1 code implementation • COLING 2022 • Zhongyuan Wang, YiXuan Wang, Shaolei Wang, Wanxiang Che
Supervised methods have achieved remarkable results in disfluency detection.
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.
no code implementations • 14 Mar 2023 • Chunyu Qiang, Peng Yang, Hao Che, Ying Zhang, Xiaorui Wang, Zhongyuan Wang
Cross-speaker style transfer in speech synthesis aims at transferring a style from source speaker to synthesized speech of a target speaker's timbre.
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.
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.
no code implementations • 13 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.
no code implementations • 8 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.
1 code implementation • The 33rd British Machine Vision Conference 2022 • Ji Huang, Chao Liang, Yue Zhang, Zhongyuan Wang, Chunjie Zhang
Existing RA work can be generally divided into unsupervised methods and fully-supervised methods.
no code implementations • 19 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.
no code implementations • 17 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.
1 code implementation • 28 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.
1 code implementation • 13 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.
no code implementations • 10 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.
2 code implementations • 8 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.
no code implementations • 28 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.
2 code implementations • 16 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.
1 code implementation • 21 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.
no code implementations • 18 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.
no code implementations • 8 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.
no code implementations • 9 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.
no code implementations • 31 May 2022 • Liang Hou, Qi Cao, Yige Yuan, Songtao Zhao, Chongyang Ma, Siyuan Pan, Pengfei Wan, Zhongyuan Wang, HuaWei Shen, Xueqi Cheng
Training generative adversarial networks (GANs) with limited data is challenging because discriminator is prone to overfitting.
no code implementations • 30 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.
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.
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.
no code implementations • 30 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.
1 code implementation • 10 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.
1 code implementation • 24 Nov 2021 • Zezheng Wang, Zitong Yu, Xun Wang, Yunxiao Qin, Jiahong Li, Chenxu Zhao, Zhen Lei, Xin Liu, Size Li, Zhongyuan Wang
Face anti-spoofing (FAS) plays a crucial role in securing face recognition systems.
no code implementations • 30 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.
no code implementations • 16 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.
2 code implementations • COLING 2022 • Xing Wu, Chaochen Gao, Yipeng Su, Jizhong Han, Zhongyuan Wang, Songlin Hu
Contrastive learning has been gradually applied to learn high-quality 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.
1 code implementation • 11 Jun 2021 • Xing Cheng, Hezheng Lin, Xiangyu Wu, Fan Yang, Dong Shen, Zhongyuan Wang, Nian Shi, Honglin Liu
The task of multi-label image classification is to recognize all the object labels presented in an image.
Ranked #12 on Multi-Label Classification on MS-COCO
1 code implementation • 10 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.
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.
no code implementations • ICCV 2021 • Song Liu, Haoqi Fan, Shengsheng Qian, Yiru Chen, Wenkui Ding, Zhongyuan Wang
Video-Text Retrieval has been a hot research topic with the growth of multimedia data on the internet.
1 code implementation • 19 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.
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.
no code implementations • 15 Mar 2021 • Shenhao Cao, Qin Zou, Xiuqing Mao, Zhongyuan Wang
Detecting facial forgery images and videos is an increasingly important topic in multimedia forensics.
1 code implementation • 4 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.
1 code implementation • 4 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.
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.
no code implementations • COLING 2020 • Keqing He, Shuyu Lei, Yushu Yang, Huixing Jiang, Zhongyuan Wang
Slot filling and intent detection are two major tasks for spoken language understanding.
1 code implementation • EMNLP 2020 • Shaolei Wang, Zhongyuan Wang, Wanxiang Che, Ting Liu
Most existing approaches to disfluency detection heavily rely on human-annotated corpora, which is expensive to obtain in practice.
1 code implementation • 22 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).
no code implementations • 19 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.
no code implementations • 1 Oct 2020 • Shaolei Wang, Baoxin Wang, Jiefu Gong, Zhongyuan Wang, Xiao Hu, Xingyi Duan, Zizhuo Shen, Gang Yue, Ruiji Fu, Dayong Wu, Wanxiang Che, Shijin Wang, Guoping Hu, Ting Liu
Grammatical error diagnosis is an important task in natural language processing.
1 code implementation • 1 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.
no code implementations • 19 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.
2 code implementations • 18 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.
1 code implementation • 26 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.
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.
Ranked #6 on Single Image Deraining on Test2800
3 code implementations • 20 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.
no code implementations • 25 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.
no code implementations • 19 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.
5 code implementations • 11 May 2019 • Hongwei Wang, Fuzheng Zhang, Mengdi Zhang, Jure Leskovec, Miao Zhao, Wenjie Li, Zhongyuan Wang
Here we propose Knowledge-aware Graph Neural Networks with Label Smoothness regularization (KGNN-LS) to provide better recommendations.
Ranked #1 on Recommendation Systems on Dianping-Food
1 code implementation • 26 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.
no code implementations • COLING 2016 • Taesung Lee, Seung-won Hwang, Zhongyuan Wang
Besides providing the relevant information, amusing users has been an important role of the web.