Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Hany FaridSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works299 from public data
- Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics1,885
This work presents a new large-scale challenging DeepFake video dataset, Celeb-DF, which contains 5,639 high-quality DeepFake videos of celebrities generated using improved synthesis process and conducts a comprehensive evaluation of DeepFake detection methods and datasets to demonstrate the escalated level of challenges posed by Celebrity-DF.
- Exposing Deep Fakes Using Inconsistent Head Poses1,173
This paper proposes a new method to expose AI-generated fake face images or videos based on the observations that Deep Fakes are created by splicing synthesized face region into the original image, and in doing so, introducing errors that can be revealed when 3D head poses are estimated from the face images.
- 1,043
- UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking799
This work performs 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.
- The Visual Object Tracking VOT2016 Challenge Results776
The Visual Object Tracking challenge VOT2016 goes beyond its predecessors by introducing a new semi-automatic ground truth bounding box annotation methodology and extending the evaluation system with the no-reset experiment.
- Invisible Backdoor Attack with Sample-Specific Triggers721
Inspired by the recent advance in DNN-based image steganography, sample-specific invisible additive noises as backdoor triggers are generated by encoding an attacker-specified string into benign images through an encoder-decoder network.
- 641
- Detecting Hidden Messages Using Higher-Order Statistics and Support Vector Machines570
An approach to detecting hidden messages in images that uses a wavelet-like decomposition to build higher-order statistical models of natural images and support vector machines are used to discriminate between untouched and adulterated images.
- 467
- 447
- 434
- Object-Driven Text-To-Image Synthesis via Adversarial Training326
A thorough comparison between the classic grid attention and the new object-driven attention is provided through analyzing their mechanisms and visualizing their attention layers, showing insights of how the proposed model generates complex scenes in high quality.
- Multi-Scale Structure-Aware Network for Human Pose Estimation300
A robust multi-scale structure-aware neural network for human pose estimation that effectively improves state-of-the-art pose estimation methods that suffer from difficulties in scale varieties, occlusions, and complex multi-person scenarios.
- 279
- 272
- Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection237
This work proposes a simple yet effective detector called LSDA (Latent Space Data Augmentation), based on a heuristic idea: representations with a wider variety of forgeries should be able to learn a more generalizable decision boundary, thereby mitigating the overfitting of method-specific features.
- Exposing Region Splicing Forgeries with Blind Local Noise Estimation230
An effective method to expose region splicing by revealing inconsistencies in local noise levels, based on the fact that images of different origins may have different noise characteristics introduced by the sensors or post-processing steps.
- Deepfake Detection: Current Challenges and Next Steps223
This paper highlights a few of challenges of high quality fake videos and audios generated by AI- algorithms (the deep fakes) and discusses the research opportunities in this direction.
- Stochastic online AUC maximization223
It is shown that AUC optimization can be equivalently formulated as a convex-concave saddle point problem and a stochastic online algorithm (SOLAM) is proposed which has time and space complexity of one datum.
- Celeb-DF: A New Dataset for DeepFake Forensics214
A new DeepFake dataset is presented, Celeb-DF, for the development and evaluation of DeepFake detection algorithms, generated using a refined synthesis algorithm that reduces the visual artifacts observed in existing datasets.
- A digital technique for art authentication212
A computational technique for authenticating works of art, specifically paintings and drawings, from high-resolution digital scans of the original works, is described, which confirms expert authentications of Pieter Bruegel the Elder.
- Steganalysis using color wavelet statistics and one-class support vector machines202
This paper extends statistical models using first-and higher-order wavelet statistics, and employed a non-linear support vector machines (SVM) to detect steganographic messages to exploit color statistics.
- 196
- 170
- 169
- Fusing Global and Local Features for Generalized AI-Synthesized Image Detection168
A two-branch model is designed to combine global spatial information from the whole image and local informative features from multiple patches selected by a novel patch selection module to fuse the global and local features.
- 153
- 145
- Exposing GAN-Generated Faces Using Inconsistent Corneal Specular Highlights144
This work shows that GAN synthesized faces can be exposed with the inconsistent corneal specular highlights between two eyes, and describes an automatic method to extract and compare corneals from two eyes.
- 142
- Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark139
The Space-Time Neighbor-Aware Network (STNNet) is designed as a strong baseline to solve object detection, tracking and counting jointly in dense crowds and performs favorably against the state-of-the-arts.
- AI-Synthesized Voice Detection Using Neural Vocoder Artifacts128
This study proposes a new approach to identifying synthetic human voices by detecting artifacts of vocoders in audio signals by treating vocoder identification as a pretext task, and introduces a multi-task learning framework for a binaryclass RawNet2 model that shares the feature extractor with a Vocoder identification module.
- Exposing GAN-synthesized Faces Using Landmark Locations127
This work describes a new method to expose GAN-synthesized images using the locations of the facial landmark points, based on the observations that the facial parts configuration generated by GAN models are different from those of the real faces, due to the lack of global constraints.
- Nonlinear Extraction of Independent Components of Natural Images Using Radial Gaussianization127
It is shown that distributions of spatially proximal bandpass filter responses are better described as elliptical than as linearly transformed independent sources, and it is demonstrated that the reduction in dependency achieved by applying RG to either nearby pairs or blocks of bandpass filters is significantly greater than that achieved by ICA.
- 126
- Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensics121
The capabilities of multimodal large language models (LLMs) in DeepFake detection are investigated and it is shown that they can expose AI-generated images through careful experimental design and prompt engineering.
- 119
- Multi-label learning with missing labels for image annotation and facial action unit recognition119
This work proposes a method for multi-label learning that explicitly handles missing labels and presents an efficient algorithm to learn a parametric classifier that is applied to image annotation and facial action recognition.
- 117
- Cascade Graph Neural Networks for RGB-D Salient Object Detection117
This work introduces Cascade 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.
- Deep low-rank subspace ensemble for multi-view clustering106
A new multi-view clustering method that integrates deep matrix factorization, low-rank subspace learning, and multiple subspace ensemble in a unified framework, which is term as the Deep Low-Rank Subspace Ensemble (DLRSE) method is proposed.
- Eyes Tell All: Irregular Pupil Shapes Reveal GAN-Generated Faces105
It is shown that GAN-generated faces can be exposed via irregular pupil shapes, caused by the lack of physiological constraints in the GAN models, and an automatic method to segment the pupils from the eyes and analyze their shapes is designed to distinguish GANs from real ones.
- 105
- 97
- GAN-Generated Faces Detection: A Survey and New Perspectives95
This work aims to provide a comprehensive review of recent progress in GAN-face detection, focusing on methods that can detect face images that are generated or synthesized from GAN models.
- Multi-label Learning with Missing Labels Using Mixed Dependency Graphs95
This work proposes two convex transductive formulations of the MLML problem, denoted as MLMG-CO and ML MG-SL respectively, and proposes two important applications, including image annotation and tag based image retrieval, which can be jointly handled using these proposed methods.
- 90
- 89
- LSTM with working memory88
This paper proposes a modified LSTM-like RNN architecture that is still simple and achieves better performance on the tasks that it tested on, and introduces a new RNN performance benchmark that uses the handwritten digits and stresses several important network capabilities.
- AutoSplice: A Text-prompt Manipulated Image Dataset for Media Forensics85
This paper proposes a new approach that leverages the DALL-E2 language-image model to automatically generate and splice masked regions guided by a text prompt, which has resulted in the creation of a new image dataset called AutoSplice, containing 5,894 manipulated and authentic images.
- 85
- Improving Fairness in Deepfake Detection82
This work makes the first attempt to improve deepfake detection fairness by proposing novel loss functions that handle both the setting where demographic information is available as well as the case where this information is absent.
- 81
- Detecting AI-Synthesized Speech Using Bispectral Analysis78
It is observed that deep neural networks used to synthesize speech introduce specific and unusual spectral correlations not typically found in human speech, which can be measured using tools from bispectral analysis and used to distinguish human from synthesized speech.
- Exposing image forgery with blind noise estimation78
The proposed method to expose image forgeries by detecting the noise variance differences between original and tampered parts of an image is effective with high detection accuracy and low false positive rate both quantitatively and qualitatively.
- Guided Attention Network for Object Detection and Counting on Drones77
This paper proposes a new Guided Attention network (GAnet) to deal with both object detection and counting tasks based on the feature pyramid, and fuse different scales of feature maps by using the proposed weakly-supervised Background Attention between the background and objects for more semantic feature representation.
- Steganalysis of recorded speech75
This work shows that hidden messages alter the underlying statistics of audio signals, and develops a low-dimensional statistical feature vector that is extracted from this basis representation and used by a non-linear support vector machine for classification.
- 74
- Towards To-a-T Spatio-Temporal Focus for Skeleton-Based Action Recognition73
The STF modules with learnable gradient-enforced and instance-dependent adjacency matrices to model the high-order spatio-temporal dynamics are proposed, and STF shows better accuracy on scarce data and dataset shifting settings.
- 73
- 71
- 70
- 69
- Stochastic Proximal Algorithms for AUC Maximization68
This paper develops a novel stochastic proximal algorithm for AUC maximization which is referred to as SPAM, and achieves a convergence rate of O ( log t t ) for strongly convex functions while both space and per-iteration costs are of one datum.
- GLFF: Global and Local Feature Fusion for AI-Synthesized Image Detection67
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 is proposed.
- The Thermal Infrared Visual Object Tracking VOT-TIR2016 Challenge Results66
A significant general improvement of results has been observed, which partly compensate for the more difficult sequences introduced into the dataset in VOT-TIR2016.
- Multi-Camera Multi-Target Tracking with Space-Time-View Hyper-graph66
A new multi-camera multi-target tracking method based on a space-time-view hyper-graph that encodes higher-order constraints on 3D geometry, appearance, motion continuity, and trajectory smoothness among 2D tracklets within and across different camera views is proposed.
- DETRAC: A New Benchmark and Protocol for Multi-Object Tracking63
This work performs a comprehensive quantitative study on the effect of object detection accuracy to the overall MOT performance based on a new large-scale DETection and tRACking (DETRAC) benchmark dataset.
- End-to-end multimodal image registration via reinforcement learning61
Convolutional long-short-term-memory is incorporated after stacked convolutional layers in this method to extract spatial-temporal image features and learn the similarity metric implicitly, and achieves state-of-the-art performance in medical image registration.
- Learning Semantic Neural Tree for Human Parsing61
A novel semantic neural tree for human parsing is designed, 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.
- Statistical Modeling of Images with Fields of Gaussian Scale Mixtures61
An algorithm for image denoising based on the FoGSM model is developed, and substantial improvements over current state-of-the-art denoisers method are demonstrated.
- 60
- Geometric Hypergraph Learning for Visual Tracking58
A geometric hypergraph learning-based tracking method, which fully exploits high-order geometric relations among multiple correspondences of parts in different frames, and a confidence-aware sampling method is developed to select representative vertices and hyperedges to construct the geometric hyper graph for more robustness and scalability.
- Robust Attentive Deep Neural Network for Detecting GAN-Generated Faces57
This work proposes a robust, attentive, end-to-end framework that spots GAN-generated faces by analyzing eye inconsistencies, and automatically learns to identify inconsistent eye components by localizing and comparing artifacts between eyes.
- Constrained Submodular Minimization for Missing Labels and Class Imbalance in Multi-label Learning57
This work forms the problem as a constrained submodular minimization that is composed of a sub modular objective function that encourages label consistency and smoothness, as well as, class cardinality bound constraints to handle class imbalance.
- 55
- 55
- Tagging Like Humans: Diverse and Distinct Image Annotation54
This work generates 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.
- 52
- Single-Shot Scale-Aware Network for Real-Time Face Detection51
This work proposes a scale-aware detection network using a wide scale range of layers associated with appropriate scales of anchors to handle faces with various scales, and describes a new equal density principle to ensure anchors with different scales to be evenly distributed on the image.
- 51
- Residual Attention Based Network for Hand Bone Age Assessment50
The proposed framework is inspired by the clinical workflow (Tanner-Whitehouse) of hand bone age assessment, which focuses on the key components of the hand, and generates the final predictions as well as the associated visual supports, similar to the assessment procedure of clinicians.
- Unsupervised Learning of Multi-Level Descriptors for Person Re-Identification50
A novel coding method named weighted linear coding (WLC) to learn multi-level descriptors from raw pixel data in an unsupervised manner that guarantees the property of saliency with a similarity constraint and has a good balance between the robustness and distinctiveness.
- 47
- DeepFake the menace: mitigating the negative impacts of AI-generated content45
A conceptual analysis of the impact of DeepFakes considering the production cost and overview counter technologies to fight DeepFakes is provided and an analysis of the cost-effect tradeoff of DeepFakes is provided.
- Multi-Scale Supervised Network for Human Pose Estimation45
A robust pose estimation method based on the recent deep conv-deconv modules with two improvements: (1) multi -scale supervision of body keypoints, and (2) a global regression to improve structural consistency of keypoints.
- Integrating Audio-Visual Features For Multimodal Deepfake Detection43
This paper proposes an audio visual based method for deepfake detection, which integrates fine-grained deepfake identification with binary classification and categorizes the samples into four types by combining labels specific to each single modality.
- 43
- Boosting with Side Information43
A new training method of boosting classifiers that uses side information, which is described as AdaBoost+ and employs a novel classification label imputation method to construct extra weak classifiers from the available information that simulate the performance of better weak classifier obtained from the features in side information.
- 42
- Learning Non-Uniform Hypergraph for Multi-Object Tracking41
A new near-online MOT algorithm based on non-uniform hypergraph, which can model different degrees of dependencies among tracklets in a unified objective and achieves favorable performance against the state-of-the-art MOT methods.
- Contrast Enhancement Estimation for Digital Image Forensics41
The nature of contrast enhancement as a mapping between pixel values and the distinct characteristics it introduces to the image pixel histogram is taken advantage of, and a new method to estimate contrast enhancement operations from a single image is described.
- Dependency Reduction with Divisive Normalization: Justification and Effectiveness40
It is found that statistical dependencies in the multivariate t model and natural sensory signals are increased by the DN transform with low-input dimensions, which implies that for DN to be an effective efficient coding transform, it has to pool over a sufficiently large number of inputs.
- De-identification Without Losing Faces37
A new face de-identification method based on a face attribute transfer model (FATM), which is a deep neural network model trained to map non-identity related facial attributes to the face of donors, who are a small number of consented subjects.
- Deep Correlated Predictive Subspace Learning for Incomplete Multi-View Semi-Supervised Classification35
The proposed Deep Correlated Predictive Subspace Learning (DCPSL) method is able to learn proper subspace representation that is suitable for class label prediction, which can further improve the performance of classification.
- 32
- 29
- 29
- 29
- 28
- 27
- 26
- 26
- 25
- 25
- 25
- 25
- 24
- 24
- 24
- 23
- 23
- 23
- Backdoor Attack with Sample-Specific Triggers.22
Inspired by the recent advance in DNN-based image steganography, sample-specific invisible additive noises as backdoor triggers are generated by encoding an attacker-specified string into benign images through an encoder-decoder network.
- 21
- MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Network20
This work presents 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.
- 20
- 20
- 20
- 19
- 19
- 19
- 19
- 19
- 18
- 18
- 18
- 18
- 17
- 17
- 17
- 16
- 16
- 16
- 15
- Semantics-Oriented Multitask Learning for DeepFake Detection: A Joint Embedding Approach15
This paper proposes an automated dataset expansion technique that broadens current face forgery datasets to support semantics-oriented DeepFake detection tasks at both the global face attribute and local face region levels, and resorts to the joint embedding of face images and labels for prediction.
- 15
- 15
- Semantic Contextualization of Face Forgery: A New Definition, Dataset, and Detection Method14
A semantics-oriented face forgery detection method that captures label relations and prioritizes the primary task (i.e., real or fake face detection) is proposed and shown to be superior over traditional binary and multi-class classification-based detectors.
- 14
- 14
- 14
- 14
- 13
- 13
- 13
- 13
- 13
- 13
- Attacks in Adversarial Machine Learning: A Systematic Survey from the Lifecycle Perspective12
It is demonstrated that isolated defenses are insufficient against coordinated multi-stage attacks, and the research community must prioritize holistic defense strategies incorporating lifecycle-aware monitoring, adaptive hardening techniques, and unified threat models.
- 12
- 12
- 12
- 12
- 12
- 12
- 11
- 11
- 11
- 11
- 11
- 11
- 11
- 11
- Hiding Faces in Plain Sight: Defending DeepFakes by Disrupting Face Detection10
A new proactive defense framework to prevent individuals from being victimized in DeepFake videos is investigated, which fools face detectors by adding dedicated adversarial perturbations to video frames and introduces VideoFacePoison, an extended strategy that can efficiently propagate FacePoison across video frames instead of applying it individually to each frame, thus significantly reducing the computational overhead while retaining favorable attack performance.
- 10
- 10
- 10
- 9
- 9
- 9
- 9
- 9
- 9
- 9
- 9
- 8
- 8
- 8
- 8
- 8
- 8
- 8
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models6
AdvChain is proposed, an alignment paradigm that teaches models dynamic self-correction through adversarial CoT tuning that significantly enhances robustness against jailbreak attacks and CoT hijacking while substantially reducing over-refusal on benign prompts, achieving a superior safety-utility balance without compromising reasoning capabilities.
- 6
- 6
- 6
- 6
- Groupwise Ranking Loss for Multi-Label Learning6
This work proposes a new loss, named Groupwise Ranking LosS (GRLS), and suggests that multi-label predictor is label-wise effective if and only if GRLS is optimal.
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- An implicit Markov random field model for the multi-scale oriented representations of natural images4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- HMGIE: Hierarchical and Multi-Grained Inconsistency Evaluation for Vision-Language Data Cleansing1
An adaptive evaluation framework, called Hierarchical and Multi-Grained Inconsistency Evaluation (HMGIE), which can provide multi-grained evaluations covering both accuracy and completeness for various image-caption pairs is designed and implemented.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.