Search Results for author: Fei Wu

Found 139 papers, 52 papers with code

De-Biased Court's View Generation with Causality

no code implementations EMNLP 2020 Yiquan Wu, Kun Kuang, Yating Zhang, Xiaozhong Liu, Changlong Sun, Jun Xiao, Yueting Zhuang, Luo Si, Fei Wu

Court{'}s view generation is a novel but essential task for legal AI, aiming at improving the interpretability of judgment prediction results and enabling automatic legal document generation.

Text Generation

Boosting RGB-D Saliency Detection by Leveraging Unlabeled RGB Images

1 code implementation1 Jan 2022 Xiaoqiang Wang, Lei Zhu, Siliang Tang, Huazhu Fu, Ping Li, Fei Wu, Yi Yang, Yueting Zhuang

The depth estimation branch is trained with RGB-D images and then used to estimate the pseudo depth maps for all unlabeled RGB images to form the paired data.

Depth Estimation RGB-D Salient Object Detection +2

Feature Distillation Interaction Weighting Network for Lightweight Image Super-Resolution

1 code implementation16 Dec 2021 Guangwei Gao, Wenjie Li, Juncheng Li, Fei Wu, Huimin Lu, Yi Yu

Convolutional neural networks based single-image super-resolution (SISR) has made great progress in recent years.

Image Super-Resolution

A General Framework for Defending Against Backdoor Attacks via Influence Graph

no code implementations29 Nov 2021 Xiaofei Sun, Jiwei Li, Xiaoya Li, Ziyao Wang, Tianwei Zhang, Han Qiu, Fei Wu, Chun Fan

In this work, we propose a new and general framework to defend against backdoor attacks, inspired by the fact that attack triggers usually follow a \textsc{specific} type of attacking pattern, and therefore, poisoned training examples have greater impacts on each other during training.

Triggerless Backdoor Attack for NLP Tasks with Clean Labels

1 code implementation15 Nov 2021 Leilei Gan, Jiwei Li, Tianwei Zhang, Xiaoya Li, Yuxian Meng, Fei Wu, Shangwei Guo, Chun Fan

To deal with this issue, in this paper, we propose a new strategy to perform textual backdoor attacks which do not require an external trigger, and the poisoned samples are correctly labeled.

Edge-Cloud Polarization and Collaboration: A Comprehensive Survey

no code implementations11 Nov 2021 Jiangchao Yao, Shengyu Zhang, Yang Yao, Feng Wang, Jianxin Ma, Jianwei Zhang, Yunfei Chu, Luo Ji, Kunyang Jia, Tao Shen, Anpeng Wu, Fengda Zhang, Ziqi Tan, Kun Kuang, Chao Wu, Fei Wu, Jingren Zhou, Hongxia Yang

However, edge computing, especially edge and cloud collaborative computing, are still in its infancy to announce their success due to the resource-constrained IoT scenarios with very limited algorithms deployed.


Amazon SageMaker Model Parallelism: A General and Flexible Framework for Large Model Training

no code implementations10 Nov 2021 Can Karakus, Rahul Huilgol, Fei Wu, Anirudh Subramanian, Cade Daniel, Derya Cavdar, Teng Xu, Haohan Chen, Arash Rahnama, Luis Quintela

In contrast to existing solutions, the implementation of the SageMaker library is much more generic and flexible, in that it can automatically partition and run pipeline parallelism over arbitrary model architectures with minimal code change, and also offers a general and extensible framework for tensor parallelism, which supports a wider range of use cases, and is modular enough to be easily applied to new training scripts.

Collaborative Filtering

Unified Group Fairness on Federated Learning

no code implementations9 Nov 2021 Fengda Zhang, Kun Kuang, Yuxuan Liu, Chao Wu, Fei Wu, Jiaxun Lu, Yunfeng Shao, Jun Xiao

Specifically, we treat the performance of the federated global model at each group as an objective and employ the distributionally robust techniques to maximize the performance of the worst-performing group over an uncertainty set by group reweighting.

Fairness Federated Learning

Dialogue Inspectional Summarization with Factual Inconsistency Awareness

no code implementations5 Nov 2021 Leilei Gan, Yating Zhang, Kun Kuang, Lin Yuan, Shuo Li, Changlong Sun, Xiaozhong Liu, Fei Wu

Dialogue summarization has been extensively studied and applied, where the prior works mainly focused on exploring superior model structures to align the input dialogue and the output summary.

dialogue summary Medical Diagnosis

GNN-LM: Language Modeling based on Global Contexts via GNN

1 code implementation17 Oct 2021 Yuxian Meng, Shi Zong, Xiaoya Li, Xiaofei Sun, Tianwei Zhang, Fei Wu, Jiwei Li

Inspired by the notion that {\it to copy is easier than to memorize}, in this work, we introduce GNN-LM, which extends the vanilla neural language model (LM) by allowing to reference similar contexts in the entire training corpus.

Language Modelling

Collaborative Semantic Aggregation and Calibration for Separated Domain Generalization

1 code implementation13 Oct 2021 Junkun Yuan, Xu Ma, Defang Chen, Kun Kuang, Fei Wu, Lanfen Lin

In this paper, we introduce a separated domain generalization task with separated source datasets that can only be accessed locally for data privacy protection.

Domain Generalization

Multi-trends Enhanced Dynamic Micro-video Recommendation

no code implementations8 Oct 2021 Yujie Lu, Yingxuan Huang, Shengyu Zhang, Wei Han, Hui Chen, Zhou Zhao, Fei Wu

In this paper, we propose the DMR framework to explicitly model dynamic multi-trends of users' current preference and make predictions based on both the history and future potential trends.

Recommendation Systems

Stable Prediction on Graphs with Agnostic Distribution Shift

no code implementations8 Oct 2021 Shengyu Zhang, Kun Kuang, Jiezhong Qiu, Jin Yu, Zhou Zhao, Hongxia Yang, Zhongfei Zhang, Fei Wu

The results demonstrate that our method outperforms various SOTA GNNs for stable prediction on graphs with agnostic distribution shift, including shift caused by node labels and attributes.

Graph Learning Recommendation Systems

Domain-Specific Bias Filtering for Single Labeled Domain Generalization

1 code implementation2 Oct 2021 Junkun Yuan, Xu Ma, Defang Chen, Kun Kuang, Fei Wu, Lanfen Lin

In this paper, we investigate a Single Labeled Domain Generalization (SLDG) task with only one source domain being labeled, which is more practical and challenging than the Conventional Domain Generalization (CDG).

Domain Generalization

Why Do We Click: Visual Impression-aware News Recommendation

1 code implementation26 Sep 2021 Jiahao Xun, Shengyu Zhang, Zhou Zhao, Jieming Zhu, Qi Zhang, Jingjie Li, Xiuqiang He, Xiaofei He, Tat-Seng Chua, Fei Wu

In this work, inspired by the fact that users make their click decisions mostly based on the visual impression they perceive when browsing news, we propose to capture such visual impression information with visual-semantic modeling for news recommendation.

Decision Making News Recommendation

Memory Regulation and Alignment toward Generalizer RGB-Infrared Person

1 code implementation18 Sep 2021 Feng Chen, Fei Wu, Qi Wu, Zhiguo Wan

The domain shift, coming from unneglectable modality gap and non-overlapped identity classes between training and test sets, is a major issue of RGB-Infrared person re-identification.

Metric Learning Person Re-Identification

Homogeneous and Heterogeneous Relational Graph for Visible-infrared Person Re-identification

1 code implementation18 Sep 2021 Yujian Feng, Feng Chen, Jian Yu, Yimu Ji, Fei Wu, Shangdong Liu, Xiao-Yuan Jing

Existing VI Re-ID methods mainly focus on extracting homogeneous structural relationships in an image, i. e. the relations between local features, while ignoring the heterogeneous correlation of local features in different modalities.

Person Re-Identification

CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation

no code implementations11 Sep 2021 Shengyu Zhang, Dong Yao, Zhou Zhao, Tat-Seng Chua, Fei Wu

In this paper, we propose to learn accurate and robust user representations, which are required to be less sensitive to (attack on) noisy behaviors and trust more on the indispensable ones, by modeling counterfactual data distribution.

Representation Learning Sequential Recommendation

Paraphrase Generation as Unsupervised Machine Translation

no code implementations7 Sep 2021 Chun Fan, Yufei Tian, Yuxian Meng, Nanyun Peng, Xiaofei Sun, Fei Wu, Jiwei Li

Then based on the paraphrase pairs produced by these UMT models, a unified surrogate model can be trained to serve as the final Seq2Seq model to generate paraphrases, which can be directly used for test in the unsupervised setup, or be finetuned on labeled datasets in the supervised setup.

Paraphrase Generation Translation +1

$k$Folden: $k$-Fold Ensemble for Out-Of-Distribution Detection

1 code implementation29 Aug 2021 Xiaoya Li, Jiwei Li, Xiaofei Sun, Chun Fan, Tianwei Zhang, Fei Wu, Yuxian Meng, Jun Zhang

For a task with $k$ training labels, $k$Folden induces $k$ sub-models, each of which is trained on a subset with $k-1$ categories with the left category masked unknown to the sub-model.

Out-of-Distribution Detection Text Classification

Layer-wise Model Pruning based on Mutual Information

no code implementations EMNLP 2021 Chun Fan, Jiwei Li, Xiang Ao, Fei Wu, Yuxian Meng, Xiaofei Sun

The proposed pruning strategy offers merits over weight-based pruning techniques: (1) it avoids irregular memory access since representations and matrices can be squeezed into their smaller but dense counterparts, leading to greater speedup; (2) in a manner of top-down pruning, the proposed method operates from a more global perspective based on training signals in the top layer, and prunes each layer by propagating the effect of global signals through layers, leading to better performances at the same sparsity level.

ICDAR 2021 Competition on Scene Video Text Spotting

no code implementations26 Jul 2021 Zhanzhan Cheng, Jing Lu, Baorui Zou, Shuigeng Zhou, Fei Wu

During the competition period (opened on 1st March, 2021 and closed on 11th April, 2021), a total of 24 teams participated in the three proposed tasks with 46 valid submissions, respectively.

Text Spotting

Adaptive Hierarchical Graph Reasoning with Semantic Coherence for Video-and-Language Inference

no code implementations ICCV 2021 Juncheng Li, Siliang Tang, Linchao Zhu, Haochen Shi, Xuanwen Huang, Fei Wu, Yi Yang, Yueting Zhuang

Secondly, we introduce semantic coherence learning to explicitly encourage the semantic coherence of the adaptive hierarchical graph network from three hierarchies.

Auto IV: Counterfactual Prediction via Automatic Instrumental Variable Decomposition

no code implementations13 Jul 2021 Junkun Yuan, Anpeng Wu, Kun Kuang, Bo Li, Runze Wu, Fei Wu, Lanfen Lin

We also learn confounder representations by encouraging them to be relevant to both the treatment and the outcome.

Causal Inference

ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information

3 code implementations ACL 2021 Zijun Sun, Xiaoya Li, Xiaofei Sun, Yuxian Meng, Xiang Ao, Qing He, Fei Wu, Jiwei Li

Recent pretraining models in Chinese neglect two important aspects specific to the Chinese language: glyph and pinyin, which carry significant syntax and semantic information for language understanding.

Language Modelling Machine Reading Comprehension +3

CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation Extraction

no code implementations ACL 2021 Tao Chen, Haizhou Shi, Siliang Tang, Zhigang Chen, Fei Wu, Yueting Zhuang

The journey of reducing noise from distant supervision (DS) generated training data has been started since the DS was first introduced into the relation extraction (RE) task.

Relation Extraction

Defending against Backdoor Attacks in Natural Language Generation

1 code implementation3 Jun 2021 Chun Fan, Xiaoya Li, Yuxian Meng, Xiaofei Sun, Xiang Ao, Fei Wu, Jiwei Li, Tianwei Zhang

To defend against these attacks, we propose to detect the attack trigger by examining the effect of deleting or replacing certain words on the generation outputs, which we find successful for certain types of attacks.

Dialogue Generation Machine Translation +1

Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning

no code implementations1 Jun 2021 Jiahui Li, Kun Kuang, Baoxiang Wang, Furui Liu, Long Chen, Fei Wu, Jun Xiao

Specifically, Shapley Value and its desired properties are leveraged in deep MARL to credit any combinations of agents, which grants us the capability to estimate the individual credit for each agent.

Multi-agent Reinforcement Learning Starcraft +1

Fast Nearest Neighbor Machine Translation

1 code implementation30 May 2021 Yuxian Meng, Xiaoya Li, Xiayu Zheng, Fei Wu, Xiaofei Sun, Tianwei Zhang, Jiwei Li

Fast $k$NN-MT constructs a significantly smaller datastore for the nearest neighbor search: for each word in a source sentence, Fast $k$NN-MT first selects its nearest token-level neighbors, which is limited to tokens that are the same as the query token.

Machine Translation Translation

Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generation

1 code implementation30 May 2021 Shuhe Wang, Yuxian Meng, Xiaofei Sun, Fei Wu, Rongbin Ouyang, Rui Yan, Tianwei Zhang, Jiwei Li

Specifically, we propose to model the mutual dependency between text-visual features, where the model not only needs to learn the probability of generating the next dialog utterance given preceding dialog utterances and visual contexts, but also the probability of predicting the visual features in which a dialog utterance takes place, leading the generated dialog utterance specific to the visual context.

Parameter Estimation for the SEIR Model Using Recurrent Nets

no code implementations30 May 2021 Chun Fan, Yuxian Meng, Xiaofei Sun, Fei Wu, Tianwei Zhang, Jiwei Li

Next, based on this recurrent net that is able to generalize SEIR simulations, we are able to transform the objective to a differentiable one with respect to $\Theta_\text{SEIR}$, and straightforwardly obtain its optimal value.

Analysis and Applications of Class-wise Robustness in Adversarial Training

no code implementations29 May 2021 Qi Tian, Kun Kuang, Kelu Jiang, Fei Wu, Yisen Wang

Adversarial training is one of the most effective approaches to improve model robustness against adversarial examples.

Federated Graph Learning -- A Position Paper

no code implementations24 May 2021 Huanding Zhang, Tao Shen, Fei Wu, Mingyang Yin, Hongxia Yang, Chao Wu

Federated learning (FL) is a an emerging technique that can collaboratively train a shared model while keeping the data decentralized, which is a rational solution for distributed GNN training.

Federated Learning Graph Learning

Dependency Parsing as MRC-based Span-Span Prediction

1 code implementation17 May 2021 Leilei Gan, Yuxian Meng, Kun Kuang, Xiaofei Sun, Chun Fan, Fei Wu, Jiwei Li

Higher-order methods for dependency parsing can partially but not fully addresses the issue that edges in dependency tree should be constructed at the text span/subtree level rather than word level.

Dependency Parsing Machine Reading Comprehension

Sentence Similarity Based on Contexts

no code implementations17 May 2021 Xiaofei Sun, Yuxian Meng, Xiang Ao, Fei Wu, Tianwei Zhang, Jiwei Li, Chun Fan

The proposed framework is based on the core idea that the meaning of a sentence should be defined by its contexts, and that sentence similarity can be measured by comparing the probabilities of generating two sentences given the same context.

Language Modelling Semantic Similarity +2

VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations

no code implementations13 May 2021 Peng Zhang, Can Li, Liang Qiao, Zhanzhan Cheng, ShiLiang Pu, Yi Niu, Fei Wu

To address the above limitations, we propose a unified framework VSR for document layout analysis, combining vision, semantics and relations.

Document Layout Analysis

Reciprocal Feature Learning via Explicit and Implicit Tasks in Scene Text Recognition

1 code implementation13 May 2021 Hui Jiang, Yunlu Xu, Zhanzhan Cheng, ShiLiang Pu, Yi Niu, Wenqi Ren, Fei Wu, Wenming Tan

In this work, we excavate the implicit task, character counting within the traditional text recognition, without additional labor annotation cost.

Scene Text Recognition

LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment

1 code implementation13 May 2021 Liang Qiao, Zaisheng Li, Zhanzhan Cheng, Peng Zhang, ShiLiang Pu, Yi Niu, Wenqi Ren, Wenming Tan, Fei Wu

In this paper, we aim to obtain more reliable aligned bounding boxes by fully utilizing the visual information from both text regions in proposed local features and cell relations in global features.

BertGCN: Transductive Text Classification by Combining GCN and BERT

1 code implementation12 May 2021 Yuxiao Lin, Yuxian Meng, Xiaofei Sun, Qinghong Han, Kun Kuang, Jiwei Li, Fei Wu

In this work, we propose BertGCN, a model that combines large scale pretraining and transductive learning for text classification.

Text Classification

Leaning Compact and Representative Features for Cross-Modality Person Re-Identification

no code implementations26 Mar 2021 Guangwei Gao, Hao Shao, Yi Yu, Fei Wu, Meng Yang

This paper pays close attention to the cross-modality visible-infrared person re-identification (VI Re-ID) task, which aims to match human samples between visible and infrared modes.

Cross-Modality Person Re-identification Knowledge Distillation +1

JDSR-GAN: Constructing A Joint and Collaborative Learning Network for Masked Face Super-Resolution

no code implementations25 Mar 2021 Guangwei Gao, Lei Tang, Yi Yu, Fei Wu, Huimin Lu, Jian Yang

In this work, we treat the mask occlusion as image noise and construct a joint and collaborative learning network, called JDSR-GAN, for the masked face super-resolution task.

Denoising Super-Resolution

Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning

no code implementations4 Mar 2021 Hui Wang, Jian Tian, Songyuan Li, Hanbin Zhao, Qi Tian, Fei Wu, Xi Li

Unsupervised domain adaptation (UDA) typically carries out knowledge transfer from a label-rich source domain to an unlabeled target domain by adversarial learning.

General Classification Image Classification +2

Learning to Anticipate Egocentric Actions by Imagination

no code implementations13 Jan 2021 Yu Wu, Linchao Zhu, Xiaohan Wang, Yi Yang, Fei Wu

We further improve ImagineRNN by residual anticipation, i. e., changing its target to predicting the feature difference of adjacent frames instead of the frame content.

Action Anticipation Autonomous Driving +1

VersatileGait: A Large-Scale Synthetic Gait Dataset with Fine-GrainedAttributes and Complicated Scenarios

no code implementations5 Jan 2021 Huanzhang Dou, Wenhu Zhang, Pengyi Zhang, Yuhan Zhao, Songyuan Li, Zequn Qin, Fei Wu, Lin Dong, Xi Li

With the motivation of practical gait recognition applications, we propose to automatically create a large-scale synthetic gait dataset (called VersatileGait) by a game engine, which consists of around one million silhouette sequences of 11, 000 subjects with fine-grained attributes in various complicated scenarios.

Gait Recognition

Intriguing class-wise properties of adversarial training

no code implementations1 Jan 2021 Qi Tian, Kun Kuang, Fei Wu, Yisen Wang

Adversarial training is one of the most effective approaches to improve model robustness against adversarial examples.

Adversarial Robustness

Semi-Supervised Active Learning for Semi-Supervised Models: Exploit Adversarial Examples With Graph-Based Virtual Labels

no code implementations ICCV 2021 Jiannan Guo, Haochen Shi, Yangyang Kang, Kun Kuang, Siliang Tang, Zhuoren Jiang, Changlong Sun, Fei Wu, Yueting Zhuang

Although current mainstream methods begin to combine SSL and AL (SSL-AL) to excavate the diverse expressions of unlabeled samples, these methods' fully supervised task models are still trained only with labeled data.

Active Learning

Rethinking Pseudo-labeled Sample Mining for Semi-Supervised Object Detection

no code implementations1 Jan 2021 Duo Li, Sanli Tang, Zhanzhan Cheng, ShiLiang Pu, Yi Niu, Wenming Tan, Fei Wu, Xiaokang Yang

However, the impact of the pseudo-labeled samples' quality as well as the mining strategies for high quality training sample have rarely been studied in SSL.

Object Detection Semi-Supervised Object Detection

OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts

1 code implementation30 Dec 2020 Yuxian Meng, Shuhe Wang, Qinghong Han, Xiaofei Sun, Fei Wu, Rui Yan, Jiwei Li

Based on this dataset, we propose a family of encoder-decoder models leveraging both textual and visual contexts, from coarse-grained image features extracted from CNNs to fine-grained object features extracted from Faster R-CNNs.

Dialogue Generation

SemGloVe: Semantic Co-occurrences for GloVe from BERT

no code implementations30 Dec 2020 Leilei Gan, Zhiyang Teng, Yue Zhang, Linchao Zhu, Fei Wu, Yi Yang

In this paper, we propose SemGloVe, which distills semantic co-occurrences from BERT into static GloVe word embeddings.

Language Modelling Word Embeddings +1

FcaNet: Frequency Channel Attention Networks

1 code implementation ICCV 2021 Zequn Qin, Pengyi Zhang, Fei Wu, Xi Li

With the proof, we naturally generalize the compression of the channel attention mechanism in the frequency domain and propose our method with multi-spectral channel attention, termed as FcaNet.

Image Classification Instance Segmentation +2

MANGO: A Mask Attention Guided One-Stage Scene Text Spotter

1 code implementation8 Dec 2020 Liang Qiao, Ying Chen, Zhanzhan Cheng, Yunlu Xu, Yi Niu, ShiLiang Pu, Fei Wu

Recently end-to-end scene text spotting has become a popular research topic due to its advantages of global optimization and high maintainability in real applications.

Text Spotting

Self-Explaining Structures Improve NLP Models

1 code implementation3 Dec 2020 Zijun Sun, Chun Fan, Qinghong Han, Xiaofei Sun, Yuxian Meng, Fei Wu, Jiwei Li

The proposed model comes with the following merits: (1) span weights make the model self-explainable and do not require an additional probing model for interpretation; (2) the proposed model is general and can be adapted to any existing deep learning structures in NLP; (3) the weight associated with each text span provides direct importance scores for higher-level text units such as phrases and sentences.

 Ranked #1 on Sentiment Analysis on SST-5 Fine-grained classification (using extra training data)

Natural Language Inference Paraphrase Identification +1

Neural Semi-supervised Learning for Text Classification Under Large-Scale Pretraining

1 code implementation17 Nov 2020 Zijun Sun, Chun Fan, Xiaofei Sun, Yuxian Meng, Fei Wu, Jiwei Li

The goal of semi-supervised learning is to utilize the unlabeled, in-domain dataset U to improve models trained on the labeled dataset D. Under the context of large-scale language-model (LM) pretraining, how we can make the best use of U is poorly understood: is semi-supervised learning still beneficial with the presence of large-scale pretraining?

General Classification Language Modelling +1

Future-Aware Diverse Trends Framework for Recommendation

no code implementations1 Nov 2020 Yujie Lu, Shengyu Zhang, Yingxuan Huang, Luyao Wang, Xinyao Yu, Zhou Zhao, Fei Wu

By diverse trends, supposing the future preferences can be diversified, we propose the diverse trends extractor and the time-aware mechanism to represent the possible trends of preferences for a given user with multiple vectors.

Representation Learning Sequential Recommendation

Pair the Dots: Jointly Examining Training History and Test Stimuli for Model Interpretability

no code implementations14 Oct 2020 Yuxian Meng, Chun Fan, Zijun Sun, Eduard Hovy, Fei Wu, Jiwei Li

Any prediction from a model is made by a combination of learning history and test stimuli.

Summarize, Outline, and Elaborate: Long-Text Generation via Hierarchical Supervision from Extractive Summaries

no code implementations14 Oct 2020 Xiaofei Sun, Chun Fan, Zijun Sun, Yuxian Meng, Fei Wu, Jiwei Li

To avoid the labor-intensive process of summary soliciting, we propose the {\it reconstruction} strategy, which extracts segment summaries in an unsupervised manner by selecting its most informative part to reconstruct the segment. The proposed generation system comes with the following merits: (1) the summary provides high-level guidances for text generation and avoids the local minimum of individual word predictions; (2) the high-level discourse dependencies are captured in the conditional dependencies between summaries and are preserved during the summary expansion process and (3) additionally, we are able to consider significantly more contexts by representing contexts as concise summaries.

Text Generation

MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination

no code implementations2 Oct 2020 Shengyu Zhang, Donghui Wang, Zhou Zhao, Siliang Tang, Di Xie, Fei Wu

In this paper, we investigate the problem of text-to-pedestrian synthesis, which has many potential applications in art, design, and video surveillance.

Image Generation

Improving Robustness and Generality of NLP Models Using Disentangled Representations

no code implementations21 Sep 2020 Jiawei Wu, Xiaoya Li, Xiang Ao, Yuxian Meng, Fei Wu, Jiwei Li

We show that models trained with the proposed criteria provide better robustness and domain adaptation ability in a wide range of supervised learning tasks.

Domain Adaptation Representation Learning

Two Step Joint Model for Drug Drug Interaction Extraction

no code implementations28 Aug 2020 Siliang Tang, Qi Zhang, Tianpeng Zheng, Mengdi Zhou, Zhan Chen, Lixing Shen, Xiang Ren, Yueting Zhuang, ShiLiang Pu, Fei Wu

When patients need to take medicine, particularly taking more than one kind of drug simultaneously, they should be alarmed that there possibly exists drug-drug interaction.

Drug–drug Interaction Extraction Named Entity Recognition +2

Poet: Product-oriented Video Captioner for E-commerce

1 code implementation16 Aug 2020 Shengyu Zhang, Ziqi Tan, Jin Yu, Zhou Zhao, Kun Kuang, Jie Liu, Jingren Zhou, Hongxia Yang, Fei Wu

Then, based on the aspects of the video-associated product, we perform knowledge-enhanced spatial-temporal inference on those graphs for capturing the dynamic change of fine-grained product-part characteristics.

Video Captioning

DeVLBert: Learning Deconfounded Visio-Linguistic Representations

1 code implementation16 Aug 2020 Shengyu Zhang, Tan Jiang, Tan Wang, Kun Kuang, Zhou Zhao, Jianke Zhu, Jin Yu, Hongxia Yang, Fei Wu

In this paper, we propose to investigate the problem of out-of-domain visio-linguistic pretraining, where the pretraining data distribution differs from that of downstream data on which the pretrained model will be fine-tuned.

Image Retrieval Question Answering +1

TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text Detection

1 code implementation11 Aug 2020 Fangfang Wang, Yifeng Chen, Fei Wu, Xi Li

Arbitrary-shaped text detection is a challenging task due to the complex geometric layouts of texts such as large aspect ratios, various scales, random rotations and curve shapes.

Scene Text Detection

Topic Adaptation and Prototype Encoding for Few-Shot Visual Storytelling

no code implementations11 Aug 2020 Jiacheng Li, Siliang Tang, Juncheng Li, Jun Xiao, Fei Wu, ShiLiang Pu, Yueting Zhuang

In this paper, we focus on enhancing the generalization ability of the VIST model by considering the few-shot setting.

Meta-Learning Visual Storytelling

Memory Efficient Class-Incremental Learning for Image Classification

no code implementations4 Aug 2020 Hanbin Zhao, Hui Wang, Yongjian Fu, Fei Wu, Xi Li

To cope with the forgetting problem, many CIL methods transfer the knowledge of old classes by preserving some exemplar samples into the size-constrained memory buffer.

class-incremental learning General Classification +3

Polar Relative Positional Encoding for Video-Language Segmentation

no code implementations20 Jul 2020 Ke Ning, Lingxi Xie, Fei Wu, Qi Tian

In this paper, we propose a novel Polar Relative Positional Encoding (PRPE) mechanism that represents spatial relations in a ``linguistic'' way, i. e., in terms of direction and range.

Referring Expression Segmentation

Learning a Domain Classifier Bank for Unsupervised Adaptive Object Detection

no code implementations6 Jul 2020 Sanli Tang, Zhanzhan Cheng, ShiLiang Pu, Dashan Guo, Yi Niu, Fei Wu

To tackle this issue, we develop a fine-grained domain alignment approach with a well-designed domain classifier bank that achieves the instance-level alignment respecting to their categories.

Object Detection

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

MgSvF: Multi-Grained Slow vs. Fast Framework for Few-Shot Class-Incremental Learning

no code implementations28 Jun 2020 Hanbin Zhao, Yongjian Fu, Mintong Kang, Qi Tian, Fei Wu, Xi Li

As a challenging problem, few-shot class-incremental learning (FSCIL) continually learns a sequence of tasks, confronting the dilemma between slow forgetting of old knowledge and fast adaptation to new knowledge.

class-incremental learning Incremental Learning

Federated Mutual Learning

1 code implementation27 Jun 2020 Tao Shen, Jie Zhang, Xinkang Jia, Fengda Zhang, Gang Huang, Pan Zhou, Kun Kuang, Fei Wu, Chao Wu

The experiments show that FML can achieve better performance than alternatives in typical FL setting, and clients can be benefited from FML with different models and tasks.

Federated Learning

Comprehensive Information Integration Modeling Framework for Video Titling

1 code implementation24 Jun 2020 Shengyu Zhang, Ziqi Tan, Jin Yu, Zhou Zhao, Kun Kuang, Tan Jiang, Jingren Zhou, Hongxia Yang, Fei Wu

In e-commerce, consumer-generated videos, which in general deliver consumers' individual preferences for the different aspects of certain products, are massive in volume.

Video Captioning

Learning Decomposed Representation for Counterfactual Inference

no code implementations12 Jun 2020 Anpeng Wu, Kun Kuang, Junkun Yuan, Bo Li, Runze Wu, Qiang Zhu, Yueting Zhuang, Fei Wu

The fundamental problem in treatment effect estimation from observational data is confounder identification and balancing.

Counterfactual Inference

Stable Prediction via Leveraging Seed Variable

no code implementations9 Jun 2020 Kun Kuang, Bo Li, Peng Cui, Yue Liu, Jianrong Tao, Yueting Zhuang, Fei Wu

By assuming the relationships between causal variables and response variable are invariant across data, to address this problem, we propose a conditional independence test based algorithm to separate those causal variables with a seed variable as priori, and adopt them for stable prediction.

Balance-Subsampled Stable Prediction

no code implementations8 Jun 2020 Kun Kuang, Hengtao Zhang, Fei Wu, Yueting Zhuang, Aijun Zhang

However, this assumption is often violated in practice because the sample selection bias may induce the distribution shift from training data to test data.

Selection bias

ResKD: Residual-Guided Knowledge Distillation

no code implementations8 Jun 2020 Xuewei Li, Songyuan Li, Bourahla Omar, Fei Wu, Xi Li

In this paper, we see knowledge distillation in a fresh light, using the knowledge gap, or the residual, between a teacher and a student as guidance to train a much more lightweight student, called a res-student.

Knowledge Distillation

Deep Sequential Feature Learning in Clinical Image Classification of Infectious Keratitis

no code implementations4 Jun 2020 Yesheng Xu, Ming Kong, Wenjia Xie, Runping Duan, Zhengqing Fang, Yuxiao Lin, Qiang Zhu, Siliang Tang, Fei Wu, Yu-Feng Yao

Infectious keratitis is the most common entities of corneal diseases, in which pathogen grows in the cornea leading to inflammation and destruction of the corneal tissues.

General Classification Image Classification

Analyzing COVID-19 on Online Social Media: Trends, Sentiments and Emotions

no code implementations29 May 2020 Xiaoya Li, Mingxin Zhou, Jiawei Wu, Arianna Yuan, Fei Wu, Jiwei Li

At the time of writing, the ongoing pandemic of coronavirus disease (COVID-19) has caused severe impacts on society, economy and people's daily lives.

TRIE: End-to-End Text Reading and Information Extraction for Document Understanding

1 code implementation27 May 2020 Peng Zhang, Yunlu Xu, Zhanzhan Cheng, ShiLiang Pu, Jing Lu, Liang Qiao, Yi Niu, Fei Wu

Since real-world ubiquitous documents (e. g., invoices, tickets, resumes and leaflets) contain rich information, automatic document image understanding has become a hot topic.

Object-QA: Towards High Reliable Object Quality Assessment

no code implementations27 May 2020 Jing Lu, Baorui Zou, Zhanzhan Cheng, ShiLiang Pu, Shuigeng Zhou, Yi Niu, Fei Wu

In this paper, we define the problem of object quality assessment for the first time and propose an effective approach named Object-QA to assess high-reliable quality scores for object images.

Object Recognition

Progressive Multi-Stage Learning for Discriminative Tracking

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

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

Visual Tracking

Grounded and Controllable Image Completion by Incorporating Lexical Semantics

no code implementations29 Feb 2020 Shengyu Zhang, Tan Jiang, Qinghao Huang, Ziqi Tan, Zhou Zhao, Siliang Tang, Jin Yu, Hongxia Yang, Yi Yang, Fei Wu

Existing image completion procedure is highly subjective by considering only visual context, which may trigger unpredictable results which are plausible but not faithful to a grounded knowledge.

Refined Gate: A Simple and Effective Gating Mechanism for Recurrent Units

no code implementations26 Feb 2020 Zhanzhan Cheng, Yunlu Xu, Mingjian Cheng, Yu Qiao, ShiLiang Pu, Yi Niu, Fei Wu

Recurrent neural network (RNN) has been widely studied in sequence learning tasks, while the mainstream models (e. g., LSTM and GRU) rely on the gating mechanism (in control of how information flows between hidden states).

Language Modelling Scene Text Recognition

Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting

1 code implementation17 Feb 2020 Liang Qiao, Sanli Tang, Zhanzhan Cheng, Yunlu Xu, Yi Niu, ShiLiang Pu, Fei Wu

Many approaches have recently been proposed to detect irregular scene text and achieved promising results.

Text Spotting

Non-Autoregressive Neural Dialogue Generation

no code implementations11 Feb 2020 Qinghong Han, Yuxian Meng, Fei Wu, Jiwei Li

Unfortunately, under the framework of the \sts model, direct decoding from $\log p(y|x) + \log p(x|y)$ is infeasible since the second part (i. e., $p(x|y)$) requires the completion of target generation before it can be computed, and the search space for $y$ is enormous.

Dialogue Generation Open-Domain Dialog

LAVA NAT: A Non-Autoregressive Translation Model with Look-Around Decoding and Vocabulary Attention

no code implementations8 Feb 2020 Xiaoya Li, Yuxian Meng, Arianna Yuan, Fei Wu, Jiwei Li

Non-autoregressive translation (NAT) models generate multiple tokens in one forward pass and is highly efficient at inference stage compared with autoregressive translation (AT) methods.


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.

General Classification Multi-Label Classification +3

Dice Loss for Data-imbalanced NLP Tasks

2 code implementations ACL 2020 Xiaoya Li, Xiaofei Sun, Yuxian Meng, Junjun Liang, Fei Wu, Jiwei Li

Many NLP tasks such as tagging and machine reading comprehension are faced with the severe data imbalance issue: negative examples significantly outnumber positive examples, and the huge number of background examples (or easy-negative examples) overwhelms the training.

 Ranked #1 on Named Entity Recognition on Ontonotes v5 (English) (using extra training data)

Chinese Named Entity Recognition Machine Reading Comprehension +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

A Unified MRC Framework for Named Entity Recognition

6 code implementations ACL 2020 Xiaoya Li, Jingrong Feng, Yuxian Meng, Qinghong Han, Fei Wu, Jiwei Li

Instead of treating the task of NER as a sequence labeling problem, we propose to formulate it as a machine reading comprehension (MRC) task.

Ranked #2 on Nested Mention Recognition on ACE 2004 (using extra training data)

Chinese Named Entity Recognition Entity Extraction using GAN +4

Leveraging Model Interpretability and Stability to increase Model Robustness

1 code implementation1 Oct 2019 Fei Wu, Thomas Michel, Alexandre Briot

We then use an error detector in the form of a binary classifier on top of the DNN to automatically discriminate wrong and correct predictions of the DNN based on their hidden unit activations.

Image Classification

Large-scale Pretraining for Neural Machine Translation with Tens of Billions of Sentence Pairs

no code implementations26 Sep 2019 Yuxian Meng, Xiangyuan Ren, Zijun Sun, Xiaoya Li, Arianna Yuan, Fei Wu, Jiwei Li

In this paper, we investigate the problem of training neural machine translation (NMT) systems with a dataset of more than 40 billion bilingual sentence pairs, which is larger than the largest dataset to date by orders of magnitude.

Machine Translation Translation

Adaptive Graph Representation Learning for Video Person Re-identification

1 code implementation5 Sep 2019 Yiming Wu, Omar El Farouk Bourahla, Xi Li, Fei Wu, Qi Tian, Xue Zhou

While correlations between parts are ignored in the previous methods, to leverage the relations of different parts, we propose an innovative adaptive graph representation learning scheme for video person Re-ID, which enables the contextual interactions between relevant regional features.

Graph Representation Learning Video-Based Person Re-Identification

Learning Dynamic Context Augmentation for Global Entity Linking

2 code implementations IJCNLP 2019 Xiyuan Yang, Xiaotao Gu, Sheng Lin, Siliang Tang, Yueting Zhuang, Fei Wu, Zhigang Chen, Guoping Hu, Xiang Ren

Despite of the recent success of collective entity linking (EL) methods, these "global" inference methods may yield sub-optimal results when the "all-mention coherence" assumption breaks, and often suffer from high computational cost at the inference stage, due to the complex search space.

Entity Linking

Adversarial Seeded Sequence Growing for Weakly-Supervised Temporal Action Localization

no code implementations7 Aug 2019 Chengwei Zhang, Yunlu Xu, Zhanzhan Cheng, Yi Niu, ShiLiang Pu, Fei Wu, Futai Zou

The second module is a specific classifier for mining trivial or incomplete action regions, which is trained on the shared features after erasing the seeded regions activated by SSG.

Action Detection Weakly-supervised Temporal Action Localization +1

Walking with MIND: Mental Imagery eNhanceD Embodied QA

no code implementations5 Aug 2019 Juncheng Li, Siliang Tang, Fei Wu, Yueting Zhuang

The experimental results and further analysis prove that the agent with the MIND module is superior to its counterparts not only in EQA performance but in many other aspects such as route planning, behavioral interpretation, and the ability to generalize from a few examples.

Informative Visual Storytelling with Cross-modal Rules

1 code implementation7 Jul 2019 Jiacheng Li, Haizhou Shi, Siliang Tang, Fei Wu, Yueting Zhuang

To solve this problem, we propose a method to mine the cross-modal rules to help the model infer these informative concepts given certain visual input.

Story Generation Visual Storytelling

Galaxy Learning -- A Position Paper

no code implementations22 Apr 2019 Chao Wu, Jun Xiao, Gang Huang, Fei Wu

Model training, as well as the communication, is achieved with blockchain and its smart contracts.

Deep Q Learning Driven CT Pancreas Segmentation with Geometry-Aware U-Net

no code implementations19 Apr 2019 Yunze Man, Yangsibo Huang, Junyi Feng, Xi Li, Fei Wu

Segmentation of pancreas is important for medical image analysis, yet it faces great challenges of class imbalance, background distractions and non-rigid geometrical features.

Pancreas Segmentation Q-Learning

You Only Recognize Once: Towards Fast Video Text Spotting

1 code implementation8 Mar 2019 Zhanzhan Cheng, Jing Lu, Yi Niu, ShiLiang Pu, Fei Wu, Shuigeng Zhou

Video text spotting is still an important research topic due to its various real-applications.

Text Spotting

Reinforcement Learning for Optimal Load Distribution Sequencing in Resource-Sharing System

no code implementations5 Feb 2019 Fei Wu, Yang Cao, Thomas Robertazzi

Divisible Load Theory (DLT) is a powerful tool for modeling divisible load problems in data-intensive systems.

Cross-relation Cross-bag Attention for Distantly-supervised Relation Extraction

1 code implementation27 Dec 2018 Yujin Yuan, Liyuan Liu, Siliang Tang, Zhongfei Zhang, Yueting Zhuang, ShiLiang Pu, Fei Wu, Xiang Ren

Distant supervision leverages knowledge bases to automatically label instances, thus allowing us to train relation extractor without human annotations.

Relation Extraction

Bi-Adversarial Auto-Encoder for Zero-Shot Learning

no code implementations20 Nov 2018 Yunlong Yu, Zhong Ji, Yanwei Pang, Jichang Guo, Zhongfei Zhang, Fei Wu

Existing generative Zero-Shot Learning (ZSL) methods only consider the unidirectional alignment from the class semantics to the visual features while ignoring the alignment from the visual features to the class semantics, which fails to construct the visual-semantic interactions well.

Zero-Shot Learning

Textually Guided Ranking Network for Attentional Image Retweet Modeling

no code implementations24 Oct 2018 Zhou Zhao, Hanbing Zhan, Lingtao Meng, Jun Xiao, Jun Yu, Min Yang, Fei Wu, Deng Cai

In this paper, we study the problem of image retweet prediction in social media, which predicts the image sharing behavior that the user reposts the image tweets from their followees.

Context-Aware Deep Spatio-Temporal Network for Hand Pose Estimation from Depth Images

no code implementations6 Oct 2018 Yiming Wu, Wei Ji, Xi Li, Gang Wang, Jianwei Yin, Fei Wu

As a fundamental and challenging problem in computer vision, hand pose estimation aims to estimate the hand joint locations from depth images.

Hand Pose Estimation

Query Attack via Opposite-Direction Feature:Towards Robust Image Retrieval

2 code implementations7 Sep 2018 Zhedong Zheng, Liang Zheng, Yi Yang, Fei Wu

Opposite-Direction Feature Attack (ODFA) effectively exploits feature-level adversarial gradients and takes advantage of feature distance in the representation space.

Adversarial Attack General Classification +2

Deep Sequence Learning with Auxiliary Information for Traffic Prediction

1 code implementation13 Jun 2018 Binbing Liao, Jingqing Zhang, Chao Wu, Douglas McIlwraith, Tong Chen, Shengwen Yang, Yike Guo, Fei Wu

Predicting traffic conditions from online route queries is a challenging task as there are many complicated interactions over the roads and crowds involved.

Traffic Prediction

Distribution-based Label Space Transformation for Multi-label Learning

no code implementations15 May 2018 Zongting Lyu, Yan Yan, Fei Wu

This endows DLST the capability to handle label set sparsity and training data sparsity in multi-label learning problems.

Dimensionality Reduction Multi-Label Learning

State Distribution-aware Sampling for Deep Q-learning

no code implementations23 Apr 2018 Weichao Li, Fuxian Huang, Xi Li, Gang Pan, Fei Wu

A critical and challenging problem in reinforcement learning is how to learn the state-action value function from the experience replay buffer and simultaneously keep sample efficiency and faster convergence to a high quality solution.

Atari Games OpenAI Gym +1

Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction

1 code implementation23 Feb 2018 Huaxiu Yao, Fei Wu, Jintao Ke, Xianfeng Tang, Yitian Jia, Siyu Lu, Pinghua Gong, Jieping Ye, Zhenhui Li

Traditional demand prediction methods mostly rely on time series forecasting techniques, which fail to model the complex non-linear spatial and temporal relations.

Image Classification Time Series +2

Find the Conversation Killers: a Predictive Study of Thread-ending Posts

no code implementations22 Dec 2017 Yunhao Jiao, Cheng Li, Fei Wu, Qiaozhu Mei

In this study, we are particularly interested in identifying a post in a multi-party conversation that is unlikely to be further replied to, which therefore kills that thread of the conversation.

Representation Learning for Scale-free Networks

no code implementations29 Nov 2017 Rui Feng, Yang Yang, Wenjie Hu, Fei Wu, Yueting Zhuang

Existing network embedding works primarily focus on preserving the microscopic structure, such as the first- and second-order proximity of vertexes, while the macroscopic scale-free property is largely ignored.

Link Prediction Network Embedding

Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks

4 code implementations15 Aug 2017 Jun Xiao, Hao Ye, Xiangnan He, Hanwang Zhang, Fei Wu, Tat-Seng Chua

Factorization Machines (FMs) are a supervised learning approach that enhances the linear regression model by incorporating the second-order feature interactions.

Graph-Theoretic Spatiotemporal Context Modeling for Video Saliency Detection

no code implementations25 Jul 2017 Lina Wei, Fangfang Wang, Xi Li, Fei Wu, Jun Xiao

As a result, a key issue in video saliency detection is how to effectively capture the intrinsical properties of atomic video structures as well as their associated contextual interactions along the spatial and temporal dimensions.

Video Saliency Detection

Group-wise Deep Co-saliency Detection

no code implementations24 Jul 2017 Lina Wei, Shanshan Zhao, Omar El Farouk Bourahla, Xi Li, Fei Wu

In this paper, we propose an end-to-end group-wise deep co-saliency detection approach to address the co-salient object discovery problem based on the fully convolutional network (FCN) with group input and group output.

Co-Salient Object Detection Object Discovery +1

A Semantic QA-Based Approach for Text Summarization Evaluation

no code implementations21 Apr 2017 Ping Chen, Fei Wu, Tong Wang, Wei Ding

In this paper, we will present some preliminary results on one especially useful and challenging problem in NLP system evaluation: how to pinpoint content differences of two text passages (especially for large pas-sages such as articles and books).

Machine Translation Text Simplification +2

Transductive Zero-Shot Learning with a Self-training dictionary approach

no code implementations27 Mar 2017 Yunlong Yu, Zhong Ji, Xi Li, Jichang Guo, Zhongfei Zhang, Haibin Ling, Fei Wu

As an important and challenging problem in computer vision, zero-shot learning (ZSL) aims at automatically recognizing the instances from unseen object classes without training data.

Transfer Learning Zero-Shot Learning

Deep Learning Driven Visual Path Prediction from a Single Image

no code implementations27 Jan 2016 Siyu Huang, Xi Li, Zhongfei Zhang, Zhouzhou He, Fei Wu, Wei Liu, Jinhui Tang, Yueting Zhuang

The highly effective visual representation and deep context models ensure that our framework makes a deep semantic understanding of the scene and motion pattern, consequently improving the performance of the visual path prediction task.

DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection

no code implementations19 Oct 2015 Xi Li, Liming Zhao, Lina Wei, Ming-Hsuan Yang, Fei Wu, Yueting Zhuang, Haibin Ling, Jingdong Wang

A key problem in salient object detection is how to effectively model the semantic properties of salient objects in a data-driven manner.

Multi-Task Learning RGB Salient Object Detection +3

Metric Learning Driven Multi-Task Structured Output Optimization for Robust Keypoint Tracking

no code implementations4 Dec 2014 Liming Zhao, Xi Li, Jun Xiao, Fei Wu, Yueting Zhuang

As an important and challenging problem in computer vision and graphics, keypoint-based object tracking is typically formulated in a spatio-temporal statistical learning framework.

Metric Learning Object Tracking

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