Search Results for author: Yujiu Yang

Found 42 papers, 20 papers with code

Sparse Adversarial Attack via Perturbation Factorization

1 code implementation ECCV 2020 Yanbo Fan, Baoyuan Wu, Tuanhui Li, Yong Zhang, Mingyang Li, Zhifeng Li, Yujiu Yang

Based on this factorization, we formulate the sparse attack problem as a mixed integer programming (MIP) to jointly optimize the binary selection factors and continuous perturbation magnitudes of all pixels, with a cardinality constraint on selection factors to explicitly control the degree of sparsity.

Adversarial Attack

MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering

1 code implementation Findings (EMNLP) 2021 Junjie Wang, Yatai Ji, Jiaqi Sun, Yujiu Yang, Tetsuya Sakai

On the other hand, trilinear models such as the CTI model efficiently utilize the inter-modality information between answers, questions, and images, while ignoring intra-modality information.

Multiple-choice Question Answering +2

Learning Adaptive Warping for Real-World Rolling Shutter Correction

1 code implementation29 Apr 2022 Mingdeng Cao, Zhihang Zhong, Jiahao Wang, Yinqiang Zheng, Yujiu Yang

This paper proposes the first real-world rolling shutter (RS) correction dataset, BS-RSC, and a corresponding model to correct the RS frames in a distorted video.

EmpHi: Generating Empathetic Responses with Human-like Intents

1 code implementation26 Apr 2022 Mao Yan Chen, Siheng Li, Yujiu Yang

To address the bias of the empathetic intents distribution between empathetic dialogue models and humans, we propose a novel model to generate empathetic responses with human-consistent empathetic intents, EmpHi for short.

MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment

1 code implementation19 Apr 2022 Sidi Yang, Tianhe Wu, Shuwei Shi, Shanshan Lao, Yuan Gong, Mingdeng Cao, Jiahao Wang, Yujiu Yang

No-Reference Image Quality Assessment (NR-IQA) aims to assess the perceptual quality of images in accordance with human subjective perception.

No-Reference Image Quality Assessment

VDTR: Video Deblurring with Transformer

1 code implementation17 Apr 2022 Mingdeng Cao, Yanbo Fan, Yong Zhang, Jue Wang, Yujiu Yang

For multi-frame temporal modeling, we adapt Transformer to fuse multiple spatial features efficiently.

Deblurring Frame +1

High-fidelity GAN Inversion with Padding Space

1 code implementation21 Mar 2022 Qingyan Bai, Yinghao Xu, Jiapeng Zhu, Weihao Xia, Yujiu Yang, Yujun Shen

In this work, we propose to involve the padding space of the generator to complement the latent space with spatial information.

Image Manipulation

StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN

1 code implementation8 Mar 2022 Fei Yin, Yong Zhang, Xiaodong Cun, Mingdeng Cao, Yanbo Fan, Xuan Wang, Qingyan Bai, Baoyuan Wu, Jue Wang, Yujiu Yang

Our framework elevates the resolution of the synthesized talking face to 1024*1024 for the first time, even though the training dataset has a lower resolution.

Facial Editing Talking Face Generation +1

Context Enhanced Short Text Matching using Clickthrough Data

no code implementations3 Mar 2022 Mao Yan Chen, Haiyun Jiang, Yujiu Yang

The short text matching task employs a model to determine whether two short texts have the same semantic meaning or intent.

Text Matching

STaR: Knowledge Graph Embedding by Scaling, Translation and Rotation

no code implementations15 Feb 2022 Jiayi Li, Yujiu Yang

Therefore, we propose a corresponding bilinear model Scaling Translation and Rotation (STaR) consisting of the above two parts.

Knowledge Graph Embedding Link Prediction +1

Adder Attention for Vision Transformer

no code implementations NeurIPS 2021 Han Shu, Jiahao Wang, Hanting Chen, Lin Li, Yujiu Yang, Yunhe Wang

With the new operation, vision transformers constructed using additions can also provide powerful feature representations.

Identity-Guided Face Generation with Multi-modal Contour Conditions

no code implementations10 Oct 2021 Qingyan Bai, Weihao Xia, Fei Yin, Yujiu Yang

Concretely, we propose a novel dual-encoder architecture, in which an identity encoder extracts the identity-related feature, accompanied by a main encoder to obtain the rough contour information and further fuse all the information together.

Face Generation

Guiding Topic Flows in the Generative Chatbot by Enhancing the ConceptNet with the Conversation Corpora

no code implementations12 Sep 2021 Pengda Si, Yao Qiu, Jinchao Zhang, Yujiu Yang

Further analysis individually proves the effectiveness of the enhanced concept graph and the Edge-Transformer architecture.


Real-time Human-Centric Segmentation for Complex Video Scenes

1 code implementation16 Aug 2021 Ran Yu, Chenyu Tian, Weihao Xia, Xinyuan Zhao, Haoqian Wang, Yujiu Yang

To alleviate this problem, we propose a mechanism named Inner Center Sampling to improve the accuracy of instance segmentation.

Instance Segmentation Semantic Segmentation +1

PoseDet: Fast Multi-Person Pose Estimation Using Pose Embedding

1 code implementation22 Jul 2021 Chenyu Tian, Ran Yu, Xinyuan Zhao, Weihao Xia, Haoqian Wang, Yujiu Yang

This simple framework achieves an unprecedented speed and a competitive accuracy on the COCO benchmark compared with state-of-the-art methods.

Multi-Person Pose Estimation

Augmenting Anchors by the Detector Itself

1 code implementation28 May 2021 Xiaopei Wan, Guoqiu Li, Yujiu Yang, Zhenhua Guo

Furthermore, AADI is a learning-based anchor augmentation method, but it does not add any parameters or hyper-parameters, which is beneficial for research and downstream tasks.

Object Detection

Coarse-to-Fine Searching for Efficient Generative Adversarial Networks

no code implementations19 Apr 2021 Jiahao Wang, Han Shu, Weihao Xia, Yujiu Yang, Yunhe Wang

This paper studies the neural architecture search (NAS) problem for developing efficient generator networks.

Image Generation Neural Architecture Search

Towards Open-World Text-Guided Face Image Generation and Manipulation

2 code implementations18 Apr 2021 Weihao Xia, Yujiu Yang, Jing-Hao Xue, Baoyuan Wu

To be specific, we propose a brand new paradigm of text-guided image generation and manipulation based on the superior characteristics of a pretrained GAN model.

Language Modelling Semantic Segmentation +1

AACP: Model Compression by Accurate and Automatic Channel Pruning

no code implementations31 Jan 2021 Lanbo Lin, Yujiu Yang, Zhenhua Guo

Firstly, AACP represents the structure of a model as a structure vector and introduces a pruning step vector to control the compressing granularity of each layer.

Model Compression Neural Architecture Search

Augmenting Proposals by the Detector Itself

no code implementations28 Jan 2021 Xiaopei Wan, Zhenhua Guo, Chao He, Yujiu Yang, Fangbo Tao

Lacking enough high quality proposals for RoI box head has impeded two-stage and multi-stage object detectors for a long time, and many previous works try to solve it via improving RPN's performance or manually generating proposals from ground truth.

GAN Inversion: A Survey

1 code implementation14 Jan 2021 Weihao Xia, Yulun Zhang, Yujiu Yang, Jing-Hao Xue, Bolei Zhou, Ming-Hsuan Yang

GAN inversion aims to invert a given image back into the latent space of a pretrained GAN model, for the image to be faithfully reconstructed from the inverted code by the generator.

Image Manipulation Image Restoration

DT-QDC: A Dataset for Question Comprehension in Online Test

no code implementations COLING 2020 Sijin Wu, Yujiu Yang, Nicholas Yung, Zhengchen Shen, Zeyang Lei

With the transformation of education from the traditional classroom environment to online education and assessment, it is more and more important to accurately assess the difficulty of questions than ever.

Controllable Continuous Gaze Redirection

1 code implementation9 Oct 2020 Weihao Xia, Yujiu Yang, Jing-Hao Xue, Wensen Feng

The encoder maps images into a well-disentangled and hierarchically-organized latent space.

gaze redirection

Cognitive Representation Learning of Self-Media Online Article Quality

no code implementations13 Aug 2020 Yiru Wang, Shen Huang, Gongfu Li, Qiang Deng, Dongliang Liao, Pengda Si, Yujiu Yang, Jin Xu

The automatic quality assessment of self-media online articles is an urgent and new issue, which is of great value to the online recommendation and search.

Representation Learning

HGCN4MeSH: Hybrid Graph Convolution Network for MeSH Indexing

no code implementations ACL 2020 Miaomiao Yu, Yujiu Yang, Chenhui Li

Recently deep learning has been used in Medical subject headings (MeSH) indexing to reduce the time and monetary cost by manual annotation, including DeepMeSH, TextCNN, etc.

Extreme Multi-Label Classification Multi-Label Classification +1

Towards Multimodal Response Generation with Exemplar Augmentation and Curriculum Optimization

no code implementations26 Apr 2020 Zeyang Lei, Zekang Li, Jinchao Zhang, Fandong Meng, Yang Feng, Yujiu Yang, Cheng Niu, Jie zhou

Furthermore, to facilitate the convergence of Gaussian mixture prior and posterior distributions, we devise a curriculum optimization strategy to progressively train the model under multiple training criteria from easy to hard.

Response Generation

HSCJN: A Holistic Semantic Constraint Joint Network for Diverse Response Generation

no code implementations1 Dec 2019 Yiru Wang, Pengda Si, Zeyang Lei, Guangxu Xun, Yujiu Yang

The sequence-to-sequence (Seq2Seq) model generates target words iteratively given the previously observed words during decoding process, which results in the loss of the holistic semantics in the target response and the complete semantic relationship between responses and dialogue histories.

Response Generation

Self-supervised Feature Learning for 3D Medical Images by Playing a Rubik's Cube

no code implementations5 Oct 2019 Xinrui Zhuang, Yuexiang Li, Yifan Hu, Kai Ma, Yujiu Yang, Yefeng Zheng

Witnessed the development of deep learning, increasing number of studies try to build computer aided diagnosis systems for 3D volumetric medical data.

Brain Tumor Segmentation Self-Supervised Learning +1

Multi-glance Reading Model for Text Understanding

no code implementations WS 2018 Pengcheng Zhu, Yujiu Yang, Wenqiang Gao, Yi Liu

Based on the multi-glance mechanism, we design two types of recurrent neural network models for repeated reading: Glance Cell Model (GCM) and Glance Gate Model (GGM).

Document Classification Machine Translation +2

Faster Spatially Regularized Correlation Filters for Visual Tracking

no code implementations1 Jun 2017 Xiaoxiang Hu, Yujiu Yang

Our approach achieves equivalent performance to the baseline tracker SRDCF on all three datasets.

Visual Tracking

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