and Efficient Visual SLAM System with Deep Features

3 code implementations12 Aug 2020 Dongjiang Li, Xuesong Shi, Qiwei Long, Shenghui Liu, Wei Yang, Fangshi Wang, Qi Wei, Fei Qiao

For visual SLAM algorithms, though the theoretical framework has been well established for most aspects, feature extraction and association is still empirically designed in most cases, and can be vulnerable in complex environments.

Loop Closure Detection Simultaneous Localization and Mapping

Segment as Points for Efficient Online Multi-Object Tracking and Segmentation

1 code implementation ECCV 2020 Zhenbo Xu, Wei zhang, Xiao Tan, Wei Yang, Huan Huang, Shilei Wen, Errui Ding, Liusheng Huang

The resulting online MOTS framework, named PointTrack, surpasses all the state-of-the-art methods including 3D tracking methods by large margins (5. 4% higher MOTSA and 18 times faster over MOTSFusion) with the near real-time speed (22 FPS).

Multi-Object Tracking Multi-Object Tracking and Segmentation +1

PointTrack++ for Effective Online Multi-Object Tracking and Segmentation

1 code implementation3 Jul 2020 Zhenbo Xu, Wei zhang, Xiao Tan, Wei Yang, Xiangbo Su, Yuchen Yuan, Hongwu Zhang, Shilei Wen, Errui Ding, Liusheng Huang

In this work, we present PointTrack++, an effective on-line framework for MOTS, which remarkably extends our recently proposed PointTrack framework.

Data Augmentation Instance Segmentation +5

Human Grasp Classification for Reactive Human-to-Robot Handovers

no code implementations12 Mar 2020 Wei Yang, Chris Paxton, Maya Cakmak, Dieter Fox

In this paper, we propose an approach for human-to-robot handovers in which the robot meets the human halfway, by classifying the human's grasp of the object and quickly planning a trajectory accordingly to take the object from the human's hand according to their intent.

Classification General Classification

ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection

1 code implementation1 Mar 2020 Zhenbo Xu, Wei zhang, Xiaoqing Ye, Xiao Tan, Wei Yang, Shilei Wen, Errui Ding, Ajin Meng, Liusheng Huang

The pipeline of ZoomNet begins with an ordinary 2D object detection model which is used to obtain pairs of left-right bounding boxes.

2D object detection 3D Object Detection +2

Integrating Discrete and Neural Features via Mixed-feature Trans-dimensional Random Field Language Models

no code implementations14 Feb 2020 Silin Gao, Zhijian Ou, Wei Yang, Huifang Xu

There has been a long recognition that discrete features (n-gram features) and neural network based features have complementary strengths for language models (LMs).

Speech Recognition

Rapid Adaptation of BERT for Information Extraction on Domain-Specific Business Documents

no code implementations5 Feb 2020 Ruixue Zhang, Wei Yang, Luyun Lin, Zhengkai Tu, Yuqing Xie, Zihang Fu, Yuhao Xie, Luchen Tan, Kun Xiong, Jimmy Lin

Techniques for automatically extracting important content elements from business documents such as contracts, statements, and filings have the potential to make business operations more efficient.

Cross-Domain Modeling of Sentence-Level Evidence for Document Retrieval

no code implementations IJCNLP 2019 Zeynep Akkalyoncu Yilmaz, Wei Yang, Haotian Zhang, Jimmy Lin

This paper applies BERT to ad hoc document retrieval on news articles, which requires addressing two challenges: relevance judgments in existing test collections are typically provided only at the document level, and documents often exceed the length that BERT was designed to handle.

Applying BERT to Document Retrieval with Birch

no code implementations IJCNLP 2019 Zeynep Akkalyoncu Yilmaz, Shengjin Wang, Wei Yang, Haotian Zhang, Jimmy Lin

We present Birch, a system that applies BERT to document retrieval via integration with the open-source Anserini information retrieval toolkit to demonstrate end-to-end search over large document collections.

Information Retrieval

Our Neural Machine Translation Systems for WAT 2019

no code implementations WS 2019 Wei Yang, Jun Ogata

We use Transformer model through our work in this paper to explore and experience the powerful of the Transformer architecture relying on self-attention mechanism.

Machine Translation Translation

Multi-Stage Document Ranking with BERT

2 code implementations31 Oct 2019 Rodrigo Nogueira, Wei Yang, Kyunghyun Cho, Jimmy Lin

The advent of deep neural networks pre-trained via language modeling tasks has spurred a number of successful applications in natural language processing.

Document Ranking Language Modelling

DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System

no code implementations7 Oct 2019 Ankur Handa, Karl Van Wyk, Wei Yang, Jacky Liang, Yu-Wei Chao, Qian Wan, Stan Birchfield, Nathan Ratliff, Dieter Fox

Teleoperation offers the possibility of imparting robotic systems with sophisticated reasoning skills, intuition, and creativity to perform tasks.

Aggregating Votes with Local Differential Privacy: Usefulness, Soundness vs. Indistinguishability

no code implementations14 Aug 2019 Shaowei Wang, Jiachun Du, Wei Yang, Xinrong Diao, Zichun Liu, Yiwen Nie, Liusheng Huang, Hongli Xu

In this work, after theoretically quantifying the estimation error bound and the manipulating risk bound of the Laplace mechanism, we propose two mechanisms improving the usefulness and soundness simultaneously: the weighted sampling mechanism and the additive mechanism.

Decision Making

End-to-End Neural Context Reconstruction in Chinese Dialogue

no code implementations WS 2019 Wei Yang, Rui Qiao, Haocheng Qin, Amy Sun, Luchen Tan, Kun Xiong, Ming Li

We tackle the problem of context reconstruction in Chinese dialogue, where the task is to replace pronouns, zero pronouns, and other referring expressions with their referent nouns so that sentences can be processed in isolation without context.

Coreference Resolution POS +1

Detecting Customer Complaint Escalation with Recurrent Neural Networks and Manually-Engineered Features

no code implementations NAACL 2019 Wei Yang, Luchen Tan, Chunwei Lu, Anqi Cui, Han Li, Xi Chen, Kun Xiong, Muzi Wang, Ming Li, Jian Pei, Jimmy Lin

Consumers dissatisfied with the normal dispute resolution process provided by an e-commerce company{'}s customer service agents have the option of escalating their complaints by filing grievances with a government authority.

Document Expansion by Query Prediction

4 code implementations17 Apr 2019 Rodrigo Nogueira, Wei Yang, Jimmy Lin, Kyunghyun Cho

One technique to improve the retrieval effectiveness of a search engine is to expand documents with terms that are related or representative of the documents' content. From the perspective of a question answering system, this might comprise questions the document can potentially answer.

Passage Re-Ranking Question Answering +1

Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering

no code implementations14 Apr 2019 Wei Yang, Yuqing Xie, Luchen Tan, Kun Xiong, Ming Li, Jimmy Lin

Recently, a simple combination of passage retrieval using off-the-shelf IR techniques and a BERT reader was found to be very effective for question answering directly on Wikipedia, yielding a large improvement over the previous state of the art on a standard benchmark dataset.

Data Augmentation Open-Domain Question Answering +1

Simple Applications of BERT for Ad Hoc Document Retrieval

2 code implementations26 Mar 2019 Wei Yang, Haotian Zhang, Jimmy Lin

Following recent successes in applying BERT to question answering, we explore simple applications to ad hoc document retrieval.

Ad-Hoc Information Retrieval Question Answering

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.

Sequenced-Replacement Sampling for Deep Learning

no code implementations ICLR 2019 Chiu Man Ho, Dae Hoon Park, Wei Yang, Yi Chang

We propose sequenced-replacement sampling (SRS) for training deep neural networks.

Visual Semantic Navigation using Scene Priors

1 code implementation ICLR 2019 Wei Yang, Xiaolong Wang, Ali Farhadi, Abhinav Gupta, Roozbeh Mottaghi

Do we use the semantic/functional priors we have built over years to efficiently search and navigate?

reinforcement-learning

Towards End-to-End License Plate Detection and Recognition: A Large Dataset and Baseline

2 code implementations ECCV 2018 Zhenbo Xu, Wei Yang, Ajin Meng, Nanxue Lu, Huan Huang, Changchun Ying, Liusheng Huang

Most current license plate (LP) detection and recognition approaches are evaluated on a small and usually unrepresentative dataset since there are no publicly available large diverse datasets.

License Plate Detection

MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks

no code implementations31 Aug 2018 Siwakorn Srisakaokul, Yuhao Zhang, Zexuan Zhong, Wei Yang, Tao Xie, Bo Li

In particular, given a target model, our framework includes multiple models (constructed from the target model) to form a model family.

Testing Untestable Neural Machine Translation: An Industrial Case

no code implementations6 Jul 2018 Wujie Zheng, Wenyu Wang, Dian Liu, Changrong Zhang, Qinsong Zeng, Yuetang Deng, Wei Yang, Pinjia He, Tao Xie

To fill the gap of lacking test oracle for in-vivo testing of an NMT system, in this paper, we propose a new approach for automatically identifying translation failures, without requiring reference translations for a translation task; our approach can directly serve as a test oracle for in-vivo testing.

Machine Translation Translation

Multi-Perspective Relevance Matching with Hierarchical ConvNets for Social Media Search

3 code implementations21 May 2018 Jinfeng Rao, Wei Yang, Yuhao Zhang, Ferhan Ture, Jimmy Lin

To our best knowledge, this paper presents the first substantial work tackling search over social media posts using neural ranking models.

Information Retrieval

3D Human Pose Estimation in the Wild by Adversarial Learning

no code implementations CVPR 2018 Wei Yang, Wanli Ouyang, Xiaolong Wang, Jimmy Ren, Hongsheng Li, Xiaogang Wang

Instead of defining hard-coded rules to constrain the pose estimation results, we design a novel multi-source discriminator to distinguish the predicted 3D poses from the ground-truth, which helps to enforce the pose estimator to generate anthropometrically valid poses even with images in the wild.

Monocular 3D Human Pose Estimation

Robust 3D Human Motion Reconstruction Via Dynamic Template Construction

no code implementations31 Jan 2018 Zhong Li, Yu Ji, Wei Yang, Jinwei Ye, Jingyi Yu

In multi-view human body capture systems, the recovered 3D geometry or even the acquired imagery data can be heavily corrupted due to occlusions, noise, limited field of- view, etc.

Frame

A Roadmap for HEP Software and Computing R&D for the 2020s

1 code implementation18 Dec 2017 Johannes Albrecht, Antonio Augusto Alves Jr, Guilherme Amadio, Giuseppe Andronico, Nguyen Anh-Ky, Laurent Aphecetche, John Apostolakis, Makoto Asai, Luca Atzori, Marian Babik, Giuseppe Bagliesi, Marilena Bandieramonte, Sunanda Banerjee, Martin Barisits, Lothar A. T. Bauerdick, Stefano Belforte, Douglas Benjamin, Catrin Bernius, Wahid Bhimji, Riccardo Maria Bianchi, Ian Bird, Catherine Biscarat, Jakob Blomer, Kenneth Bloom, Tommaso Boccali, Brian Bockelman, Tomasz Bold, Daniele Bonacorsi, Antonio Boveia, Concezio Bozzi, Marko Bracko, David Britton, Andy Buckley, Predrag Buncic, Paolo Calafiura, Simone Campana, Philippe Canal, Luca Canali, Gianpaolo Carlino, Nuno Castro, Marco Cattaneo, Gianluca Cerminara, Javier Cervantes Villanueva, Philip Chang, John Chapman, Gang Chen, Taylor Childers, Peter Clarke, Marco Clemencic, Eric Cogneras, Jeremy Coles, Ian Collier, David Colling, Gloria Corti, Gabriele Cosmo, Davide Costanzo, Ben Couturier, Kyle Cranmer, Jack Cranshaw, Leonardo Cristella, David Crooks, Sabine Crépé-Renaudin, Robert Currie, Sünje Dallmeier-Tiessen, Kaushik De, Michel De Cian, Albert De Roeck, Antonio Delgado Peris, Frédéric Derue, Alessandro Di Girolamo, Salvatore Di Guida, Gancho Dimitrov, Caterina Doglioni, Andrea Dotti, Dirk Duellmann, Laurent Duflot, Dave Dykstra, Katarzyna Dziedziniewicz-Wojcik, Agnieszka Dziurda, Ulrik Egede, Peter Elmer, Johannes Elmsheuser, V. Daniel Elvira, Giulio Eulisse, Steven Farrell, Torben Ferber, Andrej Filipcic, Ian Fisk, Conor Fitzpatrick, José Flix, Andrea Formica, Alessandra Forti, Giovanni Franzoni, James Frost, Stu Fuess, Frank Gaede, Gerardo Ganis, Robert Gardner, Vincent Garonne, Andreas Gellrich, Krzysztof Genser, Simon George, Frank Geurts, Andrei Gheata, Mihaela Gheata, Francesco Giacomini, Stefano Giagu, Manuel Giffels, Douglas Gingrich, Maria Girone, Vladimir V. Gligorov, Ivan Glushkov, Wesley Gohn, Jose Benito Gonzalez Lopez, Isidro González Caballero, Juan R. González Fernández, Giacomo Govi, Claudio Grandi, Hadrien Grasland, Heather Gray, Lucia Grillo, Wen Guan, Oliver Gutsche, Vardan Gyurjyan, Andrew Hanushevsky, Farah Hariri, Thomas Hartmann, John Harvey, Thomas Hauth, Benedikt Hegner, Beate Heinemann, Lukas Heinrich, Andreas Heiss, José M. Hernández, Michael Hildreth, Mark Hodgkinson, Stefan Hoeche, Burt Holzman, Peter Hristov, Xingtao Huang, Vladimir N. Ivanchenko, Todor Ivanov, Jan Iven, Brij Jashal, Bodhitha Jayatilaka, Roger Jones, Michel Jouvin, Soon Yung Jun, Michael Kagan, Charles William Kalderon, Meghan Kane, Edward Karavakis, Daniel S. Katz, Dorian Kcira, Oliver Keeble, Borut Paul Kersevan, Michael Kirby, Alexei Klimentov, Markus Klute, Ilya Komarov, Dmitri Konstantinov, Patrick Koppenburg, Jim Kowalkowski, Luke Kreczko, Thomas Kuhr, Robert Kutschke, Valentin Kuznetsov, Walter Lampl, Eric Lancon, David Lange, Mario Lassnig, Paul Laycock, Charles Leggett, James Letts, Birgit Lewendel, Teng Li, Guilherme Lima, Jacob Linacre, Tomas Linden, Miron Livny, Giuseppe Lo Presti, Sebastian Lopienski, Peter Love, Adam Lyon, Nicolò Magini, Zachary L. Marshall, Edoardo Martelli, Stewart Martin-Haugh, Pere Mato, Kajari Mazumdar, Thomas McCauley, Josh McFayden, Shawn McKee, Andrew McNab, Rashid Mehdiyev, Helge Meinhard, Dario Menasce, Patricia Mendez Lorenzo, Alaettin Serhan Mete, Michele Michelotto, Jovan Mitrevski, Lorenzo Moneta, Ben Morgan, Richard Mount, Edward Moyse, Sean Murray, Armin Nairz, Mark S. Neubauer, Andrew Norman, Sérgio Novaes, Mihaly Novak, Arantza Oyanguren, Nurcan Ozturk, Andres Pacheco Pages, Michela Paganini, Jerome Pansanel, Vincent R. Pascuzzi, Glenn Patrick, Alex Pearce, Ben Pearson, Kevin Pedro, Gabriel Perdue, Antonio Perez-Calero Yzquierdo, Luca Perrozzi, Troels Petersen, Marko Petric, Andreas Petzold, Jónatan Piedra, Leo Piilonen, Danilo Piparo, Jim Pivarski, Witold Pokorski, Francesco Polci, Karolos Potamianos, Fernanda Psihas, Albert Puig Navarro, Günter Quast, Gerhard Raven, Jürgen Reuter, Alberto Ribon, Lorenzo Rinaldi, Martin Ritter, James Robinson, Eduardo Rodrigues, Stefan Roiser, David Rousseau, Gareth Roy, Grigori Rybkine, Andre Sailer, Tai Sakuma, Renato Santana, Andrea Sartirana, Heidi Schellman, Jaroslava Schovancová, Steven Schramm, Markus Schulz, Andrea Sciabà, Sally Seidel, Sezen Sekmen, Cedric Serfon, Horst Severini, Elizabeth Sexton-Kennedy, Michael Seymour, Davide Sgalaberna, Illya Shapoval, Jamie Shiers, Jing-Ge Shiu, Hannah Short, Gian Piero Siroli, Sam Skipsey, Tim Smith, Scott Snyder, Michael D. Sokoloff, Panagiotis Spentzouris, Hartmut Stadie, Giordon Stark, Gordon Stewart, Graeme A. Stewart, Arturo Sánchez, Alberto Sánchez-Hernández, Anyes Taffard, Umberto Tamponi, Jeff Templon, Giacomo Tenaglia, Vakhtang Tsulaia, Christopher Tunnell, Eric Vaandering, Andrea Valassi, Sofia Vallecorsa, Liviu Valsan, Peter Van Gemmeren, Renaud Vernet, Brett Viren, Jean-Roch Vlimant, Christian Voss, Margaret Votava, Carl Vuosalo, Carlos Vázquez Sierra, Romain Wartel, Gordon T. Watts, Torre Wenaus, Sandro Wenzel, Mike Williams, Frank Winklmeier, Christoph Wissing, Frank Wuerthwein, Benjamin Wynne, Zhang Xiaomei, Wei Yang, Efe Yazgan

Particle physics has an ambitious and broad experimental programme for the coming decades.

Computational Physics High Energy Physics - Experiment

Ray Space Features for Plenoptic Structure-From-Motion

no code implementations ICCV 2017 Yingliang Zhang, Peihong Yu, Wei Yang, Yuanxi Ma, Jingyi Yu

In this paper, we explore using light fields captured by plenoptic cameras or camera arrays as inputs.

Multi-Context Attention for Human Pose Estimation

2 code implementations CVPR 2017 Xiao Chu, Wei Yang, Wanli Ouyang, Cheng Ma, Alan L. Yuille, Xiaogang Wang

We further combine the holistic attention model, which focuses on the global consistency of the full human body, and the body part attention model, which focuses on the detailed description for different body parts.

Pose Estimation

Progressively Diffused Networks for Semantic Image Segmentation

no code implementations20 Feb 2017 Ruimao Zhang, Wei Yang, Zhanglin Peng, Xiaogang Wang, Liang Lin

This paper introduces Progressively Diffused Networks (PDNs) for unifying multi-scale context modeling with deep feature learning, by taking semantic image segmentation as an exemplar application.

Semantic Segmentation

Personalized Classifier Ensemble Pruning Framework for Mobile Crowdsourcing

no code implementations25 Jan 2017 Shaowei Wang, Liusheng Huang, Pengzhan Wang, Hongli Xu, Wei Yang

One of the fundamental issue in ensemble learning is the trade-off between classification accuracy and computational costs, which is the goal of ensemble pruning.

Ensemble Learning Ensemble Pruning

Improving Patent Translation using Bilingual Term Extraction and Re-tokenization for Chinese--Japanese

no code implementations WS 2016 Wei Yang, Yves Lepage

To improve the translation accuracy, we adjust and balance the granularity of segmentation results around terms for Chinese{--}Japanese patent corpus for training translation model.

Chinese Word Segmentation Machine Translation +2

End-To-End Learning of Deformable Mixture of Parts and Deep Convolutional Neural Networks for Human Pose Estimation

no code implementations CVPR 2016 Wei Yang, Wanli Ouyang, Hongsheng Li, Xiaogang Wang

In this paper, we propose a novel end-to-end framework for human pose estimation that combines DCNNs with the expressive deformable mixture of parts.

Pose Estimation

Resolving Scale Ambiguity Via XSlit Aspect Ratio Analysis

no code implementations ICCV 2015 Wei Yang, Haiting Lin, Sing Bing Kang, Jingyi Yu

We first conduct a comprehensive analysis to characterize DDAR, infer object depth from its AR, and model recoverable depth range, sensitivity, and error.

3D Reconstruction

Ambient Occlusion via Compressive Visibility Estimation

no code implementations CVPR 2015 Wei Yang, Yu Ji, Haiting Lin, Yang Yang, Sing Bing Kang, Jingyi Yu

This enables a sparsity-prior based solution for iteratively recovering the surface normal, the surface albedo, and the visibility function from a small number of images.

Compressive Sensing

Data-Driven Scene Understanding with Adaptively Retrieved Exemplars

no code implementations3 Feb 2015 Xionghao Liu, Wei Yang, Liang Lin, Qing Wang, Zhaoquan Cai, Jian-Huang Lai

In the first step, the references are selected by jointly matching their appearances with the target as well as the semantics (i. e. the assigned labels of the target and the references).

Scene Understanding Semantic Segmentation +1

Clothing Co-Parsing by Joint Image Segmentation and Labeling

no code implementations CVPR 2014 Wei Yang, Ping Luo, Liang Lin

This paper aims at developing an integrated system of clothing co-parsing, in order to jointly parse a set of clothing images (unsegmented but annotated with tags) into semantic configurations.

Semantic Segmentation

Learning Contour-Fragment-based Shape Model with And-Or Tree Representation

no code implementations3 Feb 2015 Liang Lin, Xiaolong Wang, Wei Yang, Jian-Huang Lai

This paper proposes a simple yet effective method to learn the hierarchical object shape model consisting of local contour fragments, which represents a category of shapes in the form of an And-Or tree.

Edge Detection

Discriminatively Trained And-Or Graph Models for Object Shape Detection

no code implementations2 Feb 2015 Liang Lin, Xiaolong Wang, Wei Yang, Jian-Huang Lai

In this paper, we investigate a novel reconfigurable part-based model, namely And-Or graph model, to recognize object shapes in images.

Object Detection

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