Search Results for author: Wei Li

Found 265 papers, 92 papers with code

Meta-CQG: A Meta-Learning Framework for Complex Question Generation over Knowledge Bases

no code implementations COLING 2022 Kun Zhang, Yunqi Qiu, Yuanzhuo Wang, Long Bai, Wei Li, Xuhui Jiang, HuaWei Shen, Xueqi Cheng

Complex question generation over knowledge bases (KB) aims to generate natural language questions involving multiple KB relations or functional constraints.

Contrastive Learning Meta-Learning +2

Towards Efficient Coarse-to-Fine Networks for Action and Gesture Recognition

no code implementations ECCV 2020 Niamul Quader, Juwei Lu, Peng Dai, Wei Li

State-of-the-art approaches to video-based action and gesture recognition often employ two key concepts: First, they employ multistream processing; second, they use an ensemble of convolutional networks.

3D Action Recognition Action Classification +3

基于统一模型的藏文新闻摘要(Abstractive Summarization of Tibetan News Based on Hybrid Model)

no code implementations CCL 2020 Xiaodong Yan, Xiaoqing Xie, Yu Zou, Wei Li

Seq2seq神经网络模型在中英文文本摘要的研究中取得了良好的效果, 但在低资源语言的文本摘要研究还处于探索阶段, 尤其是在藏语中。此外, 目前还没有大规模的标注语料库进行摘要提取。本文提出了一种生成藏文新闻摘要的统一模型。利用TextRank算法解决了藏语标注训练数据不足的问题。然后, 采用两层双GRU神经网络提取代表原始新闻的句子, 减少冗余信息。最后, 使用基于注意力机制的Seq2Seq来生成理解式摘要。同时, 我们加入了指针网络来处理未登录词的问题。实验结果表明, ROUGE-1评分比传统模型提高了2%。 关键词:文本摘要;藏文;TextRank; 指针网络;Bi-GRU

Abstractive Text Summarization

SgSum:Transforming Multi-document Summarization into Sub-graph Selection

1 code implementation EMNLP 2021 Moye Chen, Wei Li, Jiachen Liu, Xinyan Xiao, Hua Wu, Haifeng Wang

Comparing with traditional methods, our method has two main advantages: (1) the relations between sentences are captured by modeling both the graph structure of the whole document set and the candidate sub-graphs; (2) directly outputs an integrate summary in the form of sub-graph which is more informative and coherent.

Document Summarization Multi-Document Summarization

Weight Excitation: Built-in Attention Mechanisms in Convolutional Neural Networks

1 code implementation ECCV 2020 Niamul Quader, Md Mafijul Islam Bhuiyan, Juwei Lu, Peng Dai, Wei Li

We propose novel approaches for simultaneously identifying important weights of a convolutional neural network (ConvNet) and providing more attention to the important weights during training.

3D Action Recognition 3D Object Classification +7

《二十四史》古代汉语语义依存图库构建(Construction of Semantic Dependency Graph Bank of Ancient Chinese in twenty four histories)

no code implementations CCL 2022 Tian Huang, Yanqiu Shao, Wei Li

“语义依存图是NLP处理语义的深层分析方法, 能够对句子中词与词之间的语义进行分析。该文针对古代汉语特点, 在制定古代汉语语义依存图标注规范的基础上, 以《二十四史》为语料来源, 完成标注了规模为3000句的古代汉语语义依存图库, 标注一致性的kappa值为78. 83%。通过与现代汉语语义依存图库的对比, 对依存图库基本情况进行统计, 分析古代汉语的语义特色和规律。统计显示, 古代汉语语义分布宏观上符合齐普夫定律, 在语义事件描述上具有强烈的历史性叙事和正式文体特征, 如以人物纪传为中心, 时间、地点等周边角色描述细致, 叙事语言冷静客观, 缺少描述情态、语气、程度、时间状态等的修饰词语等。 "

基于强化学习的古今汉语句子对齐研究(Research on Sentence Alignment of Ancient and Modern Chinese based on Reinforcement Learning)

no code implementations CCL 2022 Kuai Yu, Yanqiu Shao, Wei Li

“基于深度学习的有监督机器翻译取得了良好的效果, 但训练过程中需要大量质量较高的对齐语料。对于中文古今翻译场景, 高质量的平行语料并不多, 而粗对齐的篇章、段语料比较容易获得, 因此语料对齐很有研究价值和研究必要。在传统双语平行语料的句子对齐研究中, 传统方法根据双语文本中的长度、词汇、共现文字等语法信息, 建立一个综合评判标准来衡量两个句对之间相似度。此类方法虽然在单句对齐上取得了较好的效果, 但是对于句子语义匹配的能力有限, 并且在一些多对多的对齐模式上的性能表现不佳。在本文中我们提出尝试利用现在发展迅速且具有强大语义表示能力的预训练语言模型来考虑双语的语义信息, 但是单独使用预训练语言模型只能考虑相对局部的信息, 因此我们提出采用基于动态规划算法的强化学习训练目标来整合段落全局信息, 并且进行无监督训练。实验结果证明我们提出的方法训练得到的模型性能优于此前获得最好表现的基线模型, 尤其相较于传统模型难以处理的多对多对齐模式下, 性能提升较大。”

WeCheck: Strong Factual Consistency Checker via Weakly Supervised Learning

no code implementations20 Dec 2022 Wenhao Wu, Wei Li, Xinyan Xiao, Jiachen Liu, Sujian Li, Yajuan Lv

As a result, they perform poorly on the real generated text and are biased heavily by their single-source upstream tasks.

Natural Language Inference Question Answering +1

DCS-RISR: Dynamic Channel Splitting for Efficient Real-world Image Super-Resolution

no code implementations15 Dec 2022 Junbo Qiao, Shaohui Lin, Yunlun Zhang, Wei Li, Jie Hu, Gaoqi He, Changbo Wang, Lizhuang Ma

Real-world image super-resolution (RISR) has received increased focus for improving the quality of SR images under unknown complex degradation.

Image Super-Resolution SSIM

SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud

1 code implementation6 Dec 2022 Yan Wang, Junbo Yin, Wei Li, Pascal Frossard, Ruigang Yang, Jianbing Shen

However, these UDA solutions just yield unsatisfactory 3D detection results when there is a severe domain shift, e. g., from Waymo (64-beam) to nuScenes (32-beam).

3D Object Detection Autonomous Driving +4

Exploring Stochastic Autoregressive Image Modeling for Visual Representation

1 code implementation3 Dec 2022 Yu Qi, Fan Yang, Yousong Zhu, Yufei Liu, Liwei Wu, Rui Zhao, Wei Li

By introducing stochastic prediction and the parallel encoder-decoder, SAIM significantly improve the performance of autoregressive image modeling.

Self-Supervised Learning

MIAD: A Maintenance Inspection Dataset for Unsupervised Anomaly Detection

no code implementations25 Nov 2022 Tianpeng Bao, Jiadong Chen, Wei Li, Xiang Wang, Jingjing Fei, Liwei Wu, Rui Zhao, Ye Zheng

However, existing datasets for unsupervised anomaly detection are biased towards manufacturing inspection, not considering maintenance inspection which is usually conducted under outdoor uncontrolled environment such as varying camera viewpoints, messy background and degradation of object surface after long-term working.

Unsupervised Anomaly Detection

Delving into Out-of-Distribution Detection with Vision-Language Representations

1 code implementation24 Nov 2022 Yifei Ming, Ziyang Cai, Jiuxiang Gu, Yiyou Sun, Wei Li, Yixuan Li

Recognizing out-of-distribution (OOD) samples is critical for machine learning systems deployed in the open world.

OOD Detection Out-of-Distribution Detection

Transformation-Equivariant 3D Object Detection for Autonomous Driving

no code implementations22 Nov 2022 Hai Wu, Chenglu Wen, Wei Li, Xin Li, Ruigang Yang, Cheng Wang

However, it is difficult to apply such networks to 3D object detection in autonomous driving due to its large computation cost and slow reasoning speed.

3D Object Detection Autonomous Driving +2

A Data-driven Case-based Reasoning in Bankruptcy Prediction

no code implementations2 Nov 2022 Wei Li, Wolfgang Karl Härdle, Stefan Lessmann

In addition, we delicately examine the explainability of the CBR system in the decision-making process of bankruptcy prediction.

Decision Making

FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness

no code implementations1 Nov 2022 Wenhao Wu, Wei Li, Jiachen Liu, Xinyan Xiao, Ziqiang Cao, Sujian Li, Hua Wu

We first measure a model's factual robustness by its success rate to defend against adversarial attacks when generating factual information.

Abstractive Text Summarization

A jet tagging algorithm of graph network with HaarPooling message passing

no code implementations25 Oct 2022 Fei Ma, Feiyi Liu, Wei Li

Recently methods of graph neural networks (GNNs) have been applied to solving the problems in high energy physics (HEP) and have shown its great potential for quark-gluon tagging with graph representation of jet events.

Jet Tagging

Precisely the Point: Adversarial Augmentations for Faithful and Informative Text Generation

no code implementations22 Oct 2022 Wenhao Wu, Wei Li, Jiachen Liu, Xinyan Xiao, Sujian Li, Yajuan Lyu

Though model robustness has been extensively studied in language understanding, the robustness of Seq2Seq generation remains understudied.

Informativeness Text Generation

Robot Navigation with Reinforcement Learned Path Generation and Fine-Tuned Motion Control

no code implementations19 Oct 2022 Longyuan Zhang, Ziyue Hou, Ji Wang, Ziang Liu, Wei Li

Multiple predictive path points are dynamically generated by a deep Markov model optimized using RL approach for robot to track.

Robot Navigation

HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning

no code implementations18 Oct 2022 Zixuan Li, Zhongni Hou, Saiping Guan, Xiaolong Jin, Weihua Peng, Long Bai, Yajuan Lyu, Wei Li, Jiafeng Guo, Xueqi Cheng

This is actually a matching task between a query and candidate entities based on their historical structures, which reflect behavioral trends of the entities at different timestamps.

Zero-shot Point Cloud Segmentation by Transferring Geometric Primitives

no code implementations18 Oct 2022 Runnan Chen, Xinge Zhu, Nenglun Chen, Wei Li, Yuexin Ma, Ruigang Yang, Wenping Wang

Based on this consideration, we propose a novel framework to learn the geometric primitives shared in seen and unseen categories' objects, where the learned geometric primitives are served for transferring knowledge from seen to unseen categories.

Point Cloud Segmentation Semantic Segmentation

Unified Vision and Language Prompt Learning

1 code implementation13 Oct 2022 Yuhang Zang, Wei Li, Kaiyang Zhou, Chen Huang, Chen Change Loy

Prompt tuning, a parameter- and data-efficient transfer learning paradigm that tunes only a small number of parameters in a model's input space, has become a trend in the vision community since the emergence of large vision-language models like CLIP.

Domain Generalization Few-Shot Learning +1

Stock Trading Volume Prediction with Dual-Process Meta-Learning

1 code implementation11 Oct 2022 Ruibo Chen, Wei Li, Zhiyuan Zhang, Ruihan Bao, Keiko Harimoto, Xu sun

Our method can model the common pattern behind different stocks with a meta-learner, while modeling the specific pattern for each stock across time spans with stock-dependent parameters.

Algorithmic Trading Meta-Learning

Misaligned orientations of 4f optical neural network for image classification accuracy on various datasets

no code implementations5 Oct 2022 Yanbing Liu, Wei Li, Kun Cheng, Xun Liu, Wei Yang

In order to comprehensively investigate the influence caused by the misalignment, we proposed a method for estimating the performance of a 4f-ONN in response to various misalignment in the context of the image classification task. The misalignment in numerical simulation is estimated by manipulating the optical intensity distributions in the fourth focus plane in the 4f system.

Classification Image Classification

SoccerNet 2022 Challenges Results

6 code implementations5 Oct 2022 Silvio Giancola, Anthony Cioppa, Adrien Deliège, Floriane Magera, Vladimir Somers, Le Kang, Xin Zhou, Olivier Barnich, Christophe De Vleeschouwer, Alexandre Alahi, Bernard Ghanem, Marc Van Droogenbroeck, Abdulrahman Darwish, Adrien Maglo, Albert Clapés, Andreas Luyts, Andrei Boiarov, Artur Xarles, Astrid Orcesi, Avijit Shah, Baoyu Fan, Bharath Comandur, Chen Chen, Chen Zhang, Chen Zhao, Chengzhi Lin, Cheuk-Yiu Chan, Chun Chuen Hui, Dengjie Li, Fan Yang, Fan Liang, Fang Da, Feng Yan, Fufu Yu, Guanshuo Wang, H. Anthony Chan, He Zhu, Hongwei Kan, Jiaming Chu, Jianming Hu, Jianyang Gu, Jin Chen, João V. B. Soares, Jonas Theiner, Jorge De Corte, José Henrique Brito, Jun Zhang, Junjie Li, Junwei Liang, Leqi Shen, Lin Ma, Lingchi Chen, Miguel Santos Marques, Mike Azatov, Nikita Kasatkin, Ning Wang, Qiong Jia, Quoc Cuong Pham, Ralph Ewerth, Ran Song, RenGang Li, Rikke Gade, Ruben Debien, Runze Zhang, Sangrok Lee, Sergio Escalera, Shan Jiang, Shigeyuki Odashima, Shimin Chen, Shoichi Masui, Shouhong Ding, Sin-wai Chan, Siyu Chen, Tallal El-Shabrawy, Tao He, Thomas B. Moeslund, Wan-Chi Siu, Wei zhang, Wei Li, Xiangwei Wang, Xiao Tan, Xiaochuan Li, Xiaolin Wei, Xiaoqing Ye, Xing Liu, Xinying Wang, Yandong Guo, YaQian Zhao, Yi Yu, YingYing Li, Yue He, Yujie Zhong, Zhenhua Guo, Zhiheng Li

The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.

Action Spotting Camera Calibration +3

Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks

1 code implementation28 Sep 2022 Zhiyang Chen, Yousong Zhu, Zhaowen Li, Fan Yang, Wei Li, Haixin Wang, Chaoyang Zhao, Liwei Wu, Rui Zhao, Jinqiao Wang, Ming Tang

Obj2Seq is able to flexibly determine input categories to satisfy customized requirements, and be easily extended to different visual tasks.

Multi-Label Classification Object Detection +1

Open-Ended Diverse Solution Discovery with Regulated Behavior Patterns for Cross-Domain Adaptation

no code implementations24 Sep 2022 Kang Xu, Yan Ma, Wei Li, Bingsheng Wei

While Reinforcement Learning can achieve impressive results for complex tasks, the learned policies are generally prone to fail in downstream tasks with even minor model mismatch or unexpected perturbations.

Domain Adaptation

Quantification before Selection: Active Dynamics Preference for Robust Reinforcement Learning

no code implementations23 Sep 2022 Kang Xu, Yan Ma, Wei Li

Our key insight is that dynamic systems with different parameters provide different levels of difficulty for the policy, and the difficulty of behaving well in a system is constantly changing due to the evolution of the policy.

Informativeness reinforcement-learning +1

GANet: Goal Area Network for Motion Forecasting

no code implementations20 Sep 2022 Mingkun Wang, Xinge Zhu, Changqian Yu, Wei Li, Yuexin Ma, Ruochun Jin, Xiaoguang Ren, Dongchun Ren, Mingxu Wang, Wenjing Yang

In view of this, we propose a new goal area-based framework, named Goal Area Network (GANet), for motion forecasting, which models goal areas rather than exact goal coordinates as preconditions for trajectory prediction, performing more robustly and accurately.

Motion Forecasting Trajectory Prediction

Playing Technique Detection by Fusing Note Onset Information in Guzheng Performance

no code implementations19 Sep 2022 Dichucheng Li, Yulun Wu, Qinyu Li, Jiahao Zhao, Yi Yu, Fan Xia, Wei Li

Because each Guzheng playing technique is applied to a note, a dedicated onset detector is trained to divide an audio into several notes and its predictions are fused with frame-wise IPT predictions.

LO-Det: Lightweight Oriented Object Detection in Remote Sensing Images

no code implementations16 Sep 2022 Zhanchao Huang, Wei Li, Xiang-Gen Xia, Hao Wang, Feiran Jie, Ran Tao

Specifically, a channel separation-aggregation (CSA) structure is designed to simplify the complexity of stacked separable convolutions, and a dynamic receptive field (DRF) mechanism is developed to maintain high accuracy by customizing the convolution kernel and its perception range dynamically when reducing the network complexity.

object-detection Object Detection

Multi-Grained Angle Representation for Remote Sensing Object Detection

1 code implementation7 Sep 2022 Hao Wang, Zhanchao Huang, Zhengchao Chen, Ying Song, Wei Li

The existing AOOD methods face the challenges of ambiguity and high costs in angle representation.

object-detection Object Detection

Task-wise Sampling Convolutions for Arbitrary-Oriented Object Detection in Aerial Images

1 code implementation6 Sep 2022 Zhanchao Huang, Wei Li, Xiang-Gen Xia, Hao Wang, Ran Tao

However, the inconsistent features for the localization and classification tasks in AOOD models may lead to ambiguity and low-quality object predictions, which constrains the detection performance.

object-detection Object Detection In Aerial Images

Language-aware Domain Generalization Network for Cross-Scene Hyperspectral Image Classification

no code implementations6 Sep 2022 Yuxiang Zhang, Mengmeng Zhang, Wei Li, Shuai Wang, Ran Tao

Text information including extensive prior knowledge about land cover classes has been ignored in hyperspectral image classification (HSI) tasks.

Contrastive Learning Domain Generalization +1

Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies

1 code implementation3 Sep 2022 Xingrun Xing, Yangguang Li, Wei Li, Wenrui Ding, Yalong Jiang, Yufeng Wang, Jing Shao, Chunlei Liu, Xianglong Liu

Second, to improve the robustness of binary models with contextual dependencies, we compute the contextual dynamic embeddings to determine the binarization thresholds in general binary convolutional blocks.

Binarization Inductive Bias

DeepInteraction: 3D Object Detection via Modality Interaction

1 code implementation23 Aug 2022 Zeyu Yang, Jiaqi Chen, Zhenwei Miao, Wei Li, Xiatian Zhu, Li Zhang

Existing top-performance 3D object detectors typically rely on the multi-modal fusion strategy.

3D Object Detection object-detection

Rethinking Graph Neural Networks for the Graph Coloring Problem

no code implementations15 Aug 2022 Wei Li, Ruxuan Li, Yuzhe ma, Siu On Chan, David Pan, Bei Yu

Graph coloring, a classical and critical NP-hard problem, is the problem of assigning connected nodes as different colors as possible.

Making the Best of Both Worlds: A Domain-Oriented Transformer for Unsupervised Domain Adaptation

1 code implementation2 Aug 2022 Wenxuan Ma, Jinming Zhang, Shuang Li, Chi Harold Liu, Yulin Wang, Wei Li

To alleviate these issues, we propose to simultaneously conduct feature alignment in two individual spaces focusing on different domains, and create for each space a domain-oriented classifier tailored specifically for that domain.

Pseudo Label Unsupervised Domain Adaptation

Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios

2 code implementations12 Jul 2022 Jiashi Li, Xin Xia, Wei Li, Huixia Li, Xing Wang, Xuefeng Xiao, Rui Wang, Min Zheng, Xin Pan

Then, Next Hybrid Strategy (NHS) is designed to stack NCB and NTB in an efficient hybrid paradigm, which boosts performance in various downstream tasks.

Image Classification

SJ-HD^2R: Selective Joint High Dynamic Range and Denoising Imaging for Dynamic Scenes

no code implementations20 Jun 2022 Wei Li, Shuai Xiao, Tianhong Dai, Shanxin Yuan, Tao Wang, Cheng Li, Fenglong Song

To further leverage these two paradigms, we propose a selective and joint HDR and denoising (SJ-HD$^2$R) imaging framework, utilizing scenario-specific priors to conduct the path selection with an accuracy of more than 93. 3$\%$.


Masked Frequency Modeling for Self-Supervised Visual Pre-Training

1 code implementation15 Jun 2022 Jiahao Xie, Wei Li, Xiaohang Zhan, Ziwei Liu, Yew Soon Ong, Chen Change Loy

We present Masked Frequency Modeling (MFM), a unified frequency-domain-based approach for self-supervised pre-training of visual models.

Image Restoration Representation Learning

Toward Real-world Single Image Deraining: A New Benchmark and Beyond

1 code implementation11 Jun 2022 Wei Li, Qiming Zhang, Jing Zhang, Zhen Huang, Xinmei Tian, DaCheng Tao

To address these issues, we establish a new high-quality dataset named RealRain-1k, consisting of $1, 120$ high-resolution paired clean and rainy images with low- and high-density rain streaks, respectively.

Domain Generalization Image Restoration +2

MPANet: Multi-Patch Attention For Infrared Small Target object Detection

no code implementations5 Jun 2022 Ao Wang, Wei Li, Xin Wu, Zhanchao Huang, Ran Tao

To this end, a multi-patch attention network (MPANet) based on the axial-attention encoder and the multi-scale patch branch (MSPB) structure is proposed.

object-detection Object Detection

Benchmarking Unsupervised Anomaly Detection and Localization

no code implementations30 May 2022 Ye Zheng, Xiang Wang, Yu Qi, Wei Li, Liwei Wu

From the time the MVTec AD dataset was proposed to the present, new research methods that are constantly being proposed push its precision to saturation.

Unsupervised Anomaly Detection

Do We Really Need to Use Constraint Violation in Constrained Evolutionary Multi-Objective Optimization?

no code implementations28 May 2022 Shuang Li, Ke Li, Wei Li

Constraint violation has been a building block to design evolutionary multi-objective optimization algorithms for solving constrained multi-objective optimization problems.

NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results

no code implementations25 May 2022 Eduardo Pérez-Pellitero, Sibi Catley-Chandar, Richard Shaw, Aleš Leonardis, Radu Timofte, Zexin Zhang, Cen Liu, Yunbo Peng, Yue Lin, Gaocheng Yu, Jin Zhang, Zhe Ma, Hongbin Wang, Xiangyu Chen, Xintao Wang, Haiwei Wu, Lin Liu, Chao Dong, Jiantao Zhou, Qingsen Yan, Song Zhang, Weiye Chen, Yuhang Liu, Zhen Zhang, Yanning Zhang, Javen Qinfeng Shi, Dong Gong, Dan Zhu, Mengdi Sun, Guannan Chen, Yang Hu, Haowei Li, Baozhu Zou, Zhen Liu, Wenjie Lin, Ting Jiang, Chengzhi Jiang, Xinpeng Li, Mingyan Han, Haoqiang Fan, Jian Sun, Shuaicheng Liu, Juan Marín-Vega, Michael Sloth, Peter Schneider-Kamp, Richard Röttger, Chunyang Li, Long Bao, Gang He, Ziyao Xu, Li Xu, Gen Zhan, Ming Sun, Xing Wen, Junlin Li, Shuang Feng, Fei Lei, Rui Liu, Junxiang Ruan, Tianhong Dai, Wei Li, Zhan Lu, Hengyan Liu, Peian Huang, Guangyu Ren, Yonglin Luo, Chang Liu, Qiang Tu, Fangya Li, Ruipeng Gang, Chenghua Li, Jinjing Li, Sai Ma, Chenming Liu, Yizhen Cao, Steven Tel, Barthelemy Heyrman, Dominique Ginhac, Chul Lee, Gahyeon Kim, Seonghyun Park, An Gia Vien, Truong Thanh Nhat Mai, Howoon Yoon, Tu Vo, Alexander Holston, Sheir Zaheer, Chan Y. Park

The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i. e. solutions can not exceed a given number of operations).

Image Restoration

A Survey on Hyperspectral Image Restoration: From the View of Low-Rank Tensor Approximation

no code implementations18 May 2022 Na Liu, Wei Li, Yinjian Wang, Rao Tao, Qian Du, Jocelyn Chanussot

The ability of capturing fine spectral discriminative information enables hyperspectral images (HSIs) to observe, detect and identify objects with subtle spectral discrepancy.

Deblurring Denoising +2

$(O,G)$-granular variable precision fuzzy rough sets based on overlap and grouping functions

no code implementations18 May 2022 Wei Li, Bin Yang, Junsheng Qiao

In this paper, the depiction of $(O, G)$-granular variable precision fuzzy rough sets ($(O, G)$-GVPFRSs for short) is first given based on overlap and grouping functions.

Some neighborhood-related fuzzy covering-based rough set models and their applications for decision making

no code implementations13 May 2022 Gongao Qi, Bin Yang, Wei Li

In order to further generalize the FRS theory to more complicated data environments, we firstly propose four types of fuzzy neighborhood operators based on fuzzy covering by overlap functions and their implicators in this paper.

Decision Making

On three types of $L$-fuzzy $β$-covering-based rough sets

no code implementations13 May 2022 Wei Li, Bin Yang, Junsheng Qiao

In this paper, we mainly construct three types of $L$-fuzzy $\beta$-covering-based rough set models and study the axiom sets, matrix representations and interdependency of these three pairs of $L$-fuzzy $\beta$-covering-based rough approximation operators.

Answer-Me: Multi-Task Open-Vocabulary Visual Question Answering

no code implementations2 May 2022 AJ Piergiovanni, Wei Li, Weicheng Kuo, Mohammad Saffar, Fred Bertsch, Anelia Angelova

We present Answer-Me, a task-aware multi-task framework which unifies a variety of question answering tasks, such as, visual question answering, visual entailment, visual reasoning.

Image Captioning Question Answering +3

HarmoF0: Logarithmic Scale Dilated Convolution For Pitch Estimation

1 code implementation2 May 2022 Weixing Wei, Peilin Li, Yi Yu, Wei Li

Sounds, especially music, contain various harmonic components scattered in the frequency dimension.

Few-Shot Speaker Identification Using Depthwise Separable Convolutional Network with Channel Attention

no code implementations24 Apr 2022 Yanxiong Li, Wucheng Wang, Hao Chen, Wenchang Cao, Wei Li, Qianhua He

Although few-shot learning has attracted much attention from the fields of image and audio classification, few efforts have been made on few-shot speaker identification.

Audio Classification Few-Shot Learning +1

Explore More Guidance: A Task-aware Instruction Network for Sign Language Translation Enhanced with Data Augmentation

1 code implementation Findings (NAACL) 2022 Yong Cao, Wei Li, Xianzhi Li, Min Chen, Guangyong Chen, Long Hu, Zhengdao Li, Hwang Kai

Sign language recognition and translation first uses a recognition module to generate glosses from sign language videos and then employs a translation module to translate glosses into spoken sentences.

Data Augmentation Sign Language Recognition +2

A3CLNN: Spatial, Spectral and Multiscale Attention ConvLSTM Neural Network for Multisource Remote Sensing Data Classification

no code implementations9 Apr 2022 Heng-Chao Li, Wen-Shuai Hu, Wei Li, Jun Li, Qian Du, Antonio Plaza

The problem of effectively exploiting the information multiple data sources has become a relevant but challenging research topic in remote sensing.

Transfer Learning

MS-HLMO: Multi-scale Histogram of Local Main Orientation for Remote Sensing Image Registration

no code implementations1 Apr 2022 Chenzhong Gao, Wei Li, Ran Tao, Qian Du

Considering the characteristics and differences of multi-source remote sensing images, a feature-based registration algorithm named Multi-scale Histogram of Local Main Orientation (MS-HLMO) is proposed.

Image Registration

FindIt: Generalized Localization with Natural Language Queries

no code implementations31 Mar 2022 Weicheng Kuo, Fred Bertsch, Wei Li, AJ Piergiovanni, Mohammad Saffar, Anelia Angelova

We propose FindIt, a simple and versatile framework that unifies a variety of visual grounding and localization tasks including referring expression comprehension, text-based localization, and object detection.

Natural Language Queries object-detection +4

MeMOT: Multi-Object Tracking with Memory

no code implementations CVPR 2022 Jiarui Cai, Mingze Xu, Wei Li, Yuanjun Xiong, Wei Xia, Zhuowen Tu, Stefano Soatto

We propose an online tracking algorithm that performs the object detection and data association under a common framework, capable of linking objects after a long time span.

Association Multi-Object Tracking +2

SepViT: Separable Vision Transformer

1 code implementation29 Mar 2022 Wei Li, Xing Wang, Xin Xia, Jie Wu, Xuefeng Xiao, Min Zheng, Shiping Wen

SepViT helps to carry out the information interaction within and among the windows via a depthwise separable self-attention.

Open-Vocabulary DETR with Conditional Matching

1 code implementation22 Mar 2022 Yuhang Zang, Wei Li, Kaiyang Zhou, Chen Huang, Chen Change Loy

To this end, we propose a novel open-vocabulary detector based on DETR -- hence the name OV-DETR -- which, once trained, can detect any object given its class name or an exemplar image.

Language Modelling object-detection +1

UNIMO-2: End-to-End Unified Vision-Language Grounded Learning

1 code implementation Findings (ACL) 2022 Wei Li, Can Gao, guocheng niu, Xinyan Xiao, Hao liu, Jiachen Liu, Hua Wu, Haifeng Wang

In particular, we propose to conduct grounded learning on both images and texts via a sharing grounded space, which helps bridge unaligned images and texts, and align the visual and textual semantic spaces on different types of corpora.

Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning

1 code implementation ACL 2022 Zixuan Li, Saiping Guan, Xiaolong Jin, Weihua Peng, Yajuan Lyu, Yong Zhu, Long Bai, Wei Li, Jiafeng Guo, Xueqi Cheng

Furthermore, these models are all trained offline, which cannot well adapt to the changes of evolutional patterns from then on.

Efficient universal shuffle attack for visual object tracking

no code implementations14 Mar 2022 Siao Liu, Zhaoyu Chen, Wei Li, Jiwei Zhu, Jiafeng Wang, Wenqiang Zhang, Zhongxue Gan

Recently, adversarial attacks have been applied in visual object tracking to deceive deep trackers by injecting imperceptible perturbations into video frames.

Adversarial Attack Visual Object Tracking

UniVIP: A Unified Framework for Self-Supervised Visual Pre-training

no code implementations CVPR 2022 Zhaowen Li, Yousong Zhu, Fan Yang, Wei Li, Chaoyang Zhao, Yingying Chen, Zhiyang Chen, Jiahao Xie, Liwei Wu, Rui Zhao, Ming Tang, Jinqiao Wang

Furthermore, our method can also exploit single-centric-object dataset such as ImageNet and outperforms BYOL by 2. 5% with the same pre-training epochs in linear probing, and surpass current self-supervised object detection methods on COCO dataset, demonstrating its universality and potential.

Image Classification object-detection +3

Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods

no code implementations10 Mar 2022 Wei Li, Wenhao Wu, Moye Chen, Jiachen Liu, Xinyan Xiao, Hua Wu

In this survey, we provide a systematic overview of the research progress on the faithfulness problem of NLG, including problem analysis, evaluation metrics and optimization methods.

Abstractive Text Summarization Data-to-Text Generation +2

Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels

1 code implementation CVPR 2022 Yuchao Wang, Haochen Wang, Yujun Shen, Jingjing Fei, Wei Li, Guoqiang Jin, Liwei Wu, Rui Zhao, Xinyi Le

A common practice is to select the highly confident predictions as the pseudo ground-truth, but it leads to a problem that most pixels may be left unused due to their unreliability.

Semi-Supervised Semantic Segmentation

A Lightweight and Detector-free 3D Single Object Tracker on Point Clouds

no code implementations8 Mar 2022 Yan Xia, Qiangqiang Wu, Tianyu Yang, Wei Li, Antoni B. Chan, Uwe Stilla

In this paper, we address this issue by explicitly leveraging temporal motion cues and propose DMT, a Detector-free Motion prediction based 3D Tracking network that totally removes the usage of complicated 3D detectors, which is lighter, faster, and more accurate than previous trackers.

motion prediction Object Tracking

DEEPCHORUS: A Hybrid Model of Multi-scale Convolution and Self-attention for Chorus Detection

1 code implementation13 Feb 2022 Qiqi He, Xiaoheng Sun, Yi Yu, Wei Li

Chorus detection is a challenging problem in musical signal processing as the chorus often repeats more than once in popular songs, usually with rich instruments and complex rhythm forms.

TONet: Tone-Octave Network for Singing Melody Extraction from Polyphonic Music

1 code implementation2 Feb 2022 Ke Chen, Shuai Yu, Cheng-i Wang, Wei Li, Taylor Berg-Kirkpatrick, Shlomo Dubnov

In this paper, we propose TONet, a plug-and-play model that improves both tone and octave perceptions by leveraging a novel input representation and a novel network architecture.

Information Retrieval Melody Extraction +2

A Joint Morphological Profiles and Patch Tensor Change Detection for Hyperspectral Imagery

no code implementations20 Jan 2022 Zengfu Hou, Wei Li

Multi-temporal hyperspectral images can be used to detect changed information, which has gradually attracted researchers' attention.

Change Detection Image Reconstruction

DDU-Net: Dual-Decoder-U-Net for Road Extraction Using High-Resolution Remote Sensing Images

no code implementations18 Jan 2022 Ying Wang, Yuexing Peng, Xinran Liu, Wei Li, George C. Alexandropoulos, Junchuan Yu, Daqing Ge, Wei Xiang

Extracting roads from high-resolution remote sensing images (HRSIs) is vital in a wide variety of applications, such as autonomous driving, path planning, and road navigation.

Autonomous Driving

Evolutionary Action Selection for Gradient-based Policy Learning

no code implementations12 Jan 2022 Yan Ma, Tianxing Liu, Bingsheng Wei, Yi Liu, Kang Xu, Wei Li

Evolutionary Algorithms (EAs) and Deep Reinforcement Learning (DRL) have recently been integrated to take the advantage of the both methods for better exploration and exploitation. The evolutionary part in these hybrid methods maintains a population of policy networks. However, existing methods focus on optimizing the parameters of policy network, which is usually high-dimensional and tricky for EA. In this paper, we shift the target of evolution from high-dimensional parameter space to low-dimensional action space. We propose Evolutionary Action Selection-Twin Delayed Deep Deterministic Policy Gradient (EAS-TD3), a novel hybrid method of EA and DRL. In EAS, we focus on optimizing the action chosen by the policy network and attempt to obtain high-quality actions to promote policy learning through an evolutionary algorithm.

Continuous Control

Large-Scale Video Panoptic Segmentation in the Wild: A Benchmark

1 code implementation CVPR 2022 Jiaxu Miao, Xiaohan Wang, Yu Wu, Wei Li, Xu Zhang, Yunchao Wei, Yi Yang

In contrast, our large-scale VIdeo Panoptic Segmentation in the Wild (VIPSeg) dataset provides 3, 536 videos and 84, 750 frames with pixel-level panoptic annotations, covering a wide range of real-world scenarios and categories.

Panoptic Segmentation

PPDL: Predicate Probability Distribution Based Loss for Unbiased Scene Graph Generation

no code implementations CVPR 2022 Wei Li, Haiwei Zhang, Qijie Bai, Guoqing Zhao, Ning Jiang, Xiaojie Yuan

However, the application value of SG on downstream tasks is severely limited by the predicate classification bias, which is caused by long-tailed data and presented as semantic bias of predicted relation predicates.

Graph Generation Predicate Classification +1

Transfer learning of phase transitions in percolation and directed percolation

no code implementations31 Dec 2021 Jianmin Shen, Feiyi Liu, Shiyang Chen, Dian Xu, Xiangna Chen, Shengfeng Deng, Wei Li, Gabor Papp, Chunbin Yang

With the DANN, only a small fraction of input configurations (2d images) needs to be labeled, which is automatically chosen, in order to capture the critical point.

Transfer Learning

Variational Autoencoder with CCA for Audio-Visual Cross-Modal Retrieval

no code implementations5 Dec 2021 Jiwei Zhang, Yi Yu, Suhua Tang, Jianming Wu, Wei Li

On the one hand, audio encoder and visual encoder separately encode audio data and visual data into two different latent spaces.

Cross-Modal Retrieval Information Retrieval +1

FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows

3 code implementations15 Nov 2021 Jiawei Yu, Ye Zheng, Xiang Wang, Wei Li, Yushuang Wu, Rui Zhao, Liwei Wu

However, current methods can not effectively map image features to a tractable base distribution and ignore the relationship between local and global features which are important to identify anomalies.

Ranked #5 on Anomaly Detection on MVTec AD (using extra training data)

Unsupervised Anomaly Detection Weakly Supervised Defect Detection

Deep Learning for UAV-based Object Detection and Tracking: A Survey

no code implementations25 Oct 2021 Xin Wu, Wei Li, Danfeng Hong, Ran Tao, Qian Du

Owing to effective and flexible data acquisition, unmanned aerial vehicle (UAV) has recently become a hotspot across the fields of computer vision (CV) and remote sensing (RS).

Management object-detection +2

SgSum: Transforming Multi-document Summarization into Sub-graph Selection

1 code implementation25 Oct 2021 Moye Chen, Wei Li, Jiachen Liu, Xinyan Xiao, Hua Wu, Haifeng Wang

Comparing with traditional methods, our method has two main advantages: (1) the relations between sentences are captured by modeling both the graph structure of the whole document set and the candidate sub-graphs; (2) directly outputs an integrate summary in the form of sub-graph which is more informative and coherent.

Document Summarization Multi-Document Summarization

Learning UI Navigation through Demonstrations composed of Macro Actions

no code implementations16 Oct 2021 Wei Li

The action space is restricted to the UI elements plus a few global actions.

Optical Character Recognition

MC-LCR: Multi-modal contrastive classification by locally correlated representations for effective face forgery detection

no code implementations7 Oct 2021 Gaojian Wang, Qian Jiang, Xin Jin, Wei Li, Xiaohui Cui

Moreover, we make a key observation that subtle forgery artifacts can be further exposed in the patch-wise phase and amplitude spectrum and exhibit different clues.

Referring Self-supervised Learning on 3D Point Cloud

no code implementations29 Sep 2021 Runnan Chen, Xinge Zhu, Nenglun Chen, Dawei Wang, Wei Li, Yuexin Ma, Ruigang Yang, Wenping Wang

In this paper, we study a new problem named Referring Self-supervised Learning (RSL) on 3D scene understanding: Given the 3D synthetic models with labels and the unlabeled 3D real scene scans, our goal is to distinguish the identical semantic objects on an unseen scene according to the referring synthetic 3D models.

Scene Understanding Self-Supervised Learning

A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection

1 code implementation27 Sep 2021 Zhanchao Huang, Wei Li, Xiang-Gen Xia, Ran Tao

Specifically, an anchor-free object-adaptation label assignment (OLA) strategy is presented to define the positive candidates based on two-dimensional (2-D) oriented Gaussian heatmaps, which reflect the shape and direction features of arbitrary-oriented objects.

object-detection Object Detection In Aerial Images

CENN: Conservative energy method based on neural networks with subdomains for solving variational problems involving heterogeneous and complex geometries

1 code implementation25 Sep 2021 Yizheng Wang, Jia Sun, Wei Li, Zaiyuan Lu, Yinghua Liu

The advantage of the proposed method is higher efficiency, more accurate, and less hyperparameters than the strong form PINN with subdomains.

Tied & Reduced RNN-T Decoder

no code implementations15 Sep 2021 Rami Botros, Tara N. Sainath, Robert David, Emmanuel Guzman, Wei Li, Yanzhang He

Previous works on the Recurrent Neural Network-Transducer (RNN-T) models have shown that, under some conditions, it is possible to simplify its prediction network with little or no loss in recognition accuracy (arXiv:2003. 07705 [eess. AS], [2], arXiv:2012. 06749 [cs. CL]).

Language Modelling

Musical Tempo Estimation Using a Multi-scale Network

no code implementations3 Sep 2021 Xiaoheng Sun, Qiqi He, Yongwei Gao, Wei Li

Recently, some single-step systems without onset detection have shown their effectiveness in automatic musical tempo estimation.

ASAT: Adaptively Scaled Adversarial Training in Time Series

no code implementations20 Aug 2021 Zhiyuan Zhang, Wei Li, Ruihan Bao, Keiko Harimoto, Yunfang Wu, Xu sun

Besides the security concerns of potential adversarial examples, adversarial training can also improve the generalization ability of neural networks, train robust neural networks, and provide interpretability for neural networks.

Adversarial Robustness Time Series +1

Multi defect detection and analysis of electron microscopy images with deep learning

no code implementations19 Aug 2021 Mingren Shen, Guanzhao Li, Dongxia Wu, YuHan Liu, Jacob Greaves, Wei Hao, Nathaniel J. Krakauer, Leah Krudy, Jacob Perez, Varun Sreenivasan, Bryan Sanchez, Oigimer Torres, Wei Li, Kevin Field, Dane Morgan

Electron microscopy is widely used to explore defects in crystal structures, but human detecting of defects is often time-consuming, error-prone, and unreliable, and is not scalable to large numbers of images or real-time analysis.

Defect Detection

Semantic Concentration for Domain Adaptation

1 code implementation ICCV 2021 Shuang Li, Mixue Xie, Fangrui Lv, Chi Harold Liu, Jian Liang, Chen Qin, Wei Li

To tackle this issue, we propose Semantic Concentration for Domain Adaptation (SCDA), which encourages the model to concentrate on the most principal features via the pair-wise adversarial alignment of prediction distributions.

Domain Adaptation

Wavelet-Based Network For High Dynamic Range Imaging

no code implementations3 Aug 2021 Tianhong Dai, Wei Li, Xilei Cao, Jianzhuang Liu, Xu Jia, Ales Leonardis, Youliang Yan, Shanxin Yuan

The frequency-guided upsampling module reconstructs details from multiple frequency-specific components with rich details.

Optical Flow Estimation

A Data-driven Explainable Case-based Reasoning Approach for Financial Risk Detection

no code implementations19 Jul 2021 Wei Li, Florentina Paraschiv, Georgios Sermpinis

The rapid development of artificial intelligence methods contributes to their wide applications for forecasting various financial risks in recent years.

Residual Attention Based Network for Automatic Classification of Phonation Modes

no code implementations18 Jul 2021 Xiaoheng Sun, Yiliang Jiang, Wei Li

Phonation mode is an essential characteristic of singing style as well as an important expression of performance.

Classification Feature Engineering +3

Video 3D Sampling for Self-supervised Representation Learning

no code implementations8 Jul 2021 Wei Li, Dezhao Luo, Bo Fang, Yu Zhou, Weiping Wang

As a result, we can leverage the spatial information (the size of objects), temporal information (the direction and magnitude of motions) as our learning target.

Action Recognition Representation Learning +2

Semi-TCL: Semi-Supervised Track Contrastive Representation Learning

no code implementations6 Jul 2021 Wei Li, Yuanjun Xiong, Shuo Yang, Mingze Xu, Yongxin Wang, Wei Xia

We design a new instance-to-track matching objective to learn appearance embedding that compares a candidate detection to the embedding of the tracks persisted in the tracker.

Multiple Object Tracking Representation Learning

Toward Less Hidden Cost of Code Completion with Acceptance and Ranking Models

no code implementations26 Jun 2021 Jingxuan Li, Rui Huang, Wei Li, Kai Yao, Weiguo Tan

We integrate this ranking scheme with two frequency models and a GPT-2 styled language model, along with the acceptance model to yield 27. 80% and 37. 64% increase in TOP1 and TOP5 accuracy, respectively.

Code Completion Language Modelling

MST: Masked Self-Supervised Transformer for Visual Representation

no code implementations NeurIPS 2021 Zhaowen Li, Zhiyang Chen, Fan Yang, Wei Li, Yousong Zhu, Chaoyang Zhao, Rui Deng, Liwei Wu, Rui Zhao, Ming Tang, Jinqiao Wang

More importantly, the masked tokens together with the remaining tokens are further recovered by a global image decoder, which preserves the spatial information of the image and is more friendly to the downstream dense prediction tasks.

Language Modelling Masked Language Modeling +3

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.

Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs

no code implementations ACL 2021 Zixuan Li, Xiaolong Jin, Saiping Guan, Wei Li, Jiafeng Guo, Yuanzhuo Wang, Xueqi Cheng

Specifically, at the clue searching stage, CluSTeR learns a beam search policy via reinforcement learning (RL) to induce multiple clues from historical facts.

Knowledge Graphs

DiaKG: an Annotated Diabetes Dataset for Medical Knowledge Graph Construction

1 code implementation31 May 2021 Dejie Chang, Mosha Chen, Chaozhen Liu, LiPing Liu, Dongdong Li, Wei Li, Fei Kong, Bangchang Liu, Xiaobin Luo, Ji Qi, Qiao Jin, Bin Xu

In order to accelerate the research for domain-specific knowledge graphs in the medical domain, we introduce DiaKG, a high-quality Chinese dataset for Diabetes knowledge graph, which contains 22, 050 entities and 6, 890 relations in total.

graph construction Knowledge Graphs +3

BASS: Boosting Abstractive Summarization with Unified Semantic Graph

no code implementations ACL 2021 Wenhao Wu, Wei Li, Xinyan Xiao, Jiachen Liu, Ziqiang Cao, Sujian Li, Hua Wu, Haifeng Wang

Abstractive summarization for long-document or multi-document remains challenging for the Seq2Seq architecture, as Seq2Seq is not good at analyzing long-distance relations in text.

Abstractive Text Summarization Document Summarization +2

MUSE: Multi-faceted Attention for Signed Network Embedding

no code implementations29 Apr 2021 Dengcheng Yan, Youwen Zhang, Wei Li, Yiwen Zhang

Signed network embedding is an approach to learn low-dimensional representations of nodes in signed networks with both positive and negative links, which facilitates downstream tasks such as link prediction with general data mining frameworks.

Link Prediction Network Embedding

Multi-scale PIIFD for Registration of Multi-source Remote Sensing Images

1 code implementation26 Apr 2021 Chenzhong Gao, Wei Li

This paper aims at providing multi-source remote sensing images registered in geometric space for image fusion.

Image Registration

Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning

1 code implementation21 Apr 2021 Zixuan Li, Xiaolong Jin, Wei Li, Saiping Guan, Jiafeng Guo, HuaWei Shen, Yuanzhuo Wang, Xueqi Cheng

To capture these properties effectively and efficiently, we propose a novel Recurrent Evolution network based on Graph Convolution Network (GCN), called RE-GCN, which learns the evolutional representations of entities and relations at each timestamp by modeling the KG sequence recurrently.

Representation Learning

ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion

1 code implementation19 Apr 2021 Yaqi Xia, Yan Xia, Wei Li, Rui Song, Kailang Cao, Uwe Stilla

We tackle the problem of object completion from point clouds and propose a novel point cloud completion network employing an Asymmetrical Siamese Feature Matching strategy, termed as ASFM-Net.

Point Cloud Completion

Discover the Hidden Attack Path in Multi-domain Cyberspace Based on Reinforcement Learning

no code implementations15 Apr 2021 Lei Zhang, Wei Bai, Wei Li, Shiming Xia, Qibin Zheng

To achieve these results, we pose discovering attack paths as a Reinforcement Learning (RL) problem and train an agent to discover multi-domain cyberspace attack paths.

reinforcement Learning

Dynamic Domain Adaptation for Efficient Inference

1 code implementation CVPR 2021 Shuang Li, Jinming Zhang, Wenxuan Ma, Chi Harold Liu, Wei Li

Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain by reducing the cross-domain distribution discrepancy.

Domain Generalization

Transferable Semantic Augmentation for Domain Adaptation

1 code implementation CVPR 2021 Shuang Li, Mixue Xie, Kaixiong Gong, Chi Harold Liu, Yulin Wang, Wei Li

To remedy this, we propose a Transferable Semantic Augmentation (TSA) approach to enhance the classifier adaptation ability through implicitly generating source features towards target semantics.

Domain Adaptation

Path-specific Underwater Acoustic Channel Tracking and its Application in Passive Time Reversal Mirror

no code implementations1 Mar 2021 Xiuqing Li, Wei Li, Xinlin Yi, Qihang Huang, Yuhang Wang, Chenzhe Ye

With the path-specific parameters obtained by the proposed channel tracking, the proposed PTRM can not only match the time dispersion as conventional PTRM, but also the doubly-spread channel, since the path-specific delay and Doppler scaler factor can help to match the channel in both time and frequency domain.

Dynamic Underwater Acoustic Channel Tracking for Correlated Rapidly Time-varying Channels

no code implementations1 Mar 2021 Qihang Huang, Wei Li, Weicheng Zhan, Yuhang Wang, Rongrong Guo

A model based on the underwater acoustic channel's correlation can be used as the state-space model in the Kalman filter to improve the underwater acoustic channel tracking compared that without a model.

Modelling brain based on canonical ensemble with functional MRI: A thermodynamic exploration on neural system

no code implementations26 Feb 2021 Chenxi Zhou, Bin Yang, Wenliang Fan, Wei Li

(3) The detection of neural disease was demonstrated to be benefit from thermodynamic model, implying the immense potential of thermodynamics in auxiliary diagnosis.

A Universal Urbach Rule for Disordered Organic Semiconductors

no code implementations25 Feb 2021 Christina Kaiser, Oskar J. Sandberg, Nasim Zarrabi, Wei Li, Paul Meredith, Ardalan Armin

A simple model is presented that explains absorption line-shapes of disordered systems, and we also provide a strategy to determine the excitonic disorder energy.

Optics Disordered Systems and Neural Networks

Do Transformer Modifications Transfer Across Implementations and Applications?

1 code implementation EMNLP 2021 Sharan Narang, Hyung Won Chung, Yi Tay, William Fedus, Thibault Fevry, Michael Matena, Karishma Malkan, Noah Fiedel, Noam Shazeer, Zhenzhong Lan, Yanqi Zhou, Wei Li, Nan Ding, Jake Marcus, Adam Roberts, Colin Raffel

The research community has proposed copious modifications to the Transformer architecture since it was introduced over three years ago, relatively few of which have seen widespread adoption.

Significant Inverse Magnetocaloric Effect induced by Quantum Criticality

no code implementations17 Feb 2021 Tao Liu, Xin-Yang Liu, Yuan Gao, Hai Jin, Jun He, Xian-Lei Sheng, Wentao Jin, Ziyu Chen, Wei Li

Strong fluctuations in the low-$T$ quantum critical regime can give rise to a large thermal entropy change and thus significant cooling effect when approaching the QCP.

Strongly Correlated Electrons

LEAD: LiDAR Extender for Autonomous Driving

no code implementations16 Feb 2021 Jianing Zhang, Wei Li, Honggang Gou, Lu Fang, Ruigang Yang

In this paper, we propose LEAD, i. e., LiDAR Extender for Autonomous Driving, to extend the MEMS LiDAR by coupled image w. r. t both FoV and range.

Autonomous Driving Depth Completion +1

Phase Diagram of Triangular Lattice Quantum Ising Model under External Field

no code implementations27 Jan 2021 Yuan Da Liao, Han Li, Zheng Yan, Hao-Tian Wei, Wei Li, Yang Qi, Zi Yang Meng

Quantum Ising model on a triangular lattice hosts a finite temperature Berezinskii-Kosterlitz-Thouless (BKT) phase with emergent U(1) symmetry, and it will transit into an up-up-down (UUD) phase with $C_3$ symmetry breaking upon an infinitesimal external field along the longitudinal direction, but the overall phase diagram spanned by the axes of external field and temperature remains opaque due to the lack of systematic invesitgations with controlled methodologies.

Strongly Correlated Electrons Statistical Mechanics

Correlated interaction effects in three-dimensional semi-Dirac semimetal

no code implementations14 Jan 2021 Jing-Rong Wang, Wei Li, Chang-Jin Zhang

The physical essences of the quantum critical points are determined by analyzing the susceptibility exponents for all of the source terms in particle-hole and particle-particle channels.

Strongly Correlated Electrons Materials Science

Day-ahead electricity price prediction applying hybrid models of LSTM-based deep learning methods and feature selection algorithms under consideration of market coupling

no code implementations13 Jan 2021 Wei Li, Denis Mike Becker

In the context of trade liberalisation and market harmonisation in the European markets, accurate price forecasting becomes difficult for electricity market participants to obtain because electricity forecasting requires the consideration of features from ever-growing coupling markets.

Feature Importance Time Series

A Simple Feature Augmentation for Domain Generalization

no code implementations ICCV 2021 Pan Li, Da Li, Wei Li, Shaogang Gong, Yanwei Fu, Timothy M. Hospedales

The topical domain generalization (DG) problem asks trained models to perform well on an unseen target domain with different data statistics from the source training domains.

Data Augmentation Domain Generalization

Detection Booster Training: A detection booster training method for improving the accuracy of classifiers.

no code implementations1 Jan 2021 Ali Ghobadzadeh, Deepak Sridhar, Juwei Lu, Wei Li

In this paper, we probe this direction by deriving a relationship between the estimation of unknown parameters of the probability density function (pdf) of input data and classification accuracy.

Face Recognition Image Classification

Rethinking Graph Neural Networks for Graph Coloring

no code implementations1 Jan 2021 Wei Li, Ruxuan Li, Yuzhe ma, Siu On Chan, Bei Yu

To characterize the power of GNNs for the graph coloring problem, we first formalize the discrimination power of GNNs as the capability to assign nodes different colors.

Gradient Descent Averaging and Primal-dual Averaging for Strongly Convex Optimization

no code implementations29 Dec 2020 Wei Tao, Wei Li, Zhisong Pan, Qing Tao

In order to remove this factor, we first develop gradient descent averaging (GDA), which is a general projection-based dual averaging algorithm in the strongly convex setting.

CodeVIO: Visual-Inertial Odometry with Learned Optimizable Dense Depth

no code implementations18 Dec 2020 Xingxing Zuo, Nathaniel Merrill, Wei Li, Yong liu, Marc Pollefeys, Guoquan Huang

In this work, we present a lightweight, tightly-coupled deep depth network and visual-inertial odometry (VIO) system, which can provide accurate state estimates and dense depth maps of the immediate surroundings.

Depth Estimation Depth Prediction +1

Decoupled Self Attention for Accurate One Stage Object Detection

1 code implementation14 Dec 2020 Kehe WU, Zuge Chen, Qi Ma, Xiaoliang Zhang, Wei Li

When DSA module and object confidence task are applied in RetinaNet together, the detection performances based on ResNet50 and ResNet101 can be increased by 1. 0% AP and 1. 4% AP respectively.

object-detection Object Detection +1

Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks

1 code implementation CVPR 2021 Xiaoxiao Long, Lingjie Liu, Wei Li, Christian Theobalt, Wenping Wang

We present a novel method for multi-view depth estimation from a single video, which is a critical task in various applications, such as perception, reconstruction and robot navigation.

Depth Estimation Robot Navigation

SMOT: Single-Shot Multi Object Tracking

1 code implementation30 Oct 2020 Wei Li, Yuanjun Xiong, Shuo Yang, Siqi Deng, Wei Xia

We combine this scheme with SSD detectors by proposing a novel tracking anchor assignment module.

Multi-Object Tracking

Hidden Markov Models for Pipeline Damage Detection Using Piezoelectric Transducers

no code implementations30 Sep 2020 Mingchi Zhang, Xuemin Chen, Wei Li

However, the negative pressure waves or guided stress waves may not be easily detected with environmental interference, e. g., the oil and gas pipelines in offshore environment.

VoiceFilter-Lite: Streaming Targeted Voice Separation for On-Device Speech Recognition

1 code implementation9 Sep 2020 Quan Wang, Ignacio Lopez Moreno, Mert Saglam, Kevin Wilson, Alan Chiao, Renjie Liu, Yanzhang He, Wei Li, Jason Pelecanos, Marily Nika, Alexander Gruenstein

We introduce VoiceFilter-Lite, a single-channel source separation model that runs on the device to preserve only the speech signals from a target user, as part of a streaming speech recognition system.

speech-recognition Speech Recognition

Temporal optical neurons for serial deep learning

no code implementations4 Sep 2020 Zhixing Lin, Shuqian Sun, Jose Azana, Wei Li, Ninghua Zhu, Ming Li

This concept represents a novel one-dimensional realization of artificial neural networks, enabling an efficient application of optical deep learning methods to the analysis and processing of serial data signals, while offering a new overall perspective for the temporal signal processing.

Adversarial Privacy Preserving Graph Embedding against Inference Attack

1 code implementation30 Aug 2020 Kaiyang Li, Guangchun Luo, Yang Ye, Wei Li, Shihao Ji, Zhipeng Cai

In this paper, we propose Adversarial Privacy Graph Embedding (APGE), a graph adversarial training framework that integrates the disentangling and purging mechanisms to remove users' private information from learned node representations.

Graph Embedding Inference Attack +4

Parallel Rescoring with Transformer for Streaming On-Device Speech Recognition

no code implementations30 Aug 2020 Wei Li, James Qin, Chung-Cheng Chiu, Ruoming Pang, Yanzhang He

The 2nd-pass model plays a key role in the quality improvement of the end-to-end model to surpass the conventional model.

speech-recognition Speech Recognition

Transformer based Multilingual document Embedding model

no code implementations19 Aug 2020 Wei Li, Brian Mak

One of the current state-of-the-art multilingual document embedding model LASER is based on the bidirectional LSTM neural machine translation model.

Document Embedding Machine Translation +2

Exploring the Impacts from Datasets to Monocular Depth Estimation (MDE) Models with MineNavi

no code implementations19 Aug 2020 Xiangtong Wang, Binbin Liang, Menglong Yang, Wei Li

Current computer vision tasks based on deep learning require a huge amount of data with annotations for model training or testing, especially in some dense estimation tasks, such as optical flow segmentation and depth estimation.

Monocular Depth Estimation Optical Flow Estimation +2

TEAM: We Need More Powerful Adversarial Examples for DNNs

1 code implementation31 Jul 2020 Ya-guan Qian, Ximin Zhang, Bin Wang, Wei Li, Zhaoquan Gu, Haijiang Wang, Wassim Swaileh

In this paper, we propose a novel method (TEAM, Taylor Expansion-Based Adversarial Methods) to generate more powerful adversarial examples than previous methods.

DVI: Depth Guided Video Inpainting for Autonomous Driving

2 code implementations ECCV 2020 Miao Liao, Feixiang Lu, Dingfu Zhou, Sibo Zhang, Wei Li, Ruigang Yang

To get clear street-view and photo-realistic simulation in autonomous driving, we present an automatic video inpainting algorithm that can remove traffic agents from videos and synthesize missing regions with the guidance of depth/point cloud.

Autonomous Driving Image Inpainting +2