Search Results for author: Xiao-Yu Zhang

Found 32 papers, 12 papers with code

Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detection

1 code implementation15 Mar 2024 Yuting Xu, Jian Liang, Lijun Sheng, Xiao-Yu Zhang

The deepfake threats to society and cybersecurity have provoked significant public apprehension, driving intensified efforts within the realm of deepfake video detection.

DeepFake Detection Face Swapping

Exploring Straighter Trajectories of Flow Matching with Diffusion Guidance

no code implementations28 Nov 2023 Siyu Xing, Jie Cao, Huaibo Huang, Xiao-Yu Zhang, Ran He

First, we propose a coupling strategy to straighten trajectories, creating couplings between image and noise samples under diffusion model guidance.

Learning Cross-modality Information Bottleneck Representation for Heterogeneous Person Re-Identification

no code implementations29 Aug 2023 Haichao Shi, Mandi Luo, Xiao-Yu Zhang, Ran He

Visible-Infrared person re-identification (VI-ReID) is an important and challenging task in intelligent video surveillance.

Person Re-Identification

Rumor Detection with Diverse Counterfactual Evidence

1 code implementation18 Jul 2023 Kaiwei Zhang, Junchi Yu, Haichao Shi, Jian Liang, Xiao-Yu Zhang

Our intuition is to exploit the diverse counterfactual evidence of an event graph to serve as multi-view interpretations, which are further aggregated for robust rumor detection results.

counterfactual Point Processes

Cross Architecture Distillation for Face Recognition

no code implementations26 Jun 2023 Weisong Zhao, Xiangyu Zhu, Zhixiang He, Xiao-Yu Zhang, Zhen Lei

Transformers have emerged as the superior choice for face recognition tasks, but their insufficient platform acceleration hinders their application on mobile devices.

Face Recognition Knowledge Distillation

Grouped Knowledge Distillation for Deep Face Recognition

no code implementations10 Apr 2023 Weisong Zhao, Xiangyu Zhu, Kaiwen Guo, Xiao-Yu Zhang, Zhen Lei

Therefore, we seek to probe the target logits to extract the primary knowledge related to face identity, and discard the others, to make the distillation more achievable for the student network.

Face Recognition Knowledge Distillation

Masked Relation Learning for DeepFake Detection

2 code implementations 2023 2023 Ziming Yang, Jian Liang, Yuting Xu, Xiao-Yu Zhang, Ran He

A relation learning module masks partial correlations between regions to reduce redundancy and then propagates the relational information across regions to capture the irregularity from a global view of the graph.

Binary Classification DeepFake Detection +3

MetaTKG: Learning Evolutionary Meta-Knowledge for Temporal Knowledge Graph Reasoning

no code implementations2 Feb 2023 Yuwei Xia, Mengqi Zhang, Qiang Liu, Shu Wu, Xiao-Yu Zhang

Most existing works focus on exploring evolutionary information in history to obtain effective temporal embeddings for entities and relations, but they ignore the variation in evolution patterns of facts, which makes them struggle to adapt to future data with different evolution patterns.

Knowledge Graphs Meta-Learning

Unsupervised Domain Adaptation GAN Inversion for Image Editing

no code implementations22 Nov 2022 Siyu Xing, Chen Gong, Hewei Guo, Xiao-Yu Zhang, Xinwen Hou, Yu Liu

In this paper, we resolve this problem by introducing Unsupervised Domain Adaptation (UDA) into the Inversion process, namely UDA-Inversion, for both high-quality and low-quality image inversion and editing.

Image Reconstruction Unsupervised Domain Adaptation

Heterogeneous Face Recognition via Face Synthesis with Identity-Attribute Disentanglement

no code implementations10 Jun 2022 Ziming Yang, Jian Liang, Chaoyou Fu, Mandi Luo, Xiao-Yu Zhang

Secondly, we devise a face synthesis module (FSM) to generate a large number of images with stochastic combinations of disentangled identities and attributes for enriching the attribute diversity of synthetic images.

Attribute Data Augmentation +4

Action Shuffling for Weakly Supervised Temporal Localization

no code implementations10 May 2021 Xiao-Yu Zhang, Haichao Shi, Changsheng Li, Xinchu Shi

Weakly supervised action localization is a challenging task with extensive applications, which aims to identify actions and the corresponding temporal intervals with only video-level annotations available.

Action Localization Temporal Localization +1

Stereo Plane SLAM Based on Intersecting Lines

1 code implementation19 Aug 2020 Xiao-Yu Zhang, Wei Wang, Xianyu Qi, Ziwei Liao

Adding such plane features in stereo SLAM system reduces the drift error and refines the performance.

Stereo Matching

On Deep Unsupervised Active Learning

no code implementations28 Jul 2020 Changsheng Li, Handong Ma, Zhao Kang, Ye Yuan, Xiao-Yu Zhang, Guoren Wang

Unsupervised active learning has attracted increasing attention in recent years, where its goal is to select representative samples in an unsupervised setting for human annotating.

Active Learning Decoder

Object-oriented SLAM using Quadrics and Symmetry Properties for Indoor Environments

1 code implementation11 Apr 2020 Ziwei Liao, Wei Wang, Xianyu Qi, Xiao-Yu Zhang, Lin Xue, Jianzhen Jiao, Ran Wei

As objects are often observed locally, the proposed algorithm uses the symmetrical properties of indoor artificial objects to estimate the occluded parts to obtain more accurate quadric parameters.

object-detection Object Detection

Unsupervised Annotation of Phenotypic Abnormalities via Semantic Latent Representations on Electronic Health Records

1 code implementation10 Nov 2019 Jingqing Zhang, Xiao-Yu Zhang, Kai Sun, Xian Yang, Chengliang Dai, Yike Guo

The extraction of phenotype information which is naturally contained in electronic health records (EHRs) has been found to be useful in various clinical informatics applications such as disease diagnosis.

Computational Efficiency

Integrated Multi-omics Analysis Using Variational Autoencoders: Application to Pan-cancer Classification

4 code implementations17 Aug 2019 Xiao-Yu Zhang, Jingqing Zhang, Kai Sun, Xian Yang, Chengliang Dai, Yike Guo

The training procedure of OmiVAE is comprised of an unsupervised phase without the classifier and a supervised phase with the classifier.

Classification Decision Making +3

Semi-supervised Compatibility Learning Across Categories for Clothing Matching

1 code implementation31 Jul 2019 Zekun Li, Zeyu Cui, Shu Wu, Xiao-Yu Zhang, Liang Wang

To achieve the alignment, we minimize the distances between distributions with unsupervised adversarial learning, and also the distances between some annotated compatible items which play the role of anchor points to help align.

Interaction-aware Kalman Neural Networks for Trajectory Prediction

no code implementations28 Feb 2019 Ce Ju, Zheng Wang, Cheng Long, Xiao-Yu Zhang, Gao Cong, Dong Eui Chang

Forecasting the motion of surrounding obstacles (vehicles, bicycles, pedestrians and etc.)

Robotics I.2.9; I.2.0

Dressing as a Whole: Outfit Compatibility Learning Based on Node-wise Graph Neural Networks

1 code implementation21 Feb 2019 Zeyu Cui, Zekun Li, Shu Wu, Xiao-Yu Zhang, Liang Wang

In this paper, we aim to investigate a practical problem of fashion recommendation by answering the question "which item should we select to match with the given fashion items and form a compatible outfit".

 Ranked #1 on Recommendation Systems on Polyvore (Accuracy metric)

Recommendation Systems

Socially Aware Kalman Neural Networks for Trajectory Prediction

no code implementations14 Sep 2018 Ce Ju, Zheng Wang, Xiao-Yu Zhang

Trajectory prediction is a critical technique in the navigation of robots and autonomous vehicles.

Autonomous Vehicles Trajectory Prediction

Synchronized Detection and Recovery of Steganographic Messages with Adversarial Learning

no code implementations31 Jan 2018 Haichao Shi, Xiao-Yu Zhang

To handle the problem of embedding secret messages into the specific medium, we design a novel adversarial modules to learn the steganographic algorithm, and simultaneously train three modules called generator, discriminator and steganalyzer.

SSGAN: Secure Steganography Based on Generative Adversarial Networks

no code implementations6 Jul 2017 Haichao Shi, Jing Dong, Wei Wang, Yinlong Qian, Xiao-Yu Zhang

Furthermore, a sophisticated steganalysis network is reconstructed for the discriminative network, and the network can better evaluate the performance of the generated images.


A Self-Paced Regularization Framework for Multi-Label Learning

no code implementations22 Mar 2016 Changsheng Li, Fan Wei, Junchi Yan, Weishan Dong, Qingshan Liu, Xiao-Yu Zhang, Hongyuan Zha

In this paper, we propose a novel multi-label learning framework, called Multi-Label Self-Paced Learning (MLSPL), in an attempt to incorporate the self-paced learning strategy into multi-label learning regime.

Multi-Label Learning

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