Search Results for author: Wei Wu

Found 157 papers, 58 papers with code

Large-Scale Relation Learning for Question Answering over Knowledge Bases with Pre-trained Language Models

1 code implementation EMNLP 2021 Yuanmeng Yan, Rumei Li, Sirui Wang, Hongzhi Zhang, Zan Daoguang, Fuzheng Zhang, Wei Wu, Weiran Xu

The key challenge of question answering over knowledge bases (KBQA) is the inconsistency between the natural language questions and the reasoning paths in the knowledge base (KB).

Question Answering Relation Extraction

Task-Oriented Clustering for Dialogues

1 code implementation Findings (EMNLP) 2021 Chenxu Lv, Hengtong Lu, Shuyu Lei, Huixing Jiang, Wei Wu, Caixia Yuan, Xiaojie Wang

A reliable clustering algorithm for task-oriented dialogues can help developer analysis and define dialogue tasks efficiently.

Representation Learning Text Clustering

Robust Lottery Tickets for Pre-trained Language Models

1 code implementation ACL 2022 Rui Zheng, Bao Rong, Yuhao Zhou, Di Liang, Sirui Wang, Wei Wu, Tao Gui, Qi Zhang, Xuanjing Huang

Recent works on Lottery Ticket Hypothesis have shown that pre-trained language models (PLMs) contain smaller matching subnetworks(winning tickets) which are capable of reaching accuracy comparable to the original models.

Adversarial Robustness

An Effective and Efficient Entity Alignment Decoding Algorithm via Third-Order Tensor Isomorphism

no code implementations ACL 2022 Xin Mao, Meirong Ma, Hao Yuan, Jianchao Zhu, ZongYu Wang, Rui Xie, Wei Wu, Man Lan

Entity alignment (EA) aims to discover the equivalent entity pairs between KGs, which is a crucial step for integrating multi-source KGs. For a long time, most researchers have regarded EA as a pure graph representation learning task and focused on improving graph encoders while paying little attention to the decoding process. In this paper, we propose an effective and efficient EA Decoding Algorithm via Third-order Tensor Isomorphism (DATTI). Specifically, we derive two sets of isomorphism equations: (1) Adjacency tensor isomorphism equations and (2) Gramian tensor isomorphism equations. By combining these equations, DATTI could effectively utilize the adjacency and inner correlation isomorphisms of KGs to enhance the decoding process of EA. Extensive experiments on public datasets indicate that our decoding algorithm can deliver significant performance improvements even on the most advanced EA methods, while the extra required time is less than 3 seconds.

Entity Alignment Graph Representation Learning

CQG: A Simple and Effective Controlled Generation Framework for Multi-hop Question Generation

1 code implementation ACL 2022 Zichu Fei, Qi Zhang, Tao Gui, Di Liang, Sirui Wang, Wei Wu, Xuanjing Huang

CQG employs a simple method to generate the multi-hop questions that contain key entities in multi-hop reasoning chains, which ensure the complexity and quality of the questions.

Question Generation

Perceptual Quality Assessment for Fine-Grained Compressed Images

no code implementations8 Jun 2022 ZiCheng Zhang, Wei Sun, Wei Wu, Ying Chen, Xiongkuo Min, Guangtao Zhai

Nowadays, the mainstream full-reference (FR) metrics are effective to predict the quality of compressed images at coarse-grained levels (the bit rates differences of compressed images are obvious), however, they may perform poorly for fine-grained compressed images whose bit rates differences are quite subtle.

Image Compression Image Quality Assessment

AutoDisc: Automatic Distillation Schedule for Large Language Model Compression

no code implementations29 May 2022 Chen Zhang, Yang Yang, Qifan Wang, Jiahao Liu, Jingang Wang, Wei Wu, Dawei Song

As a connection, the scale and the performance of the teacher assistant is crucial for transferring the knowledge from the teacher to the student.

Knowledge Distillation Language Modelling +1

Ensemble Multi-Relational Graph Neural Networks

no code implementations24 May 2022 Yuling Wang, Hao Xu, Yanhua Yu, Mengdi Zhang, Zhenhao Li, Yuji Yang, Wei Wu

This EMR optimization objective is able to derive an iterative updating rule, which can be formalized as an ensemble message passing (EnMP) layer with multi-relations.

Graph Adaptive Semantic Transfer for Cross-domain Sentiment Classification

no code implementations18 May 2022 Kai Zhang, Qi Liu, Zhenya Huang, Mingyue Cheng, Kun Zhang, Mengdi Zhang, Wei Wu, Enhong Chen

Existing studies in this task attach more attention to the sequence modeling of sentences while largely ignoring the rich domain-invariant semantics embedded in graph structures (i. e., the part-of-speech tags and dependency relations).

Classification Graph Attention +3

Making Pre-trained Language Models Good Long-tailed Learners

no code implementations11 May 2022 Chen Zhang, Lei Ren, Jingang Wang, Wei Wu, Dawei Song

Prompt-tuning has shown appealing performance in few-shot classification by virtue of its capability in effectively exploiting pre-trained knowledge.

Classification

Cross Domain Object Detection by Target-Perceived Dual Branch Distillation

1 code implementation CVPR 2022 Mengzhe He, Yali Wang, Jiaxi Wu, Yiru Wang, Hanqing Li, Bo Li, Weihao Gan, Wei Wu, Yu Qiao

It can adaptively enhance source detector to perceive objects in a target image, by leveraging target proposal contexts from iterative cross-attention.

object-detection Object Detection

Locality Sensitive Hashing for Structured Data: A Survey

no code implementations24 Apr 2022 Wei Wu, Bin Li

Data similarity (or distance) computation is a fundamental research topic which fosters a variety of similarity-based machine learning and data mining applications.

GNN-encoder: Learning a Dual-encoder Architecture via Graph Neural Networks for Passage Retrieval

no code implementations18 Apr 2022 Jiduan Liu, Jiahao Liu, Yang Yang, Jingang Wang, Wei Wu, Dongyan Zhao, Rui Yan

To enhance the performance of dense retrieval models without loss of efficiency, we propose a GNN-encoder model in which query (passage) information is fused into passage (query) representations via graph neural networks that are constructed by queries and their top retrieved passages.

Passage Retrieval

Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection

no code implementations CVPR 2022 Jiaxi Wu, Jiaxin Chen, Mengzhe He, Yiru Wang, Bo Li, Bingqi Ma, Weihao Gan, Wei Wu, Yali Wang, Di Huang

Specifically, TRKP adopts the teacher-student framework, where the multi-head teacher network is built to extract knowledge from labeled source domains and guide the student network to learn detectors in unlabeled target domain.

Disentanglement Domain Adaptation +2

Learning to Express in Knowledge-Grounded Conversation

no code implementations NeurIPS 2021 Xueliang Zhao, Tingchen Fu, Chongyang Tao, Wei Wu, Dongyan Zhao, Rui Yan

Grounding dialogue generation by extra knowledge has shown great potentials towards building a system capable of replying with knowledgeable and engaging responses.

Dialogue Generation

TANet: Thread-Aware Pretraining for Abstractive Conversational Summarization

no code implementations9 Apr 2022 Ze Yang, Liran Wang, Zhoujin Tian, Wei Wu, Zhoujun Li

Another is that applying the existing pre-trained models to this task is tricky because of the structural dependence within the conversation and its informal expression, etc.

Domain-Oriented Prefix-Tuning: Towards Efficient and Generalizable Fine-tuning for Zero-Shot Dialogue Summarization

1 code implementation9 Apr 2022 Lulu Zhao, Fujia Zheng, Weihao Zeng, Keqing He, Weiran Xu, Huixing Jiang, Wei Wu, Yanan Wu

The most advanced abstractive dialogue summarizers lack generalization ability on new domains and the existing researches for domain adaptation in summarization generally rely on large-scale pre-trainings.

Domain Adaptation

Unsupervised Learning of Accurate Siamese Tracking

1 code implementation CVPR 2022 Qiuhong Shen, Lei Qiao, Jinyang Guo, Peixia Li, Xin Li, Bo Li, Weitao Feng, Weihao Gan, Wei Wu, Wanli Ouyang

As unlimited self-supervision signals can be obtained by tracking a video along a cycle in time, we investigate evolving a Siamese tracker by tracking videos forward-backward.

Visual Object Tracking

Learning What You Need from What You Did: Product Taxonomy Expansion with User Behaviors Supervision

1 code implementation28 Mar 2022 Sijie Cheng, Zhouhong Gu, Bang Liu, Rui Xie, Wei Wu, Yanghua Xiao

Specifically, i) to fully exploit user behavioral information, we extract candidate hyponymy relations that match user interests from query-click concepts; ii) to enhance the semantic information of new concepts and better detect hyponymy relations, we model concepts and relations through both user-generated content and structural information in existing taxonomies and user click logs, by leveraging Pre-trained Language Models and Graph Neural Network combined with Contrastive Learning; iii) to reduce the cost of dataset construction and overcome data skews, we construct a high-quality and balanced training dataset from existing taxonomy with no supervision.

Contrastive Learning

Data-Driven, Soft Alignment of Functional Data Using Shapes and Landmarks

1 code implementation22 Mar 2022 Xiaoyang Guo, Wei Wu, Anuj Srivastava

Alignment or registration of functions is a fundamental problem in statistical analysis of functions and shapes.

ActFormer: A GAN Transformer Framework towards General Action-Conditioned 3D Human Motion Generation

no code implementations15 Mar 2022 Ziyang Song, Dongliang Wang, Nan Jiang, Zhicheng Fang, Chenjing Ding, Weihao Gan, Wei Wu

Such a design combines the strong spatio-temporal representation capacity of Transformer, superiority in generative modeling of GAN, and inherent temporal correlations from latent prior.

Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking

no code implementations10 Mar 2022 BoYu Chen, Peixia Li, Lei Bai, Lei Qiao, Qiuhong Shen, Bo Li, Weihao Gan, Wei Wu, Wanli Ouyang

Exploiting a general-purpose neural architecture to replace hand-wired designs or inductive biases has recently drawn extensive interest.

Visual Object Tracking

InstructionNER: A Multi-Task Instruction-Based Generative Framework for Few-shot NER

no code implementations8 Mar 2022 LiWen Wang, Rumei Li, Yang Yan, Yuanmeng Yan, Sirui Wang, Wei Wu, Weiran Xu

Recently, prompt-based methods have achieved significant performance in few-shot learning scenarios by bridging the gap between language model pre-training and fine-tuning for downstream tasks.

Entity Typing Few-Shot Learning +6

Graph Neural Network-Based Scheduling for Multi-UAV-Enabled Communications in D2D Networks

no code implementations15 Feb 2022 Pei Li, Lingyi Wang, Wei Wu, Fuhui Zhou, Baoyun Wang, Qihui Wu

In this paper, we propose a novel graph neural networks (GNN) based approach that can map the considered system into a specific graph structure and achieve the optimal solution in a low complexity manner.

Learning Video Representations of Human Motion From Synthetic Data

no code implementations CVPR 2022 Xi Guo, Wei Wu, Dongliang Wang, Jing Su, Haisheng Su, Weihao Gan, Jian Huang, Qin Yang

In this paper, we take an early step towards video representation learning of human actions with the help of largescale synthetic videos, particularly for human motion representation enhancement.

Action Recognition Contrastive Learning +2

Pay More Attention to History: A Context Modeling Strategy for Conversational Text-to-SQL

no code implementations16 Dec 2021 Yuntao Li, Hanchu Zhang, Yutian Li, Sirui Wang, Wei Wu, Yan Zhang

Conversational text-to-SQL aims at converting multi-turn natural language queries into their corresponding SQL representations.

Semantic Parsing Text-To-Sql

VIRT: Improving Representation-based Models for Text Matching through Virtual Interaction

no code implementations8 Dec 2021 Dan Li, Yang Yang, Hongyin Tang, Jingang Wang, Tong Xu, Wei Wu, Enhong Chen

With the booming of pre-trained transformers, representation-based models based on Siamese transformer encoders have become mainstream techniques for efficient text matching.

Text Matching

Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection

no code implementations7 Dec 2021 Shoubin Yu, Zhongyin Zhao, Haoshu Fang, Andong Deng, Haisheng Su, Dongliang Wang, Weihao Gan, Cewu Lu, Wei Wu

Different from pixel-based anomaly detection methods, pose-based methods utilize highly-structured skeleton data, which decreases the computational burden and also avoids the negative impact of background noise.

Anomaly Detection In Surveillance Videos Optical Flow Estimation

Calibrated Feature Decomposition for Generalizable Person Re-Identification

1 code implementation27 Nov 2021 Kecheng Zheng, Jiawei Liu, Wei Wu, Liang Li, Zheng-Jun Zha

The calibrated person representation is subtly decomposed into the identity-relevant feature, domain feature, and the remaining entangled one.

Domain Generalization Generalizable Person Re-identification

TODSum: Task-Oriented Dialogue Summarization with State Tracking

no code implementations25 Oct 2021 Lulu Zhao, Fujia Zheng, Keqing He, Weihao Zeng, Yuejie Lei, Huixing Jiang, Wei Wu, Weiran Xu, Jun Guo, Fanyu Meng

Previous dialogue summarization datasets mainly focus on open-domain chitchat dialogues, while summarization datasets for the broadly used task-oriented dialogue haven't been explored yet.

Popularity Bias Is Not Always Evil: Disentangling Benign and Harmful Bias for Recommendation

no code implementations16 Sep 2021 Zihao Zhao, Jiawei Chen, Sheng Zhou, Xiangnan He, Xuezhi Cao, Fuzheng Zhang, Wei Wu

To sufficiently exploit such important information for recommendation, it is essential to disentangle the benign popularity bias caused by item quality from the harmful popularity bias caused by conformity.

Recommendation Systems

DisenKGAT: Knowledge Graph Embedding with Disentangled Graph Attention Network

2 code implementations22 Aug 2021 Junkang Wu, Wentao Shi, Xuezhi Cao, Jiawei Chen, Wenqiang Lei, Fuzheng Zhang, Wei Wu, Xiangnan He

Knowledge graph completion (KGC) has become a focus of attention across deep learning community owing to its excellent contribution to numerous downstream tasks.

Disentanglement Graph Attention +2

Response Ranking with Multi-types of Deep Interactive Representations in Retrieval-based Dialogues

1 code implementation ACM Transactions on Information Systems 2021 Ruijian Xu, Chongyang Tao, Jiazhan Feng, Wei Wu, Rui Yan, Dongyan Zhao

To tackle these challenges, we propose a representation[K]-interaction[L]-matching framework that explores multiple types of deep interactive representations to build context-response matching models for response selection.

Conversational Response Selection

The impact of model risk on dynamic portfolio selection under multi-period mean-standard-deviation criterion

no code implementations5 Aug 2021 Spiridon Penev, Pavel V. Shevchenko, Wei Wu

In the worst case scenario, the optimal robust strategy can be obtained in a semi-analytical form as a solution of a system of nonlinear equations.

Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021

no code implementations27 Jul 2021 Haisheng Su, Peiqin Zhuang, Yukun Li, Dongliang Wang, Weihao Gan, Wei Wu, Yu Qiao

This technical report presents an overview of our solution used in the submission to 2021 HACS Temporal Action Localization Challenge on both Supervised Learning Track and Weakly-Supervised Learning Track.

Transfer Learning Weakly-supervised Temporal Action Localization +1

TSI: Temporal Saliency Integration for Video Action Recognition

no code implementations2 Jun 2021 Haisheng Su, Jinyuan Feng, Dongliang Wang, Weihao Gan, Wei Wu, Yu Qiao

Specifically, SME aims to highlight the motion-sensitive area through local-global motion modeling, where the saliency alignment and pyramidal feature difference are conducted successively between neighboring frames to capture motion dynamics with less noises caused by misaligned background.

Action Recognition

A Novel Automatic Modulation Classification Scheme Based on Multi-Scale Networks

no code implementations31 May 2021 Hao Zhang, Fuhui Zhou, Qihui Wu, Wei Wu, Rose Qingyang Hu

Moreover, a novel loss function that combines the center loss and the cross entropy loss is exploited to learn both discriminative and separable features in order to further improve the classification performance.

Classification Face Recognition

Improving Document Representations by Generating Pseudo Query Embeddings for Dense Retrieval

no code implementations ACL 2021 Hongyin Tang, Xingwu Sun, Beihong Jin, Jingang Wang, Fuzheng Zhang, Wei Wu

Recently, the retrieval models based on dense representations have been gradually applied in the first stage of the document retrieval tasks, showing better performance than traditional sparse vector space models.

Temporal Context Aggregation Network for Temporal Action Proposal Refinement

1 code implementation CVPR 2021 Zhiwu Qing, Haisheng Su, Weihao Gan, Dongliang Wang, Wei Wu, Xiang Wang, Yu Qiao, Junjie Yan, Changxin Gao, Nong Sang

In this paper, we propose Temporal Context Aggregation Network (TCANet) to generate high-quality action proposals through "local and global" temporal context aggregation and complementary as well as progressive boundary refinement.

Action Detection Temporal Action Proposal Generation +1

Incorporating Convolution Designs into Visual Transformers

2 code implementations ICCV 2021 Kun Yuan, Shaopeng Guo, Ziwei Liu, Aojun Zhou, Fengwei Yu, Wei Wu

Motivated by the success of Transformers in natural language processing (NLP) tasks, there emerge some attempts (e. g., ViT and DeiT) to apply Transformers to the vision domain.

 Ranked #1 on Image Classification on Oxford-IIIT Pets (using extra training data)

Image Classification Natural Language Processing

ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Prediction

1 code implementation NAACL 2021 Jiahao Bu, Lei Ren, Shuang Zheng, Yang Yang, Jingang Wang, Fuzheng Zhang, Wei Wu

Aspect category sentiment analysis (ACSA) and review rating prediction (RP) are two essential tasks to detect the fine-to-coarse sentiment polarities.

Sentiment Analysis

Learning Statistical Texture for Semantic Segmentation

1 code implementation CVPR 2021 Lanyun Zhu, Deyi Ji, Shiping Zhu, Weihao Gan, Wei Wu, Junjie Yan

In this paper, we fully take advantages of the low-level texture features and propose a novel Statistical Texture Learning Network (STLNet) for semantic segmentation.

Quantization Semantic Segmentation

BaPipe: Exploration of Balanced Pipeline Parallelism for DNN Training

no code implementations23 Dec 2020 Letian Zhao, Rui Xu, Tianqi Wang, Teng Tian, Xiaotian Wang, Wei Wu, Chio-in Ieong, Xi Jin

The size of deep neural networks (DNNs) grows rapidly as the complexity of the machine learning algorithm increases.

Improving EEG Decoding via Clustering-based Multi-task Feature Learning

no code implementations12 Dec 2020 Yu Zhang, Tao Zhou, Wei Wu, Hua Xie, Hongru Zhu, Guoxu Zhou, Andrzej Cichocki

With the encoded label matrix, we devise a novel multi-task learning algorithm by exploiting the subclass relationship to jointly optimize the EEG pattern features from the uncovered subclasses.

EEG Eeg Decoding +1

Context-Aware Graph Convolution Network for Target Re-identification

no code implementations8 Dec 2020 Deyi Ji, Haoran Wang, Hanzhe Hu, Weihao Gan, Wei Wu, Junjie Yan

Most existing re-identification methods focus on learning robust and discriminative features with deep convolution networks.

Vehicle Re-Identification

Social Media Study of Public Opinions on Potential COVID-19 Vaccines: Informing Dissent, Disparities, and Dissemination

no code implementations3 Dec 2020 Hanjia Lyu, Wei Wu, Junda Wang, Viet Duong, Xiyang Zhang, Jiebo Luo

People who have the worst personal pandemic experience are more likely to hold the anti-vaccine opinion.

Social and Information Networks

Are Pre-trained Language Models Knowledgeable to Ground Open Domain Dialogues?

no code implementations19 Nov 2020 Yufan Zhao, Wei Wu, Can Xu

We study knowledge-grounded dialogue generation with pre-trained language models.

Dialogue Generation

Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning

1 code implementation29 Oct 2020 Yuncheng Hua, Yuan-Fang Li, Gholamreza Haffari, Guilin Qi, Wei Wu

However, this comes at the cost of manually labeling similar questions to learn a retrieval model, which is tedious and expensive.

Knowledge Base Question Answering Meta-Learning

Less is More: Data-Efficient Complex Question Answering over Knowledge Bases

1 code implementation29 Oct 2020 Yuncheng Hua, Yuan-Fang Li, Guilin Qi, Wei Wu, Jingyao Zhang, Daiqing Qi

Our framework consists of a neural generator and a symbolic executor that, respectively, transforms a natural-language question into a sequence of primitive actions, and executes them over the knowledge base to compute the answer.

Multi-hop Question Answering Question Answering

Electromagnetic Source Imaging via a Data-Synthesis-Based Denoising Autoencoder

no code implementations24 Oct 2020 Gexin Huang, Zhu Liang Yu, Wei Wu, Ke Liu, Zhenghui Gu, Feifei Qi, Yuanqing Li, Jiawen Liang

Compared with the traditional methods, we show (1) that the novel deep learning approach provides an effective and easy-to-apply way to solve the ESI problem, that (2) compared to traditional methods, DST-DAE with the data synthesis strategy can better consider the characteristics of real sources than the mathematical formulation of prior assumptions, and that (3) the specifically designed architecture of DAE can not only provide a better estimation of source signals but also be robust to noise pollution.

Denoising

StyleDGPT: Stylized Response Generation with Pre-trained Language Models

1 code implementation Findings of the Association for Computational Linguistics 2020 Ze Yang, Wei Wu, Can Xu, Xinnian Liang, Jiaqi Bai, Liran Wang, Wei Wang, Zhoujun Li

Generating responses following a desired style has great potentials to extend applications of open-domain dialogue systems, yet is refrained by lacking of parallel data for training.

Response Generation

SAMOT: Switcher-Aware Multi-Object Tracking and Still Another MOT Measure

no code implementations22 Sep 2020 Weitao Feng, Zhihao Hu, Baopu Li, Weihao Gan, Wei Wu, Wanli Ouyang

Besides, we propose a new MOT evaluation measure, Still Another IDF score (SAIDF), aiming to focus more on identity issues. This new measure may overcome some problems of the previous measures and provide a better insight for identity issues in MOT.

Multi-Object Tracking

Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition

no code implementations15 Sep 2020 Haisheng Su, Jing Su, Dongliang Wang, Weihao Gan, Wei Wu, Mengmeng Wang, Junjie Yan, Yu Qiao

Second, the parameter frequency distribution is further adopted to guide the student network to learn the appearance modeling process from the teacher.

Action Recognition Knowledge Distillation

BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation

1 code implementation15 Sep 2020 Haisheng Su, Weihao Gan, Wei Wu, Yu Qiao, Junjie Yan

In this paper, we present BSN++, a new framework which exploits complementary boundary regressor and relation modeling for temporal proposal generation.

Temporal Action Proposal Generation

Zero-Resource Knowledge-Grounded Dialogue Generation

1 code implementation NeurIPS 2020 Linxiao Li, Can Xu, Wei Wu, Yufan Zhao, Xueliang Zhao, Chongyang Tao

While neural conversation models have shown great potentials towards generating informative and engaging responses via introducing external knowledge, learning such a model often requires knowledge-grounded dialogues that are difficult to obtain.

Dialogue Generation

Complementary Boundary Generator with Scale-Invariant Relation Modeling for Temporal Action Localization: Submission to ActivityNet Challenge 2020

no code implementations20 Jul 2020 Haisheng Su, Jinyuan Feng, Hao Shao, Zhenyu Jiang, Manyuan Zhang, Wei Wu, Yu Liu, Hongsheng Li, Junjie Yan

Specifically, in order to generate high-quality proposals, we consider several factors including the video feature encoder, the proposal generator, the proposal-proposal relations, the scale imbalance, and ensemble strategy.

Temporal Action Localization

Class-wise Dynamic Graph Convolution for Semantic Segmentation

no code implementations ECCV 2020 Hanzhe Hu, Deyi Ji, Weihao Gan, Shuai Bai, Wei Wu, Junjie Yan

Specifically, the CDGC module takes the coarse segmentation result as class mask to extract node features for graph construction and performs dynamic graph convolutions on the constructed graph to learn the feature aggregation and weight allocation.

graph construction Semantic Segmentation

CorefQA: Coreference Resolution as Query-based Span Prediction

1 code implementation ACL 2020 Wei Wu, Fei Wang, Arianna Yuan, Fei Wu, Jiwei Li

In this paper, we present CorefQA, an accurate and extensible approach for the coreference resolution task.

 Ranked #1 on Coreference Resolution on CoNLL 2012 (using extra training data)

Coreference Resolution Data Augmentation +1

Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning

1 code implementation ICLR 2021 Ruozi Huang, Huang Hu, Wei Wu, Kei Sawada, Mi Zhang, Daxin Jiang

In this paper, we formalize the music-conditioned dance generation as a sequence-to-sequence learning problem and devise a novel seq2seq architecture to efficiently process long sequences of music features and capture the fine-grained correspondence between music and dance.

motion synthesis

Deep learning to estimate the physical proportion of infected region of lung for COVID-19 pneumonia with CT image set

no code implementations9 Jun 2020 Wei Wu, Yu Shi, Xukun Li, Yukun Zhou, Peng Du, Shuangzhi Lv, Tingbo Liang, Jifang Sheng

For the segmented masks of intact lung and infected regions, the best method could achieve 0. 972 and 0. 757 measure in mean Dice similarity coefficient on our test benchmark.

Computed Tomography (CT)

Hierarchical Feature Embedding for Attribute Recognition

no code implementations CVPR 2020 Jie Yang, Jiarou Fan, Yiru Wang, Yige Wang, Weihao Gan, Lin Liu, Wei Wu

Attribute recognition is a crucial but challenging task due to viewpoint changes, illumination variations and appearance diversities, etc.

Scope Head for Accurate Localization in Object Detection

no code implementations11 May 2020 Geng Zhan, Dan Xu, Guo Lu, Wei Wu, Chunhua Shen, Wanli Ouyang

Existing anchor-based and anchor-free object detectors in multi-stage or one-stage pipelines have achieved very promising detection performance.

object-detection Object Detection

Estimation of the Laser Frequency Nosie Spectrum by Continuous Dynamical Decoupling

no code implementations8 May 2020 Manchao Zhang, Yi Xie, Jie Zhang, Weichen Wang, Chunwang Wu, Ting Chen, Wei Wu, Pingxing Chen

Decoherence induced by the laser frequency noise is one of the most important obstacles in the quantum information processing.

Quantum Physics

Open Domain Dialogue Generation with Latent Images

no code implementations4 Apr 2020 Ze Yang, Wei Wu, Huang Hu, Can Xu, Wei Wang, Zhoujun Li

Thus, we propose learning a response generation model with both image-grounded dialogues and textual dialogues by assuming that the visual scene information at the time of a conversation can be represented by an image, and trying to recover the latent images of the textual dialogues through text-to-image generation techniques.

Dialogue Generation Response Generation +2

Towards information-rich, logical text generation with knowledge-enhanced neural models

no code implementations2 Mar 2020 Hao Wang, Bin Guo, Wei Wu, Zhiwen Yu

Text generation system has made massive promising progress contributed by deep learning techniques and has been widely applied in our life.

Text Generation

Low-Resource Knowledge-Grounded Dialogue Generation

no code implementations ICLR 2020 Xueliang Zhao, Wei Wu, Chongyang Tao, Can Xu, Dongyan Zhao, Rui Yan

In such a low-resource setting, we devise a disentangled response decoder in order to isolate parameters that depend on knowledge-grounded dialogues from the entire generation model.

Dialogue Generation Response Generation

Deep Learning System to Screen Coronavirus Disease 2019 Pneumonia

no code implementations21 Feb 2020 Xiaowei Xu, Xiangao Jiang, Chunlian Ma, Peng Du, Xukun Li, Shuangzhi Lv, Liang Yu, Yanfei Chen, Junwei Su, Guanjing Lang, Yongtao Li, Hong Zhao, Kaijin Xu, Lingxiang Ruan, Wei Wu

We found that the real time reverse transcription-polymerase chain reaction (RT-PCR) detection of viral RNA from sputum or nasopharyngeal swab has a relatively low positive rate in the early stage to determine COVID-19 (named by the World Health Organization).

Computed Tomography (CT) COVID-19 Diagnosis

Description Based Text Classification with Reinforcement Learning

no code implementations ICML 2020 Duo Chai, Wei Wu, Qinghong Han, Fei Wu, Jiwei Li

We observe significant performance boosts over strong baselines on a wide range of text classification tasks including single-label classification, multi-label classification and multi-aspect sentiment analysis.

Classification General Classification +5

Computation Reallocation for Object Detection

no code implementations ICLR 2020 Feng Liang, Chen Lin, Ronghao Guo, Ming Sun, Wei Wu, Junjie Yan, Wanli Ouyang

However, classification allocation pattern is usually adopted directly to object detector, which is proved to be sub-optimal.

Instance Segmentation Neural Architecture Search +3

Coreference Resolution as Query-based Span Prediction

1 code implementation5 Nov 2019 Wei Wu, Fei Wang, Arianna Yuan, Fei Wu, Jiwei Li

In this paper, we present an accurate and extensible approach for the coreference resolution task.

Coreference Resolution Data Augmentation +1

Improving One-shot NAS by Suppressing the Posterior Fading

no code implementations CVPR 2020 Xiang Li, Chen Lin, Chuming Li, Ming Sun, Wei Wu, Junjie Yan, Wanli Ouyang

In this paper, we analyse existing weight sharing one-shot NAS approaches from a Bayesian point of view and identify the posterior fading problem, which compromises the effectiveness of shared weights.

Neural Architecture Search object-detection +2

A Deep Learning System That Generates Quantitative CT Reports for Diagnosing Pulmonary Tuberculosis

no code implementations5 Oct 2019 Wei Wu, Xukun Li, Peng Du, Guanjing Lang, Min Xu, Kaijin Xu, Lanjuan Li

The best model was selected to annotate the spatial location of lesions and classify them into miliary, infiltrative, caseous, tuberculoma and cavitary types simultaneously. Then the Noisy-Or Bayesian function was used to generate an overall infection probability. Finally, a quantitative diagnostic report was exported. The results showed that the recall and precision rates, from the perspective of a single lesion region of PTB, were 85. 9% and 89. 2% respectively.

Computed Tomography (CT) Decision Making +1

Low-Resource Response Generation with Template Prior

1 code implementation IJCNLP 2019 Ze Yang, Wei Wu, Jian Yang, Can Xu, Zhoujun Li

Since the paired data now is no longer enough to train a neural generation model, we consider leveraging the large scale of unpaired data that are much easier to obtain, and propose response generation with both paired and unpaired data.

Response Generation

Explaining A Black-box By Using A Deep Variational Information Bottleneck Approach

no code implementations25 Sep 2019 Seojin Bang, Pengtao Xie, Heewook Lee, Wei Wu, Eric Xing

Briefness and comprehensiveness are necessary in order to provide a large amount of information concisely when explaining a black-box decision system.

Interpretable Machine Learning

Conditional Text Generation for Harmonious Human-Machine Interaction

no code implementations8 Sep 2019 Bin Guo, Hao Wang, Yasan Ding, Wei Wu, Shaoyang Hao, Yueqi Sun, Zhiwen Yu

In recent years, with the development of deep learning, text generation technology has undergone great changes and provided many kinds of services for human beings, such as restaurant reservation and daily communication.

Conditional Text Generation

Myopic robust index tracking with Bregman divergence

no code implementations21 Aug 2019 Spiridon Penev, Pavel Shevchenko, Wei Wu

Typically, a quadratic function is used to define the tracking error of a portfolio and the look back approach is applied to solve the index tracking problem.

Task Bench: A Parameterized Benchmark for Evaluating Parallel Runtime Performance

no code implementations15 Aug 2019 Elliott Slaughter, Wei Wu, Yuankun Fu, Legend Brandenburg, Nicolai Garcia, Wilhem Kautz, Emily Marx, Kaleb S. Morris, Wonchan Lee, Qinglei Cao, George Bosilca, Seema Mirchandaney, Sean Treichler, Patrick McCormick, Alex Aiken

We present Task Bench, a parameterized benchmark designed to explore the performance of parallel and distributed programming systems under a variety of application scenarios.

Distributed, Parallel, and Cluster Computing

Towards Comprehensive Description Generation from Factual Attribute-value Tables

no code implementations ACL 2019 Tianyu Liu, Fuli Luo, Pengcheng Yang, Wei Wu, Baobao Chang, Zhifang Sui

To relieve these problems, we first propose force attention (FA) method to encourage the generator to pay more attention to the uncovered attributes to avoid potential key attributes missing.

A Document-grounded Matching Network for Response Selection in Retrieval-based Chatbots

no code implementations11 Jun 2019 Xueliang Zhao, Chongyang Tao, Wei Wu, Can Xu, Dongyan Zhao, Rui Yan

We present a document-grounded matching network (DGMN) for response selection that can power a knowledge-aware retrieval-based chatbot system.

Chatbot

DSReg: Using Distant Supervision as a Regularizer

no code implementations ICLR 2020 Yuxian Meng, Muyu Li, Xiaoya Li, Wei Wu, Jiwei Li

In this paper, we aim at tackling a general issue in NLP tasks where some of the negative examples are highly similar to the positive examples, i. e., hard-negative examples.

Multi-Task Learning Reading Comprehension +1

AM-LFS: AutoML for Loss Function Search

1 code implementation ICCV 2019 Chuming Li, Yuan Xin, Chen Lin, Minghao Guo, Wei Wu, Wanli Ouyang, Junjie Yan

The key contribution of this work is the design of search space which can guarantee the generalization and transferability on different vision tasks by including a bunch of existing prevailing loss functions in a unified formulation.

AutoML

Feedback Network for Image Super-Resolution

4 code implementations CVPR 2019 Zhen Li, Jinglei Yang, Zheng Liu, Xiaomin Yang, Gwanggil Jeon, Wei Wu

In this paper, we propose an image super-resolution feedback network (SRFBN) to refine low-level representations with high-level information.

Image Super-Resolution

Selective Sensor Fusion for Neural Visual-Inertial Odometry

no code implementations CVPR 2019 Changhao Chen, Stefano Rosa, Yishu Miao, Chris Xiaoxuan Lu, Wei Wu, Andrew Markham, Niki Trigoni

Deep learning approaches for Visual-Inertial Odometry (VIO) have proven successful, but they rarely focus on incorporating robust fusion strategies for dealing with imperfect input sensory data.

Autonomous Driving

Explaining a black-box using Deep Variational Information Bottleneck Approach

3 code implementations19 Feb 2019 Seojin Bang, Pengtao Xie, Heewook Lee, Wei Wu, Eric Xing

Briefness and comprehensiveness are necessary in order to provide a large amount of information concisely when explaining a black-box decision system.

Interpretable Machine Learning

Glyce: Glyph-vectors for Chinese Character Representations

2 code implementations NeurIPS 2019 Yuxian Meng, Wei Wu, Fei Wang, Xiaoya Li, Ping Nie, Fan Yin, Muyu Li, Qinghong Han, Xiaofei Sun, Jiwei Li

However, due to the lack of rich pictographic evidence in glyphs and the weak generalization ability of standard computer vision models on character data, an effective way to utilize the glyph information remains to be found.

Chinese Dependency Parsing Chinese Named Entity Recognition +19

Dynamic Curriculum Learning for Imbalanced Data Classification

no code implementations ICCV 2019 Yiru Wang, Weihao Gan, Jie Yang, Wei Wu, Junjie Yan

Human attribute analysis is a challenging task in the field of computer vision, since the data is largely imbalance-distributed.

Classification General Classification +1

Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification

no code implementations18 Jan 2019 Weitao Feng, Zhihao Hu, Wei Wu, Junjie Yan, Wanli Ouyang

In this paper, we propose a unified Multi-Object Tracking (MOT) framework learning to make full use of long term and short term cues for handling complex cases in MOT scenes.

General Classification Multi-Object Tracking

SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks

8 code implementations CVPR 2019 Bo Li, Wei Wu, Qiang Wang, Fangyi Zhang, Junliang Xing, Junjie Yan

Moreover, we propose a new model architecture to perform depth-wise and layer-wise aggregations, which not only further improves the accuracy but also reduces the model size.

Translation Visual Object Tracking +1

IRLAS: Inverse Reinforcement Learning for Architecture Search

1 code implementation CVPR 2019 Minghao Guo, Zhao Zhong, Wei Wu, Dahua Lin, Junjie Yan

Motivated by the fact that human-designed networks are elegant in topology with a fast inference speed, we propose a mirror stimuli function inspired by biological cognition theory to extract the abstract topological knowledge of an expert human-design network (ResNeXt).

Neural Architecture Search reinforcement-learning

A Review for Weighted MinHash Algorithms

1 code implementation12 Nov 2018 Wei Wu, Bin Li, Ling Chen, Junbin Gao, Chengqi Zhang

In this review, we mainly categorize the Weighted MinHash algorithms into quantization-based approaches, "active index"-based ones and others, and show the evolution and inherent connection of the weighted MinHash algorithms, from the integer weighted MinHash algorithms to real-valued weighted MinHash ones (particularly the Consistent Weighted Sampling scheme).

Data Structures and Algorithms

Synaptic Strength For Convolutional Neural Network

no code implementations NeurIPS 2018 Chen Lin, Zhao Zhong, Wei Wu, Junjie Yan

Inspired by the relevant concept in neural science literature, we propose Synaptic Pruning: a data-driven method to prune connections between input and output feature maps with a newly proposed class of parameters called Synaptic Strength.

Phrase-level Self-Attention Networks for Universal Sentence Encoding

no code implementations EMNLP 2018 Wei Wu, Houfeng Wang, Tianyu Liu, Shuming Ma

As a result, the memory consumption can be reduced because the self-attention is performed at the phrase level instead of the sentence level.

Multi-class Classification Natural Language Inference +3

Improving Matching Models with Hierarchical Contextualized Representations for Multi-turn Response Selection

no code implementations22 Aug 2018 Chongyang Tao, Wei Wu, Can Xu, Yansong Feng, Dongyan Zhao, Rui Yan

In this paper, we study context-response matching with pre-trained contextualized representations for multi-turn response selection in retrieval-based chatbots.

Dialogue Generation

Distractor-aware Siamese Networks for Visual Object Tracking

1 code implementation ECCV 2018 Zheng Zhu, Qiang Wang, Bo Li, Wei Wu, Junjie Yan, Weiming Hu

During the off-line training phase, an effective sampling strategy is introduced to control this distribution and make the model focus on the semantic distractors.

Incremental Learning Visual Object Tracking +1

BlockQNN: Efficient Block-wise Neural Network Architecture Generation

2 code implementations16 Aug 2018 Zhao Zhong, Zichen Yang, Boyang Deng, Junjie Yan, Wei Wu, Jing Shao, Cheng-Lin Liu

The block-wise generation brings unique advantages: (1) it yields state-of-the-art results in comparison to the hand-crafted networks on image classification, particularly, the best network generated by BlockQNN achieves 2. 35% top-1 error rate on CIFAR-10.

Image Classification Q-Learning

Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts

no code implementations19 Jul 2018 Can Xu, Wei Wu, Yu Wu

We study open domain dialogue generation with dialogue acts designed to explain how people engage in social chat.

Dialogue Generation reinforcement-learning +1

SGM: Sequence Generation Model for Multi-label Classification

1 code implementation COLING 2018 Pengcheng Yang, Xu sun, Wei Li, Shuming Ma, Wei Wu, Houfeng Wang

Further analysis of experimental results demonstrates that the proposed methods not only capture the correlations between labels, but also select the most informative words automatically when predicting different labels.

Classification General Classification +2

High Performance Visual Tracking With Siamese Region Proposal Network

5 code implementations CVPR 2018 Bo Li, Junjie Yan, Wei Wu, Zheng Zhu, Xiaolin Hu

Visual object tracking has been a fundamental topic in recent years and many deep learning based trackers have achieved state-of-the-art performance on multiple benchmarks.

Region Proposal Visual Object Tracking +1

Learning Matching Models with Weak Supervision for Response Selection in Retrieval-based Chatbots

no code implementations ACL 2018 Yu Wu, Wei Wu, Zhoujun Li, Ming Zhou

We propose a method that can leverage unlabeled data to learn a matching model for response selection in retrieval-based chatbots.

Resource Allocation Algorithm for V2X communications based on SCMA

no code implementations10 Apr 2018 Wei Wu, Linglin Kong

In this paper, we propose a resource allocation algorithm for V2X communications based on Sparse Code Multiple Access(SCMA).

Signal Processing

Robust Multiple Kernel k-means Clustering using Min-Max Optimization

1 code implementation6 Mar 2018 Seojin Bang, Yao-Liang Yu, Wei Wu

To address this problem and inspired by recent works in adversarial learning, we propose a multiple kernel clustering method with the min-max framework that aims to be robust to such adversarial perturbation.

Disease Prediction Multiview Learning

Orthogonality-Promoting Distance Metric Learning: Convex Relaxation and Theoretical Analysis

no code implementations ICML 2018 Pengtao Xie, Wei Wu, Yichen Zhu, Eric P. Xing

In this paper, we address these three issues by (1) seeking convex relaxations of the original nonconvex problems so that the global optimal is guaranteed to be achievable; (2) providing a formal analysis on OPR's capability of promoting balancedness; (3) providing a theoretical analysis that directly reveals the relationship between OPR and generalization performance.

Metric Learning

A Modified Sigma-Pi-Sigma Neural Network with Adaptive Choice of Multinomials

no code implementations1 Feb 2018 Feng Li, Yan Liu, Khidir Shaib Mohamed, Wei Wu

We propose in this paper a modified Sigma-Pi-Sigma neural network (MSPSNN) with an adaptive approach to find a better multinomial for a given problem.

PointCNN: Convolution On $\mathcal{X}$-Transformed Points

12 code implementations NeurIPS 2018 Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Xinhan Di, Baoquan Chen

The proposed method is a generalization of typical CNNs to feature learning from point clouds, thus we call it PointCNN.

 Ranked #1 on 3D Instance Segmentation on S3DIS (mIoU metric)

3D Instance Segmentation 3D Part Segmentation +1

Extreme Learning Machine with Local Connections

no code implementations22 Jan 2018 Feng Li, Sibo Yang, Huanhuan Huang, Wei Wu

This paper is concerned with the sparsification of the input-hidden weights of ELM (Extreme Learning Machine).

Binary output layer of feedforward neural networks for solving multi-class classification problems

no code implementations22 Jan 2018 Sibo Yang, Chao Zhang, Wei Wu

Considered in this short note is the design of output layer nodes of feedforward neural networks for solving multi-class classification problems with r (bigger than or equal to 3) classes of samples.

General Classification Multi-class Classification

SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networks

no code implementations13 Jan 2018 Linnan Wang, Jinmian Ye, Yiyang Zhao, Wei Wu, Ang Li, Shuaiwen Leon Song, Zenglin Xu, Tim Kraska

Given the limited GPU DRAM, SuperNeurons not only provisions the necessary memory for the training, but also dynamically allocates the memory for convolution workspaces to achieve the high performance.

Towards Interpretable Chit-chat: Open Domain Dialogue Generation with Dialogue Acts

no code implementations ICLR 2018 Wei Wu, Can Xu, Yu Wu, Zhoujun Li

Conventional methods model open domain dialogue generation as a black box through end-to-end learning from large scale conversation data.

Dialogue Generation Response Generation

End-to-end Flow Correlation Tracking with Spatial-temporal Attention

no code implementations CVPR 2018 Zheng Zhu, Wei Wu, Wei Zou, Junjie Yan

Discriminative correlation filters (DCF) with deep convolutional features have achieved favorable performance in recent tracking benchmarks.

Optical Flow Estimation

A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots

no code implementations CL 2019 Yu Wu, Wei Wu, Chen Xing, Can Xu, Zhoujun Li, Ming Zhou

The task requires matching a response candidate with a conversation context, whose challenges include how to recognize important parts of the context, and how to model the relationships among utterances in the context.

Improved Consistent Weighted Sampling Revisited

1 code implementation5 Jun 2017 Wei Wu, Bin Li, Ling Chen, Chengqi Zhang, Philip S. Yu

Min-Hash is a popular technique for efficiently estimating the Jaccard similarity of binary sets.

Data Structures and Algorithms

Hierarchical Recurrent Attention Network for Response Generation

1 code implementation25 Jan 2017 Chen Xing, Wei Wu, Yu Wu, Ming Zhou, YaLou Huang, Wei-Ying Ma

With the word level attention, hidden vectors of a word level encoder are synthesized as utterance vectors and fed to an utterance level encoder to construct hidden representations of the context.

Response Generation

Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots

3 code implementations ACL 2017 Yu Wu, Wei Wu, Chen Xing, Ming Zhou, Zhoujun Li

Existing work either concatenates utterances in context or matches a response with a highly abstract context vector finally, which may lose relationships among utterances or important contextual information.

Conversational Response Selection

Knowledge Enhanced Hybrid Neural Network for Text Matching

no code implementations15 Nov 2016 Yu Wu, Wei Wu, Zhoujun Li, Ming Zhou

Long text brings a big challenge to semantic matching due to their complicated semantic and syntactic structures.

Question Answering Text Matching

Detecting Context Dependent Messages in a Conversational Environment

no code implementations COLING 2016 Chaozhuo Li, Yu Wu, Wei Wu, Chen Xing, Zhoujun Li, Ming Zhou

While automatic response generation for building chatbot systems has drawn a lot of attention recently, there is limited understanding on when we need to consider the linguistic context of an input text in the generation process.

Chatbot Response Generation

Topic Aware Neural Response Generation

1 code implementation21 Jun 2016 Chen Xing, Wei Wu, Yu Wu, Jie Liu, YaLou Huang, Ming Zhou, Wei-Ying Ma

We consider incorporating topic information into the sequence-to-sequence framework to generate informative and interesting responses for chatbots.

Response Generation

Response Selection with Topic Clues for Retrieval-based Chatbots

1 code implementation30 Apr 2016 Yu Wu, Wei Wu, Zhoujun Li, Ming Zhou

The message vector, the response vector, and the two topic vectors are fed to neural tensors to calculate a matching score.

Large Scale Artificial Neural Network Training Using Multi-GPUs

no code implementations13 Nov 2015 Linnan Wang, Wei Wu, Jianxiong Xiao, Yang Yi

This paper describes a method for accelerating large scale Artificial Neural Networks (ANN) training using multi-GPUs by reducing the forward and backward passes to matrix multiplication.

BLASX: A High Performance Level-3 BLAS Library for Heterogeneous Multi-GPU Computing

1 code implementation16 Oct 2015 Linnan Wang, Wei Wu, Jianxiong Xiao, Yi Yang

Basic Linear Algebra Subprograms (BLAS) are a set of low level linear algebra kernels widely adopted by applications involved with the deep learning and scientific computing.

Distributed, Parallel, and Cluster Computing

Generative Models for Functional Data using Phase and Amplitude Separation

no code implementations8 Dec 2012 J. Derek Tucker, Wei Wu, Anuj Srivastava

This paper presents an approach that relies on separating the phase (x-axis) and amplitude (y-axis), then modeling these components using joint distributions.

Computation Statistics Theory Statistics Theory 62F99

Signal Estimation Under Random Time-Warpings and Nonlinear Signal Alignment

no code implementations NeurIPS 2011 Sebastian A. Kurtek, Anuj Srivastava, Wei Wu

First, we derive an estimator for the equivalence class of the unknown signal using the notion of Karcher mean on the quotient space of equivalence classes.

Registration of Functional Data Using Fisher-Rao Metric

no code implementations19 Mar 2011 Anuj Srivastava, Wei Wu, Sebastian Kurtek, Eric Klassen, J. S. Marron

We introduce a novel geometric framework for separating the phase and the amplitude variability in functional data of the type frequently studied in growth curve analysis.

Statistics Theory Applications Methodology Statistics Theory

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