Search Results for author:
Found 60 papers, 21 papers with code
Hierarchical Face Aging through Disentangled Latent Characteristics
To explore the age effects on facial images, we propose a Disentangled Adversarial Autoencoder (DAAE) to disentangle the facial images into three independent factors: age, identity and extraneous information.
ID-Cloak: Crafting Identity-Specific Cloaks Against Personalized Text-to-Image Generation
Personalized text-to-image models allow users to generate images of new concepts from several reference photos, thereby leading to critical concerns regarding civil privacy.
Survey on AI-Generated Media Detection: From Non-MLLM to MLLM
Despite significant progress in this field, there remains a gap in literature regarding a comprehensive survey that examines the transition from domain-specific to general-purpose detection methods.
InfoBFR: Real-World Blind Face Restoration via Information Bottleneck
Blind face restoration (BFR) is a highly challenging problem due to the uncertainty of data degradation patterns.
Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey
Consequently, understanding the methods of jailbreak attacks and existing defense mechanisms is essential to ensure the safe deployment of multimodal generative models in real-world scenarios, particularly in security-sensitive applications.
Breaking the Low-Rank Dilemma of Linear Attention
The Softmax attention mechanism in Transformer models is notoriously computationally expensive, particularly due to its quadratic complexity, posing significant challenges in vision applications.
DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation
Our second contribution, DreamClear, is a DiT-based image restoration model.
LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration
In the pre-training stage, we enhance the pre-trained CLIP model by introducing a simple mechanism that scales it to higher resolutions, allowing us to extract robust degradation representations that adaptively guide the IR network.
Deep Learning Technology for Face Forgery Detection: A Survey
This paper presents a comprehensive survey of recent deep learning-based approaches for facial forgery detection.
InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning
Pre-training on large-scale, high-quality datasets is crucial for enhancing the reasoning capabilities of Large Language Models (LLMs), especially in specialized domains such as mathematics.
ZePo: Zero-Shot Portrait Stylization with Faster Sampling
To blend the Consistency Features extracted from both content and style images, we introduce a Style Enhancement Attention Control technique that meticulously merges content and style features within the attention space of the target image.
MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs
Current multimodal misinformation detection (MMD) methods often assume a single source and type of forgery for each sample, which is insufficient for real-world scenarios where multiple forgery sources coexist.
Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model
In the realm of Multimodal Large Language Models (MLLMs), vision-language connector plays a crucial role to link the pre-trained vision encoders with Large Language Models (LLMs).
Vision Transformer with Sparse Scan Prior
In recent years, Transformers have achieved remarkable progress in computer vision tasks.
Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens
The Vision Transformer (ViT) has gained prominence for its superior relational modeling prowess.
ViTAR: Vision Transformer with Any Resolution
Firstly, we propose a novel module for dynamic resolution adjustment, designed with a single Transformer block, specifically to achieve highly efficient incremental token integration.
DiffMAC: Diffusion Manifold Hallucination Correction for High Generalization Blind Face Restoration
Experimental results demonstrate the superiority of DiffMAC over state-of-the-art methods, with a high degree of generalization in real-world and heterogeneous settings.
FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMs
The massive generation of multimodal fake news involving both text and images exhibits substantial distribution discrepancies, prompting the need for generalized detectors.
InfiMM-HD: A Leap Forward in High-Resolution Multimodal Understanding
Multimodal Large Language Models (MLLMs) have experienced significant advancements recently.
Ranked #118 on
Visual Question Answering
on MM-Vet
Portrait Diffusion: Training-free Face Stylization with Chain-of-Painting
Face stylization refers to the transformation of a face into a specific portrait style.
Exploring Straighter Trajectories of Flow Matching with Diffusion Guidance
First, we propose a coupling strategy to straighten trajectories, creating couplings between image and noise samples under diffusion model guidance.
InstaStyle: Inversion Noise of a Stylized Image is Secretly a Style Adviser
We employ DDIM inversion to extract this noise from the reference image and leverage a diffusion model to generate new stylized images from the "style" noise.
Video-Teller: Enhancing Cross-Modal Generation with Fusion and Decoupling
This paper proposes Video-Teller, a video-language foundation model that leverages multi-modal fusion and fine-grained modality alignment to significantly enhance the video-to-text generation task.
RMT: Retentive Networks Meet Vision Transformers
To alleviate these issues, we draw inspiration from the recent Retentive Network (RetNet) in the field of NLP, and propose RMT, a strong vision backbone with explicit spatial prior for general purposes.
Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classification
Consequently, we propose a cross-modal ordinal pairwise loss to refine the CLIP feature space, where texts and images maintain both semantic alignment and ordering alignment.
Lightweight Vision Transformer with Bidirectional Interaction
This paper proposes a Fully Adaptive Self-Attention (FASA) mechanism for vision transformer to model the local and global information as well as the bidirectional interaction between them in context-aware ways.
Rethinking Local Perception in Lightweight Vision Transformer
The combination of the AttnConv and vanilla attention which uses pooling to reduce FLOPs in CloFormer enables the model to perceive high-frequency and low-frequency information.
Ranked #621 on
Image Classification
on ImageNet
Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer
Unsupervised Domain Adaptation (UDA) can effectively address domain gap issues in real-world image Super-Resolution (SR) by accessing both the source and target data.
Pluralistic Aging Diffusion Autoencoder
Face aging is an ill-posed problem because multiple plausible aging patterns may correspond to a given input.
MSRA-SR: Image Super-resolution Transformer with Multi-scale Shared Representation Acquisition
In particular, self-attention with cross-scale matching and convolution filters with different kernel sizes are designed to exploit the multi-scale features in images.
Vision Transformer with Super Token Sampling
STA decomposes vanilla global attention into multiplications of a sparse association map and a low-dimensional attention, leading to high efficiency in capturing global dependencies.
Parallel Augmentation and Dual Enhancement for Occluded Person Re-identification
To alleviate these two issues, we propose a simple yet effective method with Parallel Augmentation and Dual Enhancement (PADE), which is robust on both occluded and non-occluded data and does not require any auxiliary clues.
Artistic Style Discovery With Independent Components
Style transfer has been well studied in recent years with excellent performance processed.
Rethinking Image Cropping: Exploring Diverse Compositions From Global Views
In this paper, we regard image cropping as a set prediction problem.
Contrastive Attention Network with Dense Field Estimation for Face Completion
This multi-scale architecture is beneficial for the decoder to utilize discriminative representations learned from encoders into images.
Toward Accurate and Reliable Iris Segmentation Using Uncertainty Learning
To make further efforts on accurate and reliable iris segmentation, we propose a bilateral self-attention module and design Bilateral Transformer (BiTrans) with hierarchical architecture by exploring spatial and visual relationships.
Causal Representation Learning for Context-Aware Face Transfer
Human face synthesis involves transferring knowledge about the identity and identity-dependent face shape (IDFS) of a human face to target face images where the context (e. g., facial expressions, head poses, and other background factors) may change dramatically.
Universal Face Restoration With Memorized Modulation
Blind face restoration (BFR) is a challenging problem because of the uncertainty of the degradation patterns.
Video Forgery Detection Using Multiple Cues on Fusion of EfficientNet and Swin Transformer
The first is that capturing the general clue of artifacts is difficult.
Information Bottleneck Disentanglement for Identity Swapping
In this work, we propose a novel information disentangling and swapping network, called InfoSwap, to extract the most expressive information for identity representation from a pre-trained face recognition model.
Memory Oriented Transfer Learning for Semi-Supervised Image Deraining
To address this issue, we propose a memory-oriented semi-supervised (MOSS) method which enables the network to explore and exploit the properties of rain streaks from both synthetic and real data.
DVG-Face: Dual Variational Generation for Heterogeneous Face Recognition
As a consequence, massive new diverse paired heterogeneous images with the same identity can be generated from noises.
Cosmetic-Aware Makeup Cleanser
Face verification aims at determining whether a pair of face images belongs to the same identity.
Informative Sample Mining Network for Multi-Domain Image-to-Image Translation
The performance of multi-domain image-to-image translation has been significantly improved by recent progress in deep generative models.
Exploiting Style and Attention in Real-World Super-Resolution
Real-world image super-resolution (SR) is a challenging image translation problem.
LAMP-HQ: A Large-Scale Multi-Pose High-Quality Database and Benchmark for NIR-VIS Face Recognition
A spectral conditional attention module is introduced to reduce the domain gap between NIR and VIS data and then improve the performance of NIR-VIS heterogeneous face recognition on various databases including the LAMP-HQ.
Dual Variational Generation for Low Shot Heterogeneous Face Recognition
Specifically, we first introduce a dual variational autoencoder to represent a joint distribution of paired heterogeneous images.
Biphasic Learning of GANs for High-Resolution Image-to-Image Translation
In this work, we present a novel training framework for GANs, namely biphasic learning, to achieve image-to-image translation in multiple visual domains at $1024^2$ resolution.
UVA: A Universal Variational Framework for Continuous Age Analysis
UVA is the first attempt to achieve facial age analysis tasks, including age translation, age generation and age estimation, in a universal framework.
Dual Variational Generation for Low-Shot Heterogeneous Face Recognition
Then, in order to ensure the identity consistency of the generated paired heterogeneous images, we impose a distribution alignment in the latent space and a pairwise identity preserving in the image space.
Ranked #1 on
Face Verification
on CASIA NIR-VIS 2.0
A Survey of Deep Facial Attribute Analysis
Deep learning based facial attribute analysis consists of two basic sub-issues: facial attribute estimation (FAE), which recognizes whether facial attributes are present in given images, and facial attribute manipulation (FAM), which synthesizes or removes desired facial attributes.
Arbitrary Talking Face Generation via Attentional Audio-Visual Coherence Learning
Talking face generation aims to synthesize a face video with precise lip synchronization as well as a smooth transition of facial motion over the entire video via the given speech clip and facial image.
Disentangled Variational Representation for Heterogeneous Face Recognition
Visible (VIS) to near infrared (NIR) face matching is a challenging problem due to the significant domain discrepancy between the domains and a lack of sufficient data for training cross-modal matching algorithms.
Ranked #2 on
Face Verification
on CASIA NIR-VIS 2.0
IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis
On the other hand, the inference model is encouraged to classify between the generated and real samples while the generator tries to fool it as GANs.
Wavelet-SRNet: A Wavelet-Based CNN for Multi-Scale Face Super Resolution
Most modern face super-resolution methods resort to convolutional neural networks (CNN) to infer high-resolution (HR) face images.
Ranked #3 on
Face Hallucination
on FFHQ 512 x 512 - 16x upscaling
