Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks65 from public data
- UCF: Uncovering Common Features for Generalizable Deepfake Detection341
A disentanglement framework that decomposes image information into three distinct components: forgery-irrelevant, method-specific forgery, and common forgery features is proposed and can perform superior generalization than current state-of-the-art methods.
- High-Fidelity GAN Inversion for Image Attribute Editing311
A novel highfidelity generative adversarial network (GAN) inversion framework that enables attribute editing with image-specific details well-preserved with a clear improvement in both inversion and editing quality is presented.
- 166
- DAE-GAN: Dynamic Aspect-aware GAN for Text-to-Image Synthesis131
A Dynamic Aspect-awarE GAN (DAE-GAN) that represents text information comprehensively from multiple granularities, including sentence- level, word-level, and aspect-level is proposed and developed, inspired by human learning behaviors.
- Enhancing Fine-Tuning based Backdoor Defense with Sharpness-Aware Minimization122
The FT-SAM is proposed, a novel backdoor defense paradigm that aims to shrink the norms of backdoor-related neurons by incorporating sharpness-aware minimization with fine-tuning, and provides a promising avenue for improving the robustness of machine learning models against backdoor attacks.
- Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection108
Extensive experiments demonstrate that the proposed Parallel Rectangle Flip Attack (PRFA) can effectively and efficiently attack various popular object detectors, including anchor-based and anchor- free, and generate transferable adversarial examples.
- 107
- Sparse Adversarial Attack via Perturbation Factorization101
An e-cient algorithm is developed by equivalently reformulating the MIP problem as a continuous optimization problem to jointly optimize the binary selection factors and continuous perturbation magnitudes of all pixels, with a cardinality constraint on selection factors to explicitly control the degree of sparsity.
- Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning96
A large-scale multi-label image database with 18M images and 11K categories is built, dubbed Tencent ML-Images, to enhance the quality of visual representation of the trained CNN model and to promote other vision tasks in the research and industry community.
- Robust Physical-World Attacks on Face Recognition71
A novel robust physical attack framework is proposed, dubbed PadvFace, to model these challenging variations of stickers, faces, and environmental conditions and an efficient Curriculum Adversarial Attack algorithm is proposed that gradually adapts adversarial stickers to environmental variations from easy to complex.
- DPE: Disentanglement of Pose and Expression for General Video Portrait Editing69
This paper introduces a novel self-supervised disentanglement framework to decouple pose and expression without 3DMMs and paired data, which consists of a motion editing module, a pose generator, and an expression generator and proposes a bidirectional cyclic training strategy with well-designed constraints.
- VDTR: Video Deblurring With Transformer68
VDTR is an effective Transformer-based model that makes the first attempt to adapt pure Transformer for video deblurring, and achieves highly competitive results on both synthetic and real-world videodeblurring benchmarks, including DVD, GOPRO, REDS and BSD.
- NOFA: NeRF-based One-shot Facial Avatar Reconstruction67
This work proposes a one-shot 3D facial avatar reconstruction framework that only requires a single source image to reconstruct a high-fidelity 3d facial avatar, and develops an efficient encoder-decoder network to reconstruct the canonical neural volume of the source image, and proposes a compensation network to complement facial details.
- Generalizable Black-Box Adversarial Attack With Meta Learning66
A meta-learning framework is developed by training a meta generator to produce perturbations conditioned on benign examples by utilizing model-level adversarial transferability to train the meta generator on a white-box surrogate model, then transfer it to help the attack against the target model.
- 3D GAN Inversion with Facial Symmetry Prior63
This work designs a pipeline and constraints to make full use of the pseudo auxiliary view obtained via image flipping, which helps obtain a view-consistent and well-structured geometry shape during the inversion process, and introduces facial symmetry prior.
- Self-Paced Learning: An Implicit Regularization Perspective63
It is demonstrated that the learning procedure of SPL-IR is associated with latent robust loss functions, thus can provide some theoretical insights for its working mechanism and demonstrate the correctness and effectiveness of implicit regularizers.
- Exact Adversarial Attack to Image Captioning via Structured Output Learning With Latent Variables61
This work proposes to fool an image captioning system to generate some targeted partial captions for an image polluted by adversarial noises, even the targeted captions are totally irrelevant to the image content.
- Fast Adversarial Training With Adaptive Step Size58
It is shown that catastrophic overfitting is instance-dependent, and fitting instances with larger input gradient norm is more likely to cause catastrophic over fitting, and a simple but effective method, Adversarial Training with Adaptive Step size (ATAS), is proposed, which learns an instance-wise adaptive step size that is inversely proportional to its gradient norm.
- 53
- HyP 2 Loss: Beyond Hypersphere Metric Space for Multi-label Image Retrieval51
A novel metric learning framework with Hybrid Proxy-Pair Loss (HyP$^2$ Loss) that constructs an expressive metric space with efficient training complexity and focuses on optimizing the hypersphere space by learnable proxies and excavating data-to-data correlations of irrelevant pairs.
- 47
- High-fidelity Facial Avatar Reconstruction from Monocular Video with Generative Priors45
This work proposes an efficient method to construct the personalized generative prior based on a small set of facial images of a given individual that allows for photo-realistic rendering with novel views, and the face reenactment can be realized by performing navigation in the latent space of 3D-GAN.
- 45
- 42
- 40
- 39
- Context-Aware Cross-Attention for Skeleton-Based Human Action Recognition38
A cross-attention module that consists of a self-att attention branch and a cross-Attention branch for skeleton-based action recognition to extract joints that are not only more informative but also highly correlated to the corresponding scenario context information.
- 20
- ToonTalker: Cross-Domain Face Reenactment18
This paper proposes a transformer-based framework to align the motions from different domains into a common latent space where motion transfer is conducted via latent code addition and proposes a novel cross-domain reenactment without paired data.
- AvatarArtist: Open-Domain 4D Avatarization16
This work focuses on open-domain 4D avatarization, and selects parametric triplanes as the intermediate 4D representation, and proposes a practical training paradigm that takes advantage of both generative adversarial networks (GANs) and diffusion models.
- 16
- Regional Adversarial Training for Better Robust Generalization14
A new adversarial training framework that considers the diversity as well as characteristics of the perturbed points in the vicinity of benign samples, and proposes a Regional Adversarial Training (RAT) defense method that first utilizes the attack path generated by the typical iterative attack method of projected gradient descent (PGD).
- 13
- 12
- Hybrid Explicit Representation for Ultra-Realistic Head Avatars11
Experiments demonstrate that this approach adapts the appropriate type of primitives to represent the different parts of the dynamic scene and outperforms all the baseline methods in both quantitative and qualitative comparisons without losing render speed.
- 11
- Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients10
This work studies the detection of adversarial examples based on the assumption that the output and internal responses of one DNN model for both adversarial and benign examples follow the generalized Gaussian distribution but with different parameters (i.e., shape factor, mean, and variance).
- 9
- Adaptive Smoothness-weighted Adversarial Training for Multiple Perturbations with Its Stability Analysis8
The smoothness analysis of ATMP is provided and it is shown that adversaries give different contributions to the smoothness of the loss function of AT MP, which develops the stability-based excess risk bounds and proposes adaptive smoothness-weighted adversarial training for multiple perturbations.
- 7
- 7
- 7
- Efficient Black-Box Adversarial Attack Guided by the Distribution of Adversarial Perturbations.6
This work proposed to transform the Gaussian-distributed variable to another space through a conditional flow-based model, to enhance the capability and flexibility of capturing the intrinsic distribution of adversarial perturbations conditioned on the benign example, and pre-train the conditional flow model based on some white-box surrogate models.
- 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.
- 5
- 5
- 4
- 4
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 1
- 1
- 1
- –
- –
- Improving the Latent Space of Image Style Transfer–
Two contrastive training schemes are proposed to solve issues in the latent space used by style transfer, where the style contrastive loss pulls the stylized result closer to the same visual style image and pushes it away from the content image.
- –
- –
- –
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.