Search Results for author: Zhongyuan Wang

Found 58 papers, 27 papers with code

Table Fact Verification with Structure-Aware Transformer

no code implementations EMNLP 2020 Hongzhi Zhang, Yingyao Wang, Sirui Wang, Xuezhi Cao, Fuzheng Zhang, Zhongyuan Wang

Verifying fact on semi-structured evidence like tables requires the ability to encode structural information and perform symbolic reasoning.

Fact Verification

LSTFE-Net:Long Short-Term Feature Enhancement Network for Video Small Object Detection

no code implementations CVPR 2023 Jinsheng Xiao, Yuanxu Wu, Yunhua Chen, Shurui Wang, Zhongyuan Wang, Jiayi Ma

We find that context information from the long-term frame and temporal information from the short-term frame are two useful cues for video small object detection.

object-detection Small Object Detection

Implicit Identity Driven Deepfake Face Swapping Detection

no code implementations CVPR 2023 Baojin Huang, Zhongyuan Wang, Jifan Yang, Jiaxin Ai, Qin Zou, Qian Wang, Dengpan Ye

Face swapping aims to replace the target face with the source face and generate the fake face that the human cannot distinguish between real and fake.

Face Swapping

Style-Label-Free: Cross-Speaker Style Transfer by Quantized VAE and Speaker-wise Normalization in Speech Synthesis

no code implementations13 Dec 2022 Chunyu Qiang, Peng Yang, Hao Che, Xiaorui Wang, Zhongyuan Wang

In order to improve the style extraction ability of the reference encoder, a style invariant and contrastive data augmentation method is proposed.

Data Augmentation Speech Synthesis +1

A Scale-Arbitrary Image Super-Resolution Network Using Frequency-domain Information

no code implementations8 Dec 2022 Jing Fang, Yinbo Yu, Zhongyuan Wang, Xin Ding, Ruimin Hu

Image super-resolution (SR) is a technique to recover lost high-frequency information in low-resolution (LR) images.

Image Super-Resolution

A Unified Model for Video Understanding and Knowledge Embedding with Heterogeneous Knowledge Graph Dataset

no code implementations19 Nov 2022 Jiaxin Deng, Dong Shen, Haojie Pan, Xiangyu Wu, Ximan Liu, Gaofeng Meng, Fan Yang, Size Li, Ruiji Fu, Zhongyuan Wang

Furthermore, based on this dataset, we propose an end-to-end model that jointly optimizes the video understanding objective with knowledge graph embedding, which can not only better inject factual knowledge into video understanding but also generate effective multi-modal entity embedding for KG.

Common Sense Reasoning Knowledge Graph Embedding +4

Back-Translation-Style Data Augmentation for Mandarin Chinese Polyphone Disambiguation

no code implementations17 Nov 2022 Chunyu Qiang, Peng Yang, Hao Che, Jinba Xiao, Xiaorui Wang, Zhongyuan Wang

In this paper we propose a simple back-translation-style data augmentation method for mandarin Chinese polyphone disambiguation, utilizing a large amount of unlabeled text data.

Data Augmentation Machine Translation +3

Kuaipedia: a Large-scale Multi-modal Short-video Encyclopedia

1 code implementation28 Oct 2022 Haojie Pan, Yuzhou Zhang, Zepeng Zhai, Ruiji Fu, Ming Liu, Yangqiu Song, Zhongyuan Wang, Bing Qin

In this paper, we propose Kuaipedia, a large-scale multi-modal encyclopedia consisting of items, aspects, and short videos lined to them, which was extracted from billions of videos of Kuaishou (Kwai), a well-known short-video platform in China.

Entity Linking Entity Typing

RaP: Redundancy-aware Video-language Pre-training for Text-Video Retrieval

1 code implementation13 Oct 2022 Xing Wu, Chaochen Gao, Zijia Lin, Zhongyuan Wang, Jizhong Han, Songlin Hu

Sparse sampling is also likely to miss important frames corresponding to some text portions, resulting in textual redundancy.

Contrastive Learning Retrieval +1

Bridging CLIP and StyleGAN through Latent Alignment for Image Editing

no code implementations10 Oct 2022 Wanfeng Zheng, Qiang Li, Xiaoyan Guo, Pengfei Wan, Zhongyuan Wang

More specifically, our efforts consist of three parts: 1) a data-free training strategy to train latent mappers to bridge the latent space of CLIP and StyleGAN; 2) for more precise mapping, temporal relative consistency is proposed to address the knowledge distribution bias problem among different latent spaces; 3) to refine the mapped latent in s space, adaptive style mixing is also proposed.

Image Manipulation Language Modelling +1

InfoCSE: Information-aggregated Contrastive Learning of Sentence Embeddings

2 code implementations8 Oct 2022 Xing Wu, Chaochen Gao, Zijia Lin, Jizhong Han, Zhongyuan Wang, Songlin Hu

Contrastive learning has been extensively studied in sentence embedding learning, which assumes that the embeddings of different views of the same sentence are closer.

Contrastive Learning Language Modelling +4

TokenFlow: Rethinking Fine-grained Cross-modal Alignment in Vision-Language Retrieval

no code implementations28 Sep 2022 Xiaohan Zou, Changqiao Wu, Lele Cheng, Zhongyuan Wang

Most existing methods in vision-language retrieval match two modalities by either comparing their global feature vectors which misses sufficient information and lacks interpretability, detecting objects in images or videos and aligning the text with fine-grained features which relies on complicated model designs, or modeling fine-grained interaction via cross-attention upon visual and textual tokens which suffers from inferior efficiency.

Retrieval Text Retrieval +1

ConTextual Masked Auto-Encoder for Dense Passage Retrieval

2 code implementations16 Aug 2022 Xing Wu, Guangyuan Ma, Meng Lin, Zijia Lin, Zhongyuan Wang, Songlin Hu

Dense passage retrieval aims to retrieve the relevant passages of a query from a large corpus based on dense representations (i. e., vectors) of the query and the passages.

Passage Retrieval Retrieval

Magic ELF: Image Deraining Meets Association Learning and Transformer

1 code implementation21 Jul 2022 Kui Jiang, Zhongyuan Wang, Chen Chen, Zheng Wang, Laizhong Cui, Chia-Wen Lin

Convolutional neural network (CNN) and Transformer have achieved great success in multimedia applications.

Rain Removal

Real-time End-to-End Video Text Spotter with Contrastive Representation Learning

no code implementations18 Jul 2022 Wejia Wu, Zhuang Li, Jiahong Li, Chunhua Shen, Hong Zhou, Size Li, Zhongyuan Wang, Ping Luo

Our contributions are three-fold: 1) CoText simultaneously address the three tasks (e. g., text detection, tracking, recognition) in a real-time end-to-end trainable framework.

Contrastive Learning Representation Learning +1

Deepfake Face Traceability with Disentangling Reversing Network

no code implementations8 Jul 2022 Jiaxin Ai, Zhongyuan Wang, Baojin Huang, Zhen Han

Deepfake face not only violates the privacy of personal identity, but also confuses the public and causes huge social harm.

DeepFake Detection Face Swapping

Diagnosing Ensemble Few-Shot Classifiers

no code implementations9 Jun 2022 Weikai Yang, Xi Ye, Xingxing Zhang, Lanxi Xiao, Jiazhi Xia, Zhongyuan Wang, Jun Zhu, Hanspeter Pfister, Shixia Liu

The base learners and labeled samples (shots) in an ensemble few-shot classifier greatly affect the model performance.

ITTR: Unpaired Image-to-Image Translation with Transformers

no code implementations30 Mar 2022 Wanfeng Zheng, Qiang Li, Guoxin Zhang, Pengfei Wan, Zhongyuan Wang

Unpaired image-to-image translation is to translate an image from a source domain to a target domain without paired training data.

Image-to-Image Translation Translation

Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing

1 code implementation CVPR 2022 Zhuo Wang, Zezheng Wang, Zitong Yu, Weihong Deng, Jiahong Li, Tingting Gao, Zhongyuan Wang

A novel Shuffled Style Assembly Network (SSAN) is proposed to extract and reassemble different content and style features for a stylized feature space.

Contrastive Learning Domain Generalization +1

Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks

1 code implementation ACL 2022 Xing Wu, Chaochen Gao, Meng Lin, Liangjun Zang, Zhongyuan Wang, Songlin Hu

Before entering the neural network, a token is generally converted to the corresponding one-hot representation, which is a discrete distribution of the vocabulary.

Data Augmentation Language Modelling +2

Contrastive Learning of Semantic and Visual Representations for Text Tracking

no code implementations30 Dec 2021 Zhuang Li, Weijia Wu, Mike Zheng Shou, Jiahong Li, Size Li, Zhongyuan Wang, Hong Zhou

Semantic representation is of great benefit to the video text tracking(VTT) task that requires simultaneously classifying, detecting, and tracking texts in the video.

Contrastive Learning

DistilCSE: Effective Knowledge Distillation For Contrastive Sentence Embeddings

1 code implementation10 Dec 2021 Chaochen Gao, Xing Wu, Peng Wang, Jue Wang, Liangjun Zang, Zhongyuan Wang, Songlin Hu

To tackle that, we propose an effective knowledge distillation framework for contrastive sentence embeddings, termed DistilCSE.

Contrastive Learning Knowledge Distillation +4

whu-nercms at trecvid2021:instance search task

no code implementations30 Oct 2021 Yanrui Niu, Jingyao Yang, Ankang Lu, Baojin Huang, Yue Zhang, Ji Huang, Shishi Wen, Dongshu Xu, Chao Liang, Zhongyuan Wang, Jun Chen

We will make a brief introduction of the experimental methods and results of the WHU-NERCMS in the TRECVID2021 in the paper.

Action Detection Face Detection +5

TANet: A new Paradigm for Global Face Super-resolution via Transformer-CNN Aggregation Network

no code implementations16 Sep 2021 Yuanzhi Wang, Tao Lu, Yanduo Zhang, Junjun Jiang, JiaMing Wang, Zhongyuan Wang, Jiayi Ma

Recently, face super-resolution (FSR) methods either feed whole face image into convolutional neural networks (CNNs) or utilize extra facial priors (e. g., facial parsing maps, facial landmarks) to focus on facial structure, thereby maintaining the consistency of the facial structure while restoring facial details.

Face Reconstruction Super-Resolution

ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding

2 code implementations COLING 2022 Xing Wu, Chaochen Gao, Liangjun Zang, Jizhong Han, Zhongyuan Wang, Songlin Hu

Unsup-SimCSE takes dropout as a minimal data augmentation method, and passes the same input sentence to a pre-trained Transformer encoder (with dropout turned on) twice to obtain the two corresponding embeddings to build a positive pair.

Contrastive Learning Data Augmentation +4

CAT: Cross Attention in Vision Transformer

1 code implementation10 Jun 2021 Hezheng Lin, Xing Cheng, Xiangyu Wu, Fan Yang, Dong Shen, Zhongyuan Wang, Qing Song, Wei Yuan

In this paper, we propose a new attention mechanism in Transformer termed Cross Attention, which alternates attention inner the image patch instead of the whole image to capture local information and apply attention between image patches which are divided from single-channel feature maps capture global information.

Omniscient Video Super-Resolution

no code implementations ICCV 2021 Peng Yi, Zhongyuan Wang, Kui Jiang, Junjun Jiang, Tao Lu, Xin Tian, Jiayi Ma

Most recent video super-resolution (SR) methods either adopt an iterative manner to deal with low-resolution (LR) frames from a temporally sliding window, or leverage the previously estimated SR output to help reconstruct the current frame recurrently.

Video Super-Resolution

Degrade is Upgrade: Learning Degradation for Low-light Image Enhancement

1 code implementation19 Mar 2021 Kui Jiang, Zhongyuan Wang, Zheng Wang, Chen Chen, Peng Yi, Tao Lu, Chia-Wen Lin

Different from existing methods tending to accomplish the relighting task directly by ignoring the fidelity and naturalness recovery, we investigate the intrinsic degradation and relight the low-light image while refining the details and color in two steps.

Low-Light Image Enhancement

Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection

no code implementations CVPR 2021 Jiaming Li, Hongtao Xie, Jiahong Li, Zhongyuan Wang, Yongdong Zhang

Face forgery detection is raising ever-increasing interest in computer vision since facial manipulation technologies cause serious worries.

Metric Learning for Anti-Compression Facial Forgery Detection

no code implementations15 Mar 2021 Shenhao Cao, Qin Zou, Xiuqing Mao, Zhongyuan Wang

Detecting facial forgery images and videos is an increasingly important topic in multimedia forensics.

Metric Learning

When Face Recognition Meets Occlusion: A New Benchmark

1 code implementation4 Mar 2021 Baojin Huang, Zhongyuan Wang, Guangcheng Wang, Kui Jiang, Kangli Zeng, Zhen Han, Xin Tian, Yuhong Yang

In particular, we first collect a variety of glasses and masks as occlusion, and randomly combine the occlusion attributes (occlusion objects, textures, and colors) to achieve a large number of more realistic occlusion types.

Face Recognition

Converse, Focus and Guess -- Towards Multi-Document Driven Dialogue

1 code implementation4 Feb 2021 Han Liu, Caixia Yuan, Xiaojie Wang, Yushu Yang, Huixing Jiang, Zhongyuan Wang

We propose a novel task, Multi-Document Driven Dialogue (MD3), in which an agent can guess the target document that the user is interested in by leading a dialogue.

Learn with Noisy Data via Unsupervised Loss Correction for Weakly Supervised Reading Comprehension

no code implementations COLING 2020 Xuemiao Zhang, Kun Zhou, Sirui Wang, Fuzheng Zhang, Zhongyuan Wang, Junfei Liu

Weakly supervised machine reading comprehension (MRC) task is practical and promising for its easily available and massive training data, but inevitablely introduces noise.

Machine Reading Comprehension

Face Hallucination via Split-Attention in Split-Attention Network

1 code implementation22 Oct 2020 Tao Lu, Yuanzhi Wang, Yanduo Zhang, Yu Wang, Wei Liu, Zhongyuan Wang, Junjun Jiang

However, most of them fail to take into account the overall facial profile and fine texture details simultaneously, resulting in reduced naturalness and fidelity of the reconstructed face, and further impairing the performance of downstream tasks (e. g., face detection, facial recognition).

Face Detection Face Hallucination +3

Query-aware Tip Generation for Vertical Search

no code implementations19 Oct 2020 Yang Yang, Junmei Hao, Canjia Li, Zili Wang, Jingang Wang, Fuzheng Zhang, Rao Fu, Peixu Hou, Gong Zhang, Zhongyuan Wang

Existing work on tip generation does not take query into consideration, which limits the impact of tips in search scenarios.

Decision Making

Answer-Driven Visual State Estimator for Goal-Oriented Visual Dialogue

1 code implementation1 Oct 2020 Zipeng Xu, Fangxiang Feng, Xiaojie Wang, Yushu Yang, Huixing Jiang, Zhongyuan Wang

In this paper, we propose an Answer-Driven Visual State Estimator (ADVSE) to impose the effects of different answers on visual states.

Question Generation Question-Generation +1

Leveraging Historical Interaction Data for Improving Conversational Recommender System

no code implementations19 Aug 2020 Kun Zhou, Wayne Xin Zhao, Hui Wang, Sirui Wang, Fuzheng Zhang, Zhongyuan Wang, Ji-Rong Wen

Most of the existing CRS methods focus on learning effective preference representations for users from conversation data alone.

Recommendation Systems

S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization

2 code implementations18 Aug 2020 Kun Zhou, Hui Wang, Wayne Xin Zhao, Yutao Zhu, Sirui Wang, Fuzheng Zhang, Zhongyuan Wang, Ji-Rong Wen

To tackle this problem, we propose the model S^3-Rec, which stands for Self-Supervised learning for Sequential Recommendation, based on the self-attentive neural architecture.

Self-Supervised Learning Sequential Recommendation

Learning Inverse Rendering of Faces from Real-world Videos

1 code implementation26 Mar 2020 Yuda Qiu, Zhangyang Xiong, Kai Han, Zhongyuan Wang, Zixiang Xiong, Xiaoguang Han

To alleviate this problem, we propose a weakly supervised training approach to train our model on real face videos, based on the assumption of consistency of albedo and normal across different frames, thus bridging the gap between real and synthetic face images.

Inverse Rendering

Multi-Scale Progressive Fusion Network for Single Image Deraining

2 code implementations CVPR 2020 Kui Jiang, Zhongyuan Wang, Peng Yi, Chen Chen, Baojin Huang, Yimin Luo, Jiayi Ma, Junjun Jiang

In this work, we explore the multi-scale collaborative representation for rain streaks from the perspective of input image scales and hierarchical deep features in a unified framework, termed multi-scale progressive fusion network (MSPFN) for single image rain streak removal.

Single Image Deraining

Masked Face Recognition Dataset and Application

3 code implementations20 Mar 2020 Zhongyuan Wang, Guangcheng Wang, Baojin Huang, Zhangyang Xiong, Qi Hong, Hao Wu, Peng Yi, Kui Jiang, Nanxi Wang, Yingjiao Pei, Heling Chen, Yu Miao, Zhibing Huang, Jinbi Liang

These datasets are freely available to industry and academia, based on which various applications on masked faces can be developed.

Face Detection Face Recognition

An End-to-End Network for Co-Saliency Detection in One Single Image

no code implementations25 Oct 2019 Yuanhao Yue, Qin Zou, Hongkai Yu, Qian Wang, Zhongyuan Wang, Song Wang

Co-saliency detection within a single image is a common vision problem that has received little attention and has not yet been well addressed.

Co-Salient Object Detection Saliency Prediction

Earlier Attention? Aspect-Aware LSTM for Aspect-Based Sentiment Analysis

no code implementations19 May 2019 Bowen Xing, Lejian Liao, Dandan song, Jingang Wang, Fuzheng Zhang, Zhongyuan Wang, He-Yan Huang

This paper proposes a novel variant of LSTM, termed as aspect-aware LSTM (AA-LSTM), which incorporates aspect information into LSTM cells in the context modeling stage before the attention mechanism.

Aspect-Based Sentiment Analysis (ABSA)

SuperPCA: A Superpixelwise PCA Approach for Unsupervised Feature Extraction of Hyperspectral Imagery

1 code implementation26 Jun 2018 Junjun Jiang, Jiayi Ma, Chen Chen, Zhongyuan Wang, Zhihua Cai, Lizhe Wang

(1) Unlike the traditional PCA method based on a whole image, SuperPCA takes into account the diversity in different homogeneous regions, that is, different regions should have different projections.

Dimensionality Reduction General Classification

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