Search Results for author:
Found 105 papers, 33 papers with code
Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective
Adversarial machine learning (AML) studies the adversarial phenomenon of machine learning, which may make inconsistent or unexpected predictions with humans.
Object-driven Text-to-Image Synthesis via Adversarial Training
In this paper, we propose Object-driven Attentive Generative Adversarial Newtorks (Obj-GANs) that allow object-centered text-to-image synthesis for complex scenes.
Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics
AI-synthesized face-swapping videos, commonly known as DeepFakes, is an emerging problem threatening the trustworthiness of online information.
VocBench: A Neural Vocoder Benchmark for Speech Synthesis
We perform a subjective and objective evaluation to compare the performance of each vocoder along a different axis.
DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection
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.
Drone-based Joint Density Map Estimation, Localization and Tracking with Space-Time Multi-Scale Attention Network
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.
Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark
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.
Exposing DeepFake Videos By Detecting Face Warping Artifacts
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.
Voice Conversion Using Speech-to-Speech Neuro-Style Transfer
An impressionist is the one who tries to mimic other people’s voices and their style of speech.
In Ictu Oculi: Exposing AI Generated Fake Face Videos by Detecting Eye Blinking
The new developments in deep generative networks have significantly improve the quality and efficiency in generating realistically-looking fake face videos.
Exposing Deep Fakes Using Inconsistent Head Poses
In this paper, we propose a new method to expose AI-generated fake face images or videos (commonly known as the Deep Fakes).
Stochastic Planner-Actor-Critic for Unsupervised Deformable Image Registration
We evaluate our method on several 2D and 3D medical image datasets, some of which contain large deformations.
Stochastic Actor-Executor-Critic for Image-to-Image Translation
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.
Image-to-Image Translation with Deep Reinforcement Learning
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.
Cascade Graph Neural Networks for RGB-D Salient Object Detection
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 #5 on
RGB-D Salient Object Detection
on NJU2K
AutoSplice: A Text-prompt Manipulated Image Dataset for Media Forensics
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.
DFGC 2021: A DeepFake Game Competition
This competition provides a common platform for benchmarking the adversarial game between current state-of-the-art DeepFake creation and detection methods.
Language-guided Human Motion Synthesis with Atomic Actions
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.
Model Attribution of Face-swap Deepfake Videos
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.
Fusing Global and Local Features for Generalized AI-Synthesized Image Detection
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.
GLFF: Global and Local Feature Fusion for AI-synthesized Image Detection
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.
DFGC 2022: The Second DeepFake Game Competition
There is a two-party game between DeepFake creators and defenders.
Learning by Minimizing the Sum of Ranked Range
In forming learning objectives, one oftentimes needs to aggregate a set of individual values to a single output.
Sum of Ranked Range Loss for Supervised Learning
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.
Exposing GAN-generated Faces Using Inconsistent Corneal Specular Highlights
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.
RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Control
Reinforcement learning is applied to solve actual complex tasks from high-dimensional, sensory inputs.
Improving Fairness in Deepfake Detection
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.
T$_k$ML-AP: Adversarial Attacks to Top-$k$ Multi-Label Learning
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.
TkML-AP: Adversarial Attacks to Top-k Multi-Label Learning
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.
Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensics
DeepFakes, which refer to AI-generated media content, have become an increasing concern due to their use as a means for disinformation.
LandmarkGAN: Synthesizing Faces from Landmarks
Face synthesis is an important problem in computer vision with many applications.
Fusion-based Few-Shot Morphing Attack Detection and Fingerprinting
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).
Outlier Robust Adversarial Training
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.
A Univariate Bound of Area Under ROC
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.
STS Classification with Dual-stream CNN
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.
Multi-label Learning with Missing Labels using Mixed Dependency Graphs
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.
Tagging like Humans: Diverse and Distinct Image Annotation
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.
Multi-Scale Structure-Aware Network for Human Pose Estimation
We develop a robust multi-scale structure-aware neural network for human pose estimation.
Ranked #13 on
Pose Estimation
on MPII Human Pose
Learning with Average Top-k Loss
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.
Contrast Enhancement Estimation for Digital Image Forensics
Our method recovers the original pixel histogram and the contrast enhancement simultaneously from a single image with an iterative algorithm.
Robust Localized Multi-view Subspace Clustering
In multi-view clustering, different views may have different confidence levels when learning a consensus representation.
LSTM with Working Memory
Our architecture is still simple and achieves better performance on the tasks that we tested on.
UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking
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.
Geometric Hypergraph Learning for Visual Tracking
Graph based representation is widely used in visual tracking field by finding correct correspondences between target parts in consecutive frames.
Improving Image Restoration with Soft-Rounding
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.
Who did What at Where and When: Simultaneous Multi-Person Tracking and Activity Recognition
We present a bootstrapping framework to simultaneously improve multi-person tracking and activity recognition at individual, interaction and social group activity levels.
Multi-Scale Supervised Network for Human Pose Estimation
Human pose estimation is an important topic in computer vision with many applications including gesture and activity recognition.
Exploring the Vulnerability of Single Shot Module in Object Detectors via Imperceptible Background Patches
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.
Robust Adversarial Perturbation on Deep Proposal-based Models
Adversarial noises are useful tools to probe the weakness of deep learning based computer vision algorithms.
Evolvement Constrained Adversarial Learning for Video Style Transfer
Video style transfer is a useful component for applications such as augmented reality, non-photorealistic rendering, and interactive games.
Learning Non-Uniform Hypergraph for Multi-Object Tracking
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.
Stochastic Online AUC Maximization
From this saddle representation, a stochastic online algorithm (SOLAM) is proposed which has time and space complexity of one datum.
On Algorithms for Sparse Multi-factor NMF
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.
Learning with Target Prior
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.
Unifying Non-Maximum Likelihood Learning Objectives with Minimum KL Contraction
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.
Divisive Normalization: Justification and Effectiveness as Efficient Coding Transform
Our analysis is based on the use of multivariate {\em t} model to capture some important statistical properties of natural sensory signals.
Reducing statistical dependencies in natural signals using radial Gaussianization
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.
Stochastic Proximal Algorithms for AUC Maximization
Stochastic optimization algorithms such as SGDs update the model sequentially with cheap per-iteration costs, making them amenable for large-scale data analysis.
Residual Attention based Network for Hand Bone Age Assessment
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.
Using Projection Kurtosis Concentration Of Natural Images For Blind Noise Covariance Matrix Estimation
Kurtosis of 1D projections provides important statistical characteristics of natural images.
UniHIST: A Unified Framework for Image Restoration With Marginal Histogram Constraints
Marginal histograms provide valuable information for various computer vision problems.
ML-MG: Multi-Label Learning With Missing Labels Using a Mixed Graph
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).
Category-Blind Human Action Recognition: A Practical Recognition System
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.
De-identification without losing faces
In this work, we describe a new face de-identification method that can preserve essential facial attributes in the faces while concealing the identities.
Attention-driven Tree-structured Convolutional LSTM for High Dimensional Data Understanding
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.
Exposing GAN-synthesized Faces Using Landmark Locations
Generative adversary networks (GANs) have recently led to highly realistic image synthesis results.
Data Priming Network for Automatic Check-Out
In this paper, we propose a new data priming method to solve the domain adaptation problem.
Scale Invariant Fully Convolutional Network: Detecting Hands Efficiently
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.
Hiding Faces in Plain Sight: Disrupting AI Face Synthesis with Adversarial Perturbations
Recent years have seen fast development in synthesizing realistic human faces using AI technologies.
Adaptive RNN Tree for Large-Scale Human Action Recognition
The RNNs in RNN-T are co-trained with the action category hierarchy, which determines the structure of RNN-T.
Ranked #107 on
Skeleton Based Action Recognition
on NTU RGB+D
Guided Attention Network for Object Detection and Counting on Drones
Object detection and counting are related but challenging problems, especially for drone based scenes with small objects and cluttered background.
Fast Portrait Segmentation with Highly Light-weight Network
In this paper, we describe a fast and light-weight portrait segmentation method based on a new highly light-weight backbone (HLB) architecture.
Learning Semantic Neural Tree for Human Parsing
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.
Domain Embedded Multi-model Generative Adversarial Networks for Image-based Face Inpainting
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.
Category-wise Attack: Transferable Adversarial Examples for Anchor Free Object Detection
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbations can completely change the classification results.
DeepFake Detection: Current Challenges and Next Steps
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.
MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Network
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.
Fast Local Attack: Generating Local Adversarial Examples for Object Detectors
The deep neural network is vulnerable to adversarial examples.
Landmark Breaker: Obstructing DeepFake By Disturbing Landmark Extraction
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.
DeepFake-o-meter: An Open Platform for DeepFake Detection
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.
Imperceptible Adversarial Examples for Fake Image Detection
Fooling people with highly realistic fake images generated with Deepfake or GANs brings a great social disturbance to our society.
Transferable Adversarial Examples for Anchor Free Object Detection
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbation can completely change prediction result.
Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Faces
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.
Robust Attentive Deep Neural Network for Exposing GAN-generated Faces
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).
Learnable Discrete Wavelet Pooling (LDW-Pooling) For Convolutional Networks
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.
Differentially Private SGDA for Minimax Problems
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.
Towards To-a-T Spatio-Temporal Focus for Skeleton-Based Action Recognition
Graph Convolutional Networks (GCNs) have been widely used to model the high-order dynamic dependencies for skeleton-based action recognition.
GAN-generated Faces Detection: A Survey and New Perspectives
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.
PseudoProp: Robust Pseudo-Label Generation for Semi-Supervised Object Detection in Autonomous Driving Systems
Semi-supervised object detection methods are widely used in autonomous driving systems, where only a fraction of objects are labeled.
Open-Eye: An Open Platform to Study Human Performance on Identifying AI-Synthesized Faces
In this work, we develop an online platform called Open-eye to study the human performance of AI-synthesized face detection.
Rank-based Decomposable Losses in Machine Learning: A Survey
Following these categories, we review the literature on rank-based aggregate losses and rank-based individual losses.
Uncertainty Aware Multitask Pyramid Vision Transformer For UAV-Based Object Re-Identification
Learning a robust and discriminative feature representation is a crucial challenge for object ReID.
Detection of Real-time DeepFakes in Video Conferencing with Active Probing and Corneal Reflection
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.
Attacking Important Pixels for Anchor-free Detectors
Existing adversarial attacks on object detection focus on attacking anchor-based detectors, which may not work well for anchor-free detectors.
Harnessing the Power of Text-image Contrastive Models for Automatic Detection of Online Misinformation
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.
Tracking Multiple Deformable Objects in Egocentric Videos
DETracker outperforms existing state-of-the-art method on the DogThruGlasses dataset and YouTube-Hand dataset.
FakeTracer: Proactively Defending Against Face-swap DeepFakes via Implanting Traces in Training
Face-swap DeepFake is an emerging AI-based face forgery technique that can replace the original face in a video with a generated face of the target identity while retaining consistent facial attributes such as expression and orientation.
ForensicsForest Family: A Series of Multi-scale Hierarchical Cascade Forests for Detecting GAN-generated Faces
The proposed ForensicsForest family is composed of three variants, which are {\em ForensicsForest}, {\em Hybrid ForensicsForest} and {\em Divide-and-Conquer ForensicsForest} respectively.
Contrastive Multi-FaceForensics: An End-to-end Bi-grained Contrastive Learning Approach for Multi-face Forgery Detection
DeepFakes have raised serious societal concerns, leading to a great surge in detection-based forensics methods in recent years.
Improving Cross-dataset Deepfake Detection with Deep Information Decomposition
Deepfake technology poses a significant threat to security and social trust.
Controlling Neural Style Transfer with Deep Reinforcement Learning
Controlling the degree of stylization in the Neural Style Transfer (NST) is a little tricky since it usually needs hand-engineering on hyper-parameters.
Integrating Audio-Visual Features for Multimodal Deepfake Detection
Deepfakes are AI-generated media in which an image or video has been digitally modified.
UMedNeRF: Uncertainty-aware Single View Volumetric Rendering for Medical Neural Radiance Fields
In the field of clinical medicine, computed tomography (CT) is an effective medical imaging modality for the diagnosis of various pathologies.
Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection
Deepfake detection faces a critical generalization hurdle, with performance deteriorating when there is a mismatch between the distributions of training and testing data.
Exposing Lip-syncing Deepfakes from Mouth Inconsistencies
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.
