Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks80 from public data
- Multi-attentional Deepfake Detection995
A new multi-attentional deepfake detection network that consists of three key components: multiple spatial attention heads to make the network attend to different local parts, a new regional independence loss and an attention guided data augmentation strategy, and state-of-the-art performance.
- Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain629
A novel Spatial-Phase Shallow Learning (SPSL) method is presented, which combines spatial image and phase spectrum to capture the up-sampling artifacts of face forgery to improve the transferability and theoretically analyze the validity of utilizing the phase spectrum.
- Deepfacelab: Integrated, flexible and extensible face-swapping framework379
DeepFaceLab, the current dominant deepfake framework for face-swapping, is presented and its pipeline, through which every aspect of the pipeline can be modified painlessly by users to achieve their customization purpose, is introduced.
- Model Watermarking for Image Processing Networks170
The first model watermarking framework for protecting image processing models, which can resist surrogate models learned with different network structures and objective functions is proposed and is easy to be extended to protect data and traditional image processing algorithms.
- HairCLIP: Design Your Hair by Text and Reference Image147
This paper proposes a new hair editing interaction mode, which enables manipulating hair attributes individually or jointly based on the texts or reference images provided by users, and encode the image and text conditions in a shared embedding space and proposes a unified hair editing framework.
- FInfer: Frame Inference-Based Deepfake Detection for High-Visual-Quality Videos105
A frame inference-based detection framework (FInfer) to solve the problem of high-visual-quality Deepfake detection by first learning the referenced representations of the current and future frames’ faces and utilizing an autoregressive model.
- A Robust Approach to Multimodal Deepfake Detection101
A novel approach for detecting deepfake video sequences by leveraging data multimodality that extracts audio-visual features from the input video over time and analyzes them using time-aware neural networks, and indicates that a multimodal approach is more effective than a monomodal one, even if trained on disjoint monommodal datasets.
- Initiative Defense against Facial Manipulation90
A novel framework of initiative defense to degrade the performance of facial manipulation models controlled by malicious users is proposed, which is to actively inject imperceptible venom into target facial data before manipulation.
- 64
- 60
- 58
- 50
- Improved Image Matting via Real-time User Clicks and Uncertainty Estimation42
An improved deep image matting framework which is trimap-free and only needs several user click interactions to eliminate the ambiguity is proposed, and a new uncertainty estimation module that can predict which parts need polishing and a following local refinement module is introduced.
- Adversarial batch image steganography against CNN-based pooled steganalysis37
This paper proposes a general framework of adversarial embedding for batch steganography, in which a new loss function is designed and the batch strategy is combined with adversarialembedding, and shows the proposed method significantly improves the security performance of batch Steganography against pooled steganalysis and keeps a high-security level against single image Steganalysis.
- Defining Joint Distortion for JPEG Steganography37
This paper inspects the embedding change from the spatial domain and proposes a principle of Block Boundary Continuity (BBC) for defining JPEG joint distortion, which aims to restrain blocking artifacts caused by inter-block adjacent modifications and thus effectively preserve the spatial continuity at block boundaries.
- HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending31
Besides the unprecedented user interaction mode support, quantitative and qualitative experiments demonstrate the superiority of HairCLIPv2 in terms of editing effects, irrelevant attribute preservation and visual naturalness.
- 30
- GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models23
This work constructs GenderPair, a novel pair-based benchmark designed to assess gender bias in LLMs comprehensively, and establishes pioneering criteria for gender equality benchmarks, spanning dimensions such as inclusivity, diversity, explainability, objectivity, robustness, and realisticity.
- CasaGPT: Cuboid Arrangement and Scene Assembly for Interior Design21
A novel approach for indoor scene synthesis, which learns to arrange decomposed cuboid primitives to represent 3D objects within a scene, using an autoregressive model to sequentially arrange cuboids, producing physically plausible scenes.
- 20
- 18
- Self-appreciation is not enough: exercise identity mediates body appreciation and physical activity and the role of perceived stress17
The results demonstrated that body appreciation positively predicted physical activity, exercise identity partially mediated the positive effect of body appreciation on physical activity, and perceived stress played a moderating role in body appreciation and exercise identity.
- A dual-labeled dataset and fusion model for automatic teeth segmentation, numbering, and state assessment on panoramic radiographs17
This fusion model is the first to integrate automatic dental segmentation, numbering, and state assessment of teeth on panoramic radiographs, and provides highly accurate results, including detailed visualizations and automated report generation.
- BiFPro: A Bidirectional Facial-data Protection Framework against DeepFake17
Experimental results demonstrate that the proposed Bidirectional Facial-data Protection Framework could generate the watermarking which is fragile to FOD and at the same time robust to FIF with an average watermark extraction success rate reaching more than 95% when defending against the four advanced DeepFake techniques.
- 17
- 16
- 16
- Catch You Everything Everywhere: Guarding Textual Inversion via Concept Watermarking13
The novel concept watermarking is proposed, where watermark information is embedded into the target concept and then extracted from generated images based on the watermarked concept, showing great resilience to different diffusion sampling processes possibly chosen by malicious users, meanwhile preserving utility for normal use.
- 13
- 13
- Identification of benign and malignant breast nodules on ultrasound: comparison of multiple deep learning models and model interpretation11
The weakly supervised DenseNet121 model, utilizing complete image inputs without ROI annotations, demonstrated superior diagnostic performance in distinguishing between benign and malignant breast nodules when compared to ResNet50, EfficientNetb0, and Vision Transformer models.
- UniForensics: Face Forgery Detection via General Facial Representation10
UniForensics is introduced, a novel deepfake detection framework that leverages a transformer-based video classification network, initialized with a meta-functional face encoder for enriched facial representation, that outperforms existing face forgery detection methods in generalization ability and robustness.
- 10
- Adversarial defense via self-orthogonal randomization super-network10
This paper proposes a novel type of defense method named ‘‘Self-Orthogonal Randomization Super-network” ( SORS), which can achieve significantly better robustness than the vanilla single model baseline and the naive model ensemble baseline.
- 9
- FaceRSA: RSA-Aware Facial Identity Cryptography Framework9
This paper presents the first facial identity cryptography framework with full properties analogous to RSA, and leverages the powerful generative capabilities of StyleGAN to achieve megapixel-level facial identity anonymization and deanonymization.
- SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models8
This work introduces SafeGuider, a two-step framework designed for robust safety control without compromising generation quality, which combines an embedding-level recognition model with a safety-aware feature erasure beam search algorithm and demonstrates exceptional effectiveness in minimizing attack success rates.
- Audio-Visual Contrastive Pre-train for Face Forgery Detection8
This work proposes a video-level deepfake detection method based on a temporal transformer with a self-supervised audio–visual contrastive learning approach for pre-training the deepfake detector that achieves better generalization ability in cross-dataset evaluations.
- 8
- Controversial ‘pixel’ prior rule for JPEG adaptive steganography7
The authors develop a rule for cost reassignment in spatial domain called the `controversial pixel prior (CPP)' rule, which defines controversial pixels by utilizing the controversies among several comparable schemes and name it the J-CPP rule.
- 5
- 5
- 5
- 4
- 4
- Detecting Adversarial Examples via Reconstruction-based Semantic Inconsistency4
This paper proposes a reconstruction-based detection via intrinsic features of the classifier to explore adversarial examples from the perspective of the target classifier rather than the distribution in pixel space perceived by humans.
- 4
- 4
- 4
- Rapid liquid biopsy for Mohs surgery: rare target cell separation from surgical margin lavage fluid with a high recovery rate and selectivity4
The capability of this method for rare-cell separation with a high recovery rate and good selectivity may facilitate improvement of performance of Mohs surgery for real clinical practice, including shortening examination time and increasing detection sensitivity.
- 4
- FaceTracer: Unveiling Source Identities From Swapped Face Images and Videos for Fraud Prevention3
The first non-intrusive framework specifically designed to trace the identity of the source person from swapped face images or videos, FaceTracer leverages a disentanglement module that effectively suppresses identity information related to the target person while isolating the identity features of the source person.
- ControlFace: Feature Disentangling for Controllable Face Swapping3
Extensive experiments and comparisons with state-of-the-art face swapping methods demonstrate the superiority of the proposed face swapping framework in terms of transferring identity information, producing high-quality face images, and controllable face swapping.
- Face Swapping Consistency Transfer with Neural Identity Carrier3
A novel framework Neural Identity Carrier (NICe), which learns identity transformation from an arbitrary face-swapping proxy via a U-Net through modeling the incoherence between frames as noise, guaranteeing the temporal stableness of deepfake approaches and predicting detailed results against over-smoothness.
- EARG-Net: Edge-Aware Reconstruction-Guided Network for Image Manipulation Detection and Localization2
A novel edge-aware framework that leverages the strong natural image priors of pre-trained inpainting models to harmonize manipulated regions to reconstructs tampered areas using surrounding context, yielding perceptually coherent results.
- 2
- 2
- 2
- 2
- : Color decomposition-based adversarial examples for screen devices2
Inspired by the properties of the human visual system, the first color decomposition-based adversarial example method CDAE for screen devices is designed, which decomposes one regular screen frame into two symmetric adversarial frames with maximum modifications while theoretically guaranteeing the visual quality perceived by human observers.
- 2
- 1
- 1
- 1
- Efficient Dataset Distillation through Low-Rank Space Sampling1
This paper proposes a dataset distillation method based on Matching Training Trajectories with Low-rank Space Sampling (MTT-LSS), which uses low-rank approximations to capture multiple low-dimensional manifold subspaces of the original data.
- Temporal Optimization for Face Swapping Video based on Consistency Inheritance1
A face swapping mapper network to inherit identity and suppress noise is proposed and a 3D face disentanglement model is introduced to regress FLAME parameters and guide the optimization direction precisely for facial detail consistency.
- 1
- An improved genetic algorithm in path planning for mobile robot1
A new way of crossover and mutation for genetic algorithm to prevent the local optima and guarantee the feasibility of the mutated path is proposed, and the adaptive adjustment ofrossover and mutation probability is improved to improve the search efficiency of the algorithm optimization.
- –
- –
- –
- –
- Beyond Sliders: Mastering the Art of Diffusion-based Image Manipulation–
Improved upon concept sliders, this method refines the image through fine-grained guidance—both textual and visual—in an adversarial manner, leading to a marked enhancement in image quality and realism.
- –
- –
- –
- –
- –
- Intelligent detection robot system design–
This paper develops on the existing robot platform, using external controllers and sensors, and uses hardware devices with low cost and easy control to make better detection effects to achieve multi-purpose, multi-functional environment detection.
- –
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 2026-10-12. 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.