no code implementations • 8 Dec 2024 • Hao Chen, Hui Guo, Baochen Hu, Shu Hu, Jinrong Hu, Siwei Lyu, Xi Wu, Xin Wang
The rapid growth of social media has resulted in an explosion of online news content, leading to a significant increase in the spread of misleading or false information.
no code implementations • 7 Dec 2024 • Zihao Zhu, Hongbao Zhang, Guanzong Wu, Siwei Lyu, Baoyuan Wu
Then, the hierarchical inconsistency evaluation module provides a progressive evaluation procedure with a dynamic question-answer generation and evaluation strategy guided by the semantic graph, producing a hierarchical inconsistency evaluation graph (HIEG).
no code implementations • 2 Dec 2024 • Delong Zhu, Yuezun Li, Baoyuan Wu, Jiaran Zhou, Zhibo Wang, Siwei Lyu
The motivation stems from the reliance of most DeepFake methods on face detectors to automatically extract victim faces from videos for training or synthesis (testing).
no code implementations • 24 Oct 2024 • Zhaofeng Si, Shu Hu, Kaiyi Ji, Siwei Lyu
Meta-learning is a general approach to equip machine learning models with the ability to handle few-shot scenarios when dealing with many tasks.
no code implementations • 8 Oct 2024 • Yize Chen, Zhiyuan Yan, Siwei Lyu, Baoyuan Wu
To verify the effectiveness of this framework, we further present a practical implementation, where an automated forgery features generation, evaluation, and ranking procedure is designed for MFA module; an automated generation procedure of the fine-tuning dataset containing real and fake images with explanations based on top-ranked features is developed for SFS model; an external conventional deepfake detector focusing on blending artifact, which corresponds to a low detection capability in the pre-trained MLLM, is integrated for WFS module.
2 code implementations • 29 Sep 2024 • Zhenyu Zhou, Defang Chen, Can Wang, Chun Chen, Siwei Lyu
Diffusion-based generative models have demonstrated their powerful performance across various tasks, but this comes at a cost of the slow sampling speed.
1 code implementation • 28 Sep 2024 • Zheyuan Zhan, Defang Chen, Jian-Ping Mei, Zhenghe Zhao, Jiawei Chen, Chun Chen, Siwei Lyu, Can Wang
In this survey, we categorize existing works based on how conditions are integrated into the two fundamental components of diffusion-based modeling, i. e., the denoising network and the sampling process.
no code implementations • 29 Aug 2024 • Mian Zou, Baosheng Yu, Yibing Zhan, Siwei Lyu, Kede Ma
In this paper, we delve deeper into semantics-oriented multitask learning for DeepFake detection, leveraging the relationships among face semantics via joint embedding.
1 code implementation • 14 Aug 2024 • Wujie Sun, Defang Chen, Siwei Lyu, Genlang Chen, Chun Chen, Can Wang
Recent research on knowledge distillation has increasingly focused on logit distillation because of its simplicity, effectiveness, and versatility in model compression.
no code implementations • 8 Aug 2024 • Jingfu Yang, Peng Huang, Jing Hu, Shu Hu, Siwei Lyu, Xin Wang, Jun Guo, Xi Wu
The network is embedded with a nonlocal module to capture global information, while a 3D attention module is embedded to focus on the details of the lesion so that it can directly analyze the 3D lung CT and output the classification results.
no code implementations • 5 Aug 2024 • Ye Yao, Tingfeng Han, Shan Jia, Siwei Lyu
Image inpainting, which is the task of filling in missing areas in an image, is a common image editing technique.
no code implementations • 3 Jun 2024 • Mingzhen Huang, Jialing Cai, Shan Jia, Vishnu Suresh Lokhande, Siwei Lyu
This dataset is a benchmark for evaluating text-driven image editing methods in multifaceted scenarios.
1 code implementation • 28 May 2024 • Mihir Chauhan, Mohammad Abuzar Shaikh, Bina Ramamurthy, Mingchen Gao, Siwei Lyu, Sargur Srihari
We present SSL-HV: Self-Supervised Learning approaches applied to the task of Handwriting Verification.
2 code implementations • 18 May 2024 • Defang Chen, Zhenyu Zhou, Can Wang, Chunhua Shen, Siwei Lyu
Diffusion-based generative models use stochastic differential equations (SDEs) and their equivalent ordinary differential equations (ODEs) to establish a smooth connection between a complex data distribution and a tractable prior distribution.
no code implementations • 14 May 2024 • Mian Zou, Baosheng Yu, Yibing Zhan, Siwei Lyu, Kede Ma
In recent years, deep learning has greatly streamlined the process of generating realistic fake face images.
1 code implementation • 30 Apr 2024 • Cai Yu, Shan Jia, Xiaomeng Fu, Jin Liu, Jiahe Tian, Jiao Dai, Xi Wang, Siwei Lyu, Jizhong Han
With the rising prevalence of deepfakes, there is a growing interest in developing generalizable detection methods for various types of deepfakes.
1 code implementation • 28 Apr 2024 • Mingzhen Huang, Shan Jia, Zhou Zhou, Yan Ju, Jialing Cai, Siwei Lyu
In the battle against widespread online misinformation, a growing problem is text-image inconsistency, where images are misleadingly paired with texts with different intent or meaning.
1 code implementation • 19 Apr 2024 • Yan Ju, Chengzhe Sun, Shan Jia, Shuwei Hou, Zhaofeng Si, Soumyya Kanti Datta, Lipeng Ke, Riky Zhou, Anita Nikolich, Siwei Lyu
Furthermore, it serves as an evaluation and benchmarking platform for researchers in digital media forensics to compare the performance of multiple algorithms on the same input.
1 code implementation • 21 Mar 2024 • Shan Jia, Reilin Lyu, Kangran Zhao, Yize Chen, Zhiyuan Yan, Yan Ju, Chuanbo Hu, Xin Li, Baoyuan Wu, Siwei Lyu
DeepFakes, which refer to AI-generated media content, have become an increasing concern due to their use as a means for disinformation.
1 code implementation • 18 Jan 2024 • Soumyya Kanti Datta, Shan Jia, Siwei Lyu
A lip-syncing deepfake is a digitally manipulated video in which a person's lip movements are created convincingly using AI models to match altered or entirely new audio.
1 code implementation • CVPR 2024 • Zhiyuan Yan, Yuhao Luo, Siwei Lyu, Qingshan Liu, Baoyuan Wu
Deepfake detection faces a critical generalization hurdle, with performance deteriorating when there is a mismatch between the distributions of training and testing data.
no code implementations • 10 Nov 2023 • Jing Hu, Qinrui Fan, Shu Hu, Siwei Lyu, Xi Wu, Xin Wang
In the field of clinical medicine, computed tomography (CT) is an effective medical imaging modality for the diagnosis of various pathologies.
no code implementations • 5 Oct 2023 • Sneha Muppalla, Shan Jia, Siwei Lyu
Deepfakes are AI-generated media in which an image or video has been digitally modified.
no code implementations • 30 Sep 2023 • Shanmin Yang, Hui Guo, Shu Hu, Bin Zhu, Ying Fu, Siwei Lyu, Xi Wu, Xin Wang
Deepfake technology poses a significant threat to security and social trust.
no code implementations • 30 Sep 2023 • Chengming Feng, Jing Hu, Xin Wang, Shu Hu, Bin Zhu, Xi Wu, Hongtu Zhu, Siwei Lyu
Controlling the degree of stylization in the Neural Style Transfer (NST) is a little tricky since it usually needs hand-engineering on hyper-parameters.
2 code implementations • 24 Sep 2023 • Xin Wang, Ziwei Luo, Jing Hu, Chengming Feng, Shu Hu, Bin Zhu, Xi Wu, Hongtu Zhu, Xin Li, Siwei Lyu
The key feature in the RL-I2IT framework is to decompose a monolithic learning process into small steps with a lightweight model to progressively transform a source image successively to a target image.
1 code implementation • 10 Sep 2023 • Shu Hu, Zhenhuan Yang, Xin Wang, Yiming Ying, Siwei Lyu
Theoretically, we show that the learning objective of ORAT satisfies the $\mathcal{H}$-consistency in binary classification, which establishes it as a proper surrogate to adversarial 0/1 loss.
1 code implementation • 18 Aug 2023 • Yuanhao Zhai, Mingzhen Huang, Tianyu Luan, Lu Dong, Ifeoma Nwogu, Siwei Lyu, David Doermann, Junsong Yuan
In this paper, we propose ATOM (ATomic mOtion Modeling) to mitigate this problem, by decomposing actions into atomic actions, and employing a curriculum learning strategy to learn atomic action composition.
1 code implementation • 3 Aug 2023 • Cong Zhang, Honggang Qi, Shuhui Wang, Yuezun Li, Siwei Lyu
One straightforward way to address this issue is to simultaneous process multi-face by integrating face extraction and forgery detection in an end-to-end fashion by adapting advanced object detection architectures.
no code implementations • 2 Aug 2023 • Jiucui Lu, Jiaran Zhou, Junyu Dong, Bin Li, Siwei Lyu, Yuezun Li
The proposed ForensicsForest family is composed of three variants, which are {\em ForensicsForest}, {\em Hybrid ForensicsForest} and {\em Divide-and-Conquer ForensicsForest} respectively.
no code implementations • 27 Jul 2023 • Pu Sun, Honggang Qi, Yuezun Li, Siwei Lyu
In light of these two traces, our method can effectively expose DeepFakes by identifying them.
2 code implementations • NeurIPS 2023 • Zhiyuan Yan, Yong Zhang, Xinhang Yuan, Siwei Lyu, Baoyuan Wu
To fill this gap, we present the first comprehensive benchmark for deepfake detection, called DeepfakeBench, which offers three key contributions: 1) a unified data management system to ensure consistent input across all detectors, 2) an integrated framework for state-of-the-art methods implementation, and 3) standardized evaluation metrics and protocols to promote transparency and reproducibility.
1 code implementation • 29 Jun 2023 • Yan Ju, Shu Hu, Shan Jia, George H. Chen, Siwei Lyu
Despite the development of effective deepfake detectors in recent years, recent studies have demonstrated that biases in the data used to train these detectors can lead to disparities in detection accuracy across different races and genders.
no code implementations • 19 Apr 2023 • Hao Chen, Peng Zheng, Xin Wang, Shu Hu, Bin Zhu, Jinrong Hu, Xi Wu, Siwei Lyu
As growing usage of social media websites in the recent decades, the amount of news articles spreading online rapidly, resulting in an unprecedented scale of potentially fraudulent information.
1 code implementation • 14 Apr 2023 • Shan Jia, Mingzhen Huang, Zhou Zhou, Yan Ju, Jialing Cai, Siwei Lyu
To achieve this, we propose a new approach that leverages the DALL-E2 language-image model to automatically generate and splice masked regions guided by a text prompt.
1 code implementation • 19 Feb 2023 • Baoyuan Wu, Zihao Zhu, Li Liu, Qingshan Liu, Zhaofeng He, Siwei Lyu
Adversarial machine learning (AML) studies the adversarial phenomenon of machine learning, which may make inconsistent or unexpected predictions with humans.
no code implementations • 26 Jan 2023 • Yunxu Xie, Shu Hu, Xin Wang, Quanyu Liao, Bin Zhu, Xi Wu, Siwei Lyu
Existing adversarial attacks on object detection focus on attacking anchor-based detectors, which may not work well for anchor-free detectors.
no code implementations • CVPR 2023 • Mingzhen Huang, Xiaoxing Li, Jun Hu, Honghong Peng, Siwei Lyu
DETracker outperforms existing state-of-the-art method on the DogThruGlasses dataset and YouTube-Hand dataset.
1 code implementation • 16 Nov 2022 • Yan Ju, Shan Jia, Jialing Cai, Haiying Guan, Siwei Lyu
To address this issue, we propose a Global and Local Feature Fusion (GLFF) framework to learn rich and discriminative representations by combining multi-scale global features from the whole image with refined local features from informative patches for AI synthesized image detection.
1 code implementation • 27 Oct 2022 • Na Zhang, Shan Jia, Siwei Lyu, Xin Li
Our technical contributions include: 1) We propose a fusion-based few-shot learning (FSL) method to learn discriminative features that can generalize to unseen morphing attack types from predefined presentation attacks; 2) The proposed FSL based on the fusion of the PRNU model and Noiseprint network is extended from binary MAD to multiclass morphing attack fingerprinting (MAF).
no code implementations • 21 Oct 2022 • Hui Guo, Xin Wang, Siwei Lyu
Specifically, we authenticate video calls by displaying a distinct pattern on the screen and using the corneal reflection extracted from the images of the call participant's face.
1 code implementation • 20 Oct 2022 • Yanfei Xiang, Xin Wang, Shu Hu, Bin Zhu, Xiaomeng Huang, Xi Wu, Siwei Lyu
Reinforcement learning is applied to solve actual complex tasks from high-dimensional, sensory inputs.
no code implementations • 19 Sep 2022 • Syeda Nyma Ferdous, Xin Li, Siwei Lyu
Learning a robust and discriminative feature representation is a crucial challenge for object ReID.
no code implementations • 18 Jul 2022 • Shu Hu, Xin Wang, Siwei Lyu
Following these categories, we review the literature on rank-based aggregate losses and rank-based individual losses.
1 code implementation • 30 Jun 2022 • Bo Peng, Wei Xiang, Yue Jiang, Wei Wang, Jing Dong, Zhenan Sun, Zhen Lei, Siwei Lyu
There is a two-party game between DeepFake creators and defenders.
no code implementations • 13 May 2022 • Hui Guo, Shu Hu, Xin Wang, Ming-Ching Chang, Siwei Lyu
In this work, we develop an online platform called Open-eye to study the human performance of AI-synthesized face detection.
1 code implementation • 26 Mar 2022 • Yan Ju, Shan Jia, Lipeng Ke, Hongfei Xue, Koki Nagano, Siwei Lyu
Specifically, we design a two-branch model to combine global spatial information from the whole image and local informative features from multiple patches selected by a novel patch selection module.
no code implementations • 11 Mar 2022 • Shu Hu, Chun-Hao Liu, Jayanta Dutta, Ming-Ching Chang, Siwei Lyu, Naveen Ramakrishnan
Semi-supervised object detection methods are widely used in autonomous driving systems, where only a fraction of objects are labeled.
1 code implementation • 25 Feb 2022 • Shan Jia, Xin Li, Siwei Lyu
Then we take Deepfakes model attribution as a multiclass classification task and propose a spatial and temporal attention based method to explore the differences among Deepfakes in the new dataset.
no code implementations • 15 Feb 2022 • Xin Wang, Hui Guo, Shu Hu, Ming-Ching Chang, Siwei Lyu
Generative Adversarial Networks (GAN) have led to the generation of very realistic face images, which have been used in fake social media accounts and other disinformation matters that can generate profound impacts.
no code implementations • 4 Feb 2022 • Lipeng Ke, Kuan-Chuan Peng, Siwei Lyu
Graph Convolutional Networks (GCNs) have been widely used to model the high-order dynamic dependencies for skeleton-based action recognition.
no code implementations • 22 Jan 2022 • Zhenhuan Yang, Shu Hu, Yunwen Lei, Kush R. Varshney, Siwei Lyu, Yiming Ying
We further provide its utility analysis in the nonconvex-strongly-concave setting which is the first-ever-known result in terms of the primal population risk.
1 code implementation • 14 Dec 2021 • Ziwei Luo, Jing Hu, Xin Wang, Siwei Lyu, Bin Kong, Youbing Yin, Qi Song, Xi Wu
Training a model-free deep reinforcement learning model to solve image-to-image translation is difficult since it involves high-dimensional continuous state and action spaces.
1 code implementation • 14 Dec 2021 • Ziwei Luo, Jing Hu, Xin Wang, Shu Hu, Bin Kong, Youbing Yin, Qi Song, Xi Wu, Siwei Lyu
We evaluate our method on several 2D and 3D medical image datasets, some of which contain large deformations.
1 code implementation • 6 Dec 2021 • Ehab A. AlBadawy, Andrew Gibiansky, Qing He, JiLong Wu, Ming-Ching Chang, Siwei Lyu
We perform a subjective and objective evaluation to compare the performance of each vocoder along a different axis.
no code implementations • 13 Sep 2021 • Bor-Shiun Wang, Jun-Wei Hsieh, Ming-Ching Chang, Ping-Yang Chen, Lipeng Ke, Siwei Lyu
We introduce the Learning Discrete Wavelet Pooling (LDW-Pooling) that can be applied universally to replace standard pooling operations to better extract features with improved accuracy and efficiency.
no code implementations • 5 Sep 2021 • Hui Guo, Shu Hu, Xin Wang, Ming-Ching Chang, Siwei Lyu
However, images from existing public datasets do not represent real-world scenarios well enough in terms of view variations and data distributions (where real faces largely outnumber synthetic faces).
no code implementations • 1 Sep 2021 • Hui Guo, Shu Hu, Xin Wang, Ming-Ching Chang, Siwei Lyu
Generative adversary network (GAN) generated high-realistic human faces have been used as profile images for fake social media accounts and are visually challenging to discern from real ones.
1 code implementation • 31 Jul 2021 • Shu Hu, Lipeng Ke, Xin Wang, Siwei Lyu
Top-$k$ multi-label learning, which returns the top-$k$ predicted labels from an input, has many practical applications such as image annotation, document analysis, and web search engine.
1 code implementation • 7 Jun 2021 • Shu Hu, Yiming Ying, Xin Wang, Siwei Lyu
A combination loss of AoRR and TKML is proposed as a new learning objective for improving the robustness of multi-label learning in the face of outliers in sample and labels alike.
no code implementations • 3 Jun 2021 • Quanyu Liao, Xin Wang, Bin Kong, Siwei Lyu, Bin Zhu, Youbing Yin, Qi Song, Xi Wu
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbation can completely change prediction result.
no code implementations • 3 Jun 2021 • Quanyu Liao, Yuezun Li, Xin Wang, Bin Kong, Bin Zhu, Siwei Lyu, Youbing Yin, Qi Song, Xi Wu
Fooling people with highly realistic fake images generated with Deepfake or GANs brings a great social disturbance to our society.
1 code implementation • 2 Jun 2021 • Bo Peng, Hongxing Fan, Wei Wang, Jing Dong, Yuezun Li, Siwei Lyu, Qi Li, Zhenan Sun, Han Chen, Baoying Chen, Yanjie Hu, Shenghai Luo, Junrui Huang, Yutong Yao, Boyuan Liu, Hefei Ling, Guosheng Zhang, Zhiliang Xu, Changtao Miao, Changlei Lu, Shan He, Xiaoyan Wu, Wanyi Zhuang
This competition provides a common platform for benchmarking the adversarial game between current state-of-the-art DeepFake creation and detection methods.
1 code implementation • CVPR 2021 • Longyin Wen, Dawei Du, Pengfei Zhu, QinGhua Hu, Qilong Wang, Liefeng Bo, Siwei Lyu
To promote the developments of object detection, tracking and counting algorithms in drone-captured videos, we construct a benchmark with a new drone-captured largescale dataset, named as DroneCrowd, formed by 112 video clips with 33, 600 HD frames in various scenarios.
no code implementations • 2 Mar 2021 • Yuezun Li, Cong Zhang, Pu Sun, Honggang Qi, Siwei Lyu
In recent years, the advent of deep learning-based techniques and the significant reduction in the cost of computation resulted in the feasibility of creating realistic videos of human faces, commonly known as DeepFakes.
no code implementations • 1 Feb 2021 • Pu Sun, Yuezun Li, Honggang Qi, Siwei Lyu
In this paper, we describe Landmark Breaker, the first dedicated method to disrupt facial landmark extraction, and apply it to the obstruction of the generation of DeepFake videos. Our motivation is that disrupting the facial landmark extraction can affect the alignment of input face so as to degrade the DeepFake quality.
1 code implementation • ICCV 2021 • Shu Hu, Lipeng Ke, Xin Wang, Siwei Lyu
Top-k multi-label learning, which returns the top-k predicted labels from an input, has many practical applications such as image annotation, document analysis, and web search engine.
1 code implementation • 31 Oct 2020 • Pu Sun, Yuezun Li, Honggang Qi, Siwei Lyu
Face synthesis is an important problem in computer vision with many applications.
no code implementations • 27 Oct 2020 • Quanyu Liao, Xin Wang, Bin Kong, Siwei Lyu, Youbing Yin, Qi Song, Xi Wu
The deep neural network is vulnerable to adversarial examples.
1 code implementation • Interspeech 2020 • Ehab A AlBadawy, Siwei Lyu
An impressionist is the one who tries to mimic other people’s voices and their style of speech.
1 code implementation • NeurIPS 2020 • Shu Hu, Yiming Ying, Xin Wang, Siwei Lyu
In forming learning objectives, one oftentimes needs to aggregate a set of individual values to a single output.
no code implementations • 3 Oct 2020 • Yi Wei, Zhe Gan, Wenbo Li, Siwei Lyu, Ming-Ching Chang, Lei Zhang, Jianfeng Gao, Pengchuan Zhang
We present Mask-guided Generative Adversarial Network (MagGAN) for high-resolution face attribute editing, in which semantic facial masks from a pre-trained face parser are used to guide the fine-grained image editing process.
1 code implementation • 24 Sep 2020 • Shu Hu, Yuezun Li, Siwei Lyu
We show that such artifacts exist widely in high-quality GAN synthesized faces and further describe an automatic method to extract and compare corneal specular highlights from two eyes.
1 code implementation • ECCV 2020 • Ao Luo, Xin Li, Fan Yang, Zhicheng Jiao, Hong Cheng, Siwei Lyu
Current works either simply distill prior knowledge from the corresponding depth map for handling the RGB-image or blindly fuse color and geometric information to generate the coarse depth-aware representations, hindering the performance of RGB-D saliency detectors. In this work, we introduceCascade Graph Neural Networks(Cas-Gnn), a unified framework which is capable of comprehensively distilling and reasoning the mutual benefits between these two data sources through a set of cascade graphs, to learn powerful representations for RGB-D salient object detection.
Ranked #6 on
RGB-D Salient Object Detection
on NJU2K
no code implementations • 11 Mar 2020 • Siwei Lyu
High quality fake videos and audios generated by AI-algorithms (the deep fakes) have started to challenge the status of videos and audios as definitive evidence of events.
no code implementations • 10 Feb 2020 • Quanyu Liao, Xin Wang, Bin Kong, Siwei Lyu, Youbing Yin, Qi Song, Xi Wu
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbations can completely change the classification results.
no code implementations • 5 Feb 2020 • Xian Zhang, Xin Wang, Bin Kong, Youbing Yin, Qi Song, Siwei Lyu, Jiancheng Lv, Canghong Shi, Xiaojie Li
We firstly represent only face regions using the latent variable as the domain knowledge and combine it with the non-face parts textures to generate high-quality face images with plausible contents.
no code implementations • ECCV 2020 • Ruyi Ji, Dawei Du, Libo Zhang, Longyin Wen, Yanjun Wu, Chen Zhao, Feiyue Huang, Siwei Lyu
In this paper, we design a novel semantic neural tree for human parsing, which uses a tree architecture to encode physiological structure of human body, and designs a coarse to fine process in a cascade manner to generate accurate results.
1 code implementation • 4 Dec 2019 • Longyin Wen, Dawei Du, Pengfei Zhu, QinGhua Hu, Qilong Wang, Liefeng Bo, Siwei Lyu
This paper proposes a space-time multi-scale attention network (STANet) to solve density map estimation, localization and tracking in dense crowds of video clips captured by drones with arbitrary crowd density, perspective, and flight altitude.
no code implementations • 19 Oct 2019 • Yuezun Li, Ao Luo, Siwei Lyu
In this paper, we describe a fast and light-weight portrait segmentation method based on a new highly light-weight backbone (HLB) architecture.
8 code implementations • CVPR 2020 • Yuezun Li, Xin Yang, Pu Sun, Honggang Qi, Siwei Lyu
AI-synthesized face-swapping videos, commonly known as DeepFakes, is an emerging problem threatening the trustworthiness of online information.
no code implementations • 25 Sep 2019 • Yuan-Qiang Cai, Dawei Du, Libo Zhang, Longyin Wen, Weiqiang Wang, Yanjun Wu, Siwei Lyu
Object detection and counting are related but challenging problems, especially for drone based scenes with small objects and cluttered background.
no code implementations • 21 Jun 2019 • Yuezun Li, Xin Yang, Baoyuan Wu, Siwei Lyu
Recent years have seen fast development in synthesizing realistic human faces using AI technologies.
no code implementations • 11 Jun 2019 • Dan Liu, Dawei Du, Libo Zhang, Tiejian Luo, Yanjun Wu, Feiyue Huang, Siwei Lyu
Existing hand detection methods usually follow the pipeline of multiple stages with high computation cost, i. e., feature extraction, region proposal, bounding box regression, and additional layers for rotated region detection.
no code implementations • 10 Apr 2019 • Cong-Cong Li, Dawei Du, Libo Zhang, Tiejian Luo, Yanjun Wu, Qi Tian, Longyin Wen, Siwei Lyu
In this paper, we propose a new data priming method to solve the domain adaptation problem.
no code implementations • 30 Mar 2019 • Xin Yang, Yuezun Li, Honggang Qi, Siwei Lyu
Generative adversary networks (GANs) have recently led to highly realistic image synthesis results.
1 code implementation • CVPR 2019 • Wenbo Li, Pengchuan Zhang, Lei Zhang, Qiuyuan Huang, Xiaodong He, Siwei Lyu, Jianfeng Gao
In this paper, we propose Object-driven Attentive Generative Adversarial Newtorks (Obj-GANs) that allow object-centered text-to-image synthesis for complex scenes.
no code implementations • 12 Feb 2019 • Yuezun Li, Siwei Lyu
In this work, we describe a new face de-identification method that can preserve essential facial attributes in the faces while concealing the identities.
no code implementations • 29 Jan 2019 • Bin Kong, Xin Wang, Junjie Bai, Yi Lu, Feng Gao, Kunlin Cao, Qi Song, Shaoting Zhang, Siwei Lyu, Youbing Yin
In order to address these limitations, we present tree-structured ConvLSTM models for tree-structured image analysis tasks which can be trained end-to-end.
no code implementations • 21 Dec 2018 • Eric Wu, Bin Kong, Xin Wang, Junjie Bai, Yi Lu, Feng Gao, Shaoting Zhang, Kunlin Cao, Qi Song, Siwei Lyu, Youbing Yin
The hierarchical attention components of the residual attention subnet force our network to focus on the key components of the X-ray images and generate the final predictions as well as the associated visual supports, which is similar to the assessment procedure of clinicians.
no code implementations • 10 Dec 2018 • Longyin Wen, Dawei Du, Shengkun Li, Xiao Bian, Siwei Lyu
The majority of Multi-Object Tracking (MOT) algorithms based on the tracking-by-detection scheme do not use higher order dependencies among objects or tracklets, which makes them less effective in handling complex scenarios.
no code implementations • 6 Nov 2018 • Wenbo Li, Longyin Wen, Xiao Bian, Siwei Lyu
Video style transfer is a useful component for applications such as augmented reality, non-photorealistic rendering, and interactive games.
3 code implementations • 1 Nov 2018 • Yuezun Li, Siwei Lyu
Compared to previous methods which use a large amount of real and DeepFake generated images to train CNN classifier, our method does not need DeepFake generated images as negative training examples since we target the artifacts in affine face warping as the distinctive feature to distinguish real and fake images.
1 code implementation • 1 Nov 2018 • Xin Yang, Yuezun Li, Siwei Lyu
In this paper, we propose a new method to expose AI-generated fake face images or videos (commonly known as the Deep Fakes).
no code implementations • 16 Sep 2018 • Yuezun Li, Daniel Tian, Ming-Ching Chang, Xiao Bian, Siwei Lyu
Adversarial noises are useful tools to probe the weakness of deep learning based computer vision algorithms.
no code implementations • 16 Sep 2018 • Yuezun Li, Xiao Bian, Ming-Ching Chang, Siwei Lyu
In this paper, we focus on exploring the vulnerability of the Single Shot Module (SSM) commonly used in recent object detectors, by adding small perturbations to patches in the background outside the object.
no code implementations • 5 Aug 2018 • Lipeng Ke, Ming-Ching Chang, Honggang Qi, Siwei Lyu
Human pose estimation is an important topic in computer vision with many applications including gesture and activity recognition.
no code implementations • 3 Jul 2018 • Wenbo Li, Ming-Ching Chang, Siwei Lyu
We present a bootstrapping framework to simultaneously improve multi-person tracking and activity recognition at individual, interaction and social group activity levels.
no code implementations • ICML 2018 • Michael Natole, Yiming Ying, Siwei Lyu
Stochastic optimization algorithms such as SGDs update the model sequentially with cheap per-iteration costs, making them amenable for large-scale data analysis.
3 code implementations • 7 Jun 2018 • Yuezun Li, Ming-Ching Chang, Siwei Lyu
The new developments in deep generative networks have significantly improve the quality and efficiency in generating realistically-looking fake face videos.
no code implementations • 20 May 2018 • Shuchen Weng, Wenbo Li, Yi Zhang, Siwei Lyu
Inspired by the dual-stream hypothesis in neural science, we propose a novel dual-stream framework for modeling the interweaved spatiotemporal dependency, and develop a convolutional neural network within this framework that aims to achieve high adaptability and flexibility in STS configurations from various diagonals, i. e., sequential order, dependency range and features.
no code implementations • 16 Apr 2018 • Siwei Lyu, Yiming Ying
In this work, we describe a new surrogate loss based on a reformulation of the AUC risk, which does not require pairwise comparison but rankings of the predictions.
no code implementations • CVPR 2018 • Baoyuan Wu, Weidong Chen, Peng Sun, Wei Liu, Bernard Ghanem, Siwei Lyu
In D2IA, we generate a relevant and distinct tag subset, in which the tags are relevant to the image contents and semantically distinct to each other, using sequential sampling from a determinantal point process (DPP) model.
no code implementations • 31 Mar 2018 • Baoyuan Wu, Fan Jia, Wei Liu, Bernard Ghanem, Siwei Lyu
This work focuses on the problem of multi-label learning with missing labels (MLML), which aims to label each test instance with multiple class labels given training instances that have an incomplete/partial set of these labels.
no code implementations • ECCV 2018 • Lipeng Ke, Ming-Ching Chang, Honggang Qi, Siwei Lyu
We develop a robust multi-scale structure-aware neural network for human pose estimation.
Ranked #13 on
Pose Estimation
on MPII Human Pose
no code implementations • The IEEE International Conference on Computer Vision (ICCV), 2017 2017 • Wenbo Li, Longyin Wen, Ming-Ching Chang, Ser Nam Lim, Siwei Lyu
The RNNs in RNN-T are co-trained with the action category hierarchy, which determines the structure of RNN-T.
Ranked #118 on
Skeleton Based Action Recognition
on NTU RGB+D
no code implementations • 13 Jun 2017 • Longyin Wen, Honggang Qi, Siwei Lyu
Our method recovers the original pixel histogram and the contrast enhancement simultaneously from a single image with an iterative algorithm.
no code implementations • NeurIPS 2017 • Yanbo Fan, Siwei Lyu, Yiming Ying, Bao-Gang Hu
We further give a learning theory analysis of \matk learning on the classification calibration of the \atk loss and the error bounds of \atk-SVM.
no code implementations • 22 May 2017 • Yanbo Fan, Jian Liang, Ran He, Bao-Gang Hu, Siwei Lyu
In multi-view clustering, different views may have different confidence levels when learning a consensus representation.
no code implementations • NeurIPS 2016 • Yiming Ying, Longyin Wen, Siwei Lyu
From this saddle representation, a stochastic online algorithm (SOLAM) is proposed which has time and space complexity of one datum.
no code implementations • 6 May 2016 • Andrew Pulver, Siwei Lyu
Our architecture is still simple and achieves better performance on the tasks that we tested on.
no code implementations • 18 Mar 2016 • Dawei Du, Honggang Qi, Longyin Wen, Qi Tian, Qingming Huang, Siwei Lyu
Graph based representation is widely used in visual tracking field by finding correct correspondences between target parts in consecutive frames.
no code implementations • ICCV 2015 • Wenbo Li, Longyin Wen, Mooi Choo Chuah, Siwei Lyu
In this paper, we propose the category-blind human recognition method (CHARM) which can recognize a human action without making assumptions of the action category.
no code implementations • ICCV 2015 • Baoyuan Wu, Siwei Lyu, Bernard Ghanem
This work focuses on the problem of multi-label learning with missing labels (MLML), which aims to label each test instance with multiple class labels given training instances that have an incomplete/partial set of these labels (i. e. some of their labels are missing).
no code implementations • 13 Nov 2015 • Longyin Wen, Dawei Du, Zhaowei Cai, Zhen Lei, Ming-Ching Chang, Honggang Qi, Jongwoo Lim, Ming-Hsuan Yang, Siwei Lyu
In this work, we perform a comprehensive quantitative study on the effects of object detection accuracy to the overall MOT performance, using the new large-scale University at Albany DETection and tRACking (UA-DETRAC) benchmark dataset.
no code implementations • ICCV 2015 • Xing Mei, Honggang Qi, Bao-Gang Hu, Siwei Lyu
In this work, we describe an effective and efficient approach to incorporate the knowledge of distinct pixel values of the pristine images into the general regularized least squares restoration framework.
no code implementations • CVPR 2015 • Xing Mei, Wei-Ming Dong, Bao-Gang Hu, Siwei Lyu
Marginal histograms provide valuable information for various computer vision problems.
no code implementations • CVPR 2014 • Xing Zhang, Siwei Lyu
Kurtosis of 1D projections provides important statistical characteristics of natural images.
no code implementations • NeurIPS 2013 • Siwei Lyu, Xin Wang
Nonnegative matrix factorization (NMF) is a popular data analysis method, the objective of which is to decompose a matrix with all nonnegative components into the product of two other nonnegative matrices.
no code implementations • NeurIPS 2012 • Zuoguan Wang, Siwei Lyu, Gerwin Schalk, Qiang Ji
In this work, we describe a new learning scheme for parametric learning, in which the target variables $\y$ can be modeled with a prior model $p(\y)$ and the relations between data and target variables are estimated through $p(\y)$ and a set of uncorresponded data $\x$ in training.
no code implementations • NeurIPS 2011 • Siwei Lyu
When used to learn high dimensional parametric probabilistic models, the clas- sical maximum likelihood (ML) learning often suffers from computational in- tractability, which motivates the active developments of non-ML learning meth- ods.
no code implementations • NeurIPS 2010 • Siwei Lyu
Our analysis is based on the use of multivariate {\em t} model to capture some important statistical properties of natural sensory signals.
no code implementations • NeurIPS 2008 • Siwei Lyu, Eero P. Simoncelli
In this case, no linear transform suffices to properly decompose the signal into independent components, but we show that a simple nonlinear transformation, which we call radial Gaussianization (RG), is able to remove all dependencies.