Search Results for author:
Found 190 papers, 71 papers with code
Binarized Neural Network for Single Image Super Resolution
Lighter model and faster inference are the focus of current single image super-resolution (SISR) research.
Big Brother is Watching: Proactive Deepfake Detection via Learnable Hidden Face
As deepfake technologies continue to advance, passive detection methods struggle to generalize with various forgery manipulations and datasets.
Structure-Accurate Medical Image Translation based on Dynamic Frequency Balance and Knowledge Guidance
Multimodal medical images play a crucial role in the precise and comprehensive clinical diagnosis.
A Knowledge-guided Adversarial Defense for Resisting Malicious Visual Manipulation
The generated adversarial noise can actively interfere with the malicious manipulation model by triggering knowledge-guided and perception-related disruptions in the fake samples.
Unbiased Max-Min Embedding Classification for Transductive Few-Shot Learning: Clustering and Classification Are All You Need
Our UMMEC method significantly improves classification performance with minimal labeled data, advancing the state-of-the-art in TFSL.
Extremely Simple Out-of-distribution Detection for Audio-visual Generalized Zero-shot Learning
Zero-shot Learning(ZSL) attains knowledge transfer from seen classes to unseen classes by exploring auxiliary category information, which is a promising yet difficult research topic.
Dynamic Cross-Modal Feature Interaction Network for Hyperspectral and LiDAR Data Classification
To address these limitations, we propose a novel Dynamic Cross-Modal Feature Interaction Network (DCMNet), the first framework leveraging a dynamic routing mechanism for HSI and LiDAR classification.
GBFRS: Robust Fuzzy Rough Sets via Granular-ball Computing
Fuzzy rough set theory is effective for processing datasets with complex attributes, supported by a solid mathematical foundation and closely linked to kernel methods in machine learning.
A Multi-annotated and Multi-modal Dataset for Wide-angle Video Quality Assessment
Wide-angle video is favored for its wide viewing angle and ability to capture a large area of scenery, making it an ideal choice for sports and adventure recording.
CSHNet: A Novel Information Asymmetric Image Translation Method
To address this, we propose the CNN-Swin Hybrid Network (CSHNet), which combines two key modules: Swin Embedded CNN (SEC) and CNN Embedded Swin (CES), forming the SEC-CES-Bottleneck (SCB).
iFADIT: Invertible Face Anonymization via Disentangled Identity Transform
However, many still face limitations in visual quality and often overlook the potential to recover the original face from the anonymized version, which can be valuable in specific contexts such as image forensics.
CognitionCapturer: Decoding Visual Stimuli From Human EEG Signal With Multimodal Information
This results in the loss of critical multimodal information in EEG.
Motion Artifact Removal in Pixel-Frequency Domain via Alternate Masks and Diffusion Model
Motion artifacts present in magnetic resonance imaging (MRI) can seriously interfere with clinical diagnosis.
Jointly RS Image Deblurring and Super-Resolution with Adjustable-Kernel and Multi-Domain Attention
In the deblurring branch, we design a pixel-adjustable kernel block (PAKB) to estimate the local and spatial-varying blur kernels.
AI-Generated Image Quality Assessment Based on Task-Specific Prompt and Multi-Granularity Similarity
Recently, AI-generated images (AIGIs) created by given prompts (initial prompts) have garnered widespread attention.
Mamba-CL: Optimizing Selective State Space Model in Null Space for Continual Learning
Continual Learning (CL) aims to equip AI models with the ability to learn a sequence of tasks over time, without forgetting previously learned knowledge.
SA3DIP: Segment Any 3D Instance with Potential 3D Priors
Thus, we present ScanNetV2-INS with complete ground truth labels and supplement additional instances for 3D class-agnostic instance segmentation.
Show Me What and Where has Changed? Question Answering and Grounding for Remote Sensing Change Detection
Furthermore, we present VisTA, a simple yet effective baseline method that unifies the tasks of question answering and grounding by delivering both visual and textual answers.
GBCT: An Efficient and Adaptive Granular-Ball Clustering Algorithm for Complex Data
Traditional clustering algorithms often focus on the most fine-grained information and achieve clustering by calculating the distance between each pair of data points or implementing other calculations based on points.
Effective Diffusion Transformer Architecture for Image Super-Resolution
In this work, we design an effective diffusion transformer for image super-resolution (DiT-SR) that achieves the visual quality of prior-based methods, but through a training-from-scratch manner.
Beyond Euclidean: Dual-Space Representation Learning for Weakly Supervised Video Violence Detection
While numerous Video Violence Detection (VVD) methods have focused on representation learning in Euclidean space, they struggle to learn sufficiently discriminative features, leading to weaknesses in recognizing normal events that are visually similar to violent events (\emph{i. e.}, ambiguous violence).
Infrared and Visible Image Fusion with Hierarchical Human Perception
Existing methods take pixel intensity, texture and high-level vision task information as the standards to determine preservation of information, lacking enhancement for human perception.
Knowledge-Enhanced Facial Expression Recognition with Emotional-to-Neutral Transformation
Then, we transform the facial expression representation to a neutral representation by simulating the difference in text embeddings from textual facial expression to textual neutral.
Facial Expression Recognition
Facial Expression Recognition (FER)
Unleashing the Power of Generic Segmentation Models: A Simple Baseline for Infrared Small Target Detection
Recent advancements in deep learning have greatly advanced the field of infrared small object detection (IRSTD).
Non-target Divergence Hypothesis: Toward Understanding Domain Gaps in Cross-Modal Knowledge Distillation
Compared to single-modal knowledge distillation, cross-modal knowledge distillation faces more severe challenges due to domain gaps between modalities.
Foodfusion: A Novel Approach for Food Image Composition via Diffusion Models
However, existing diffusion models face challenges in processing and fusing information from multiple images and lack access to high-quality publicly available datasets, which prevents the application of diffusion models in food image composition.
MsMemoryGAN: A Multi-scale Memory GAN for Palm-vein Adversarial Purification
At the testing stage, given an adversarial sample, the MsMemoryGAN retrieves its most relevant normal patterns in memory for the reconstruction.
One Step Diffusion-based Super-Resolution with Time-Aware Distillation
Specifically, we introduce a novel score distillation strategy to align the data distribution between the outputs of the student and teacher models after minor noise perturbation.
Neural Architecture Search based Global-local Vision Mamba for Palm-Vein Recognition
In this paper, first, we propose a hybrid network structure named Global-local Vision Mamba (GLVM), to learn the local correlations in images explicitly and global dependencies among tokens for vein feature representation.
The Llama 3 Herd of Models
This paper presents a new set of foundation models, called Llama 3.
Ranked #3 on
Question Answering
on PeerQA
Thinking Racial Bias in Fair Forgery Detection: Models, Datasets and Evaluations
In the paper, we first contribute a dedicated dataset called the Fair Forgery Detection (FairFD) dataset, where we prove the racial bias of public state-of-the-art (SOTA) methods.
IRSAM: Advancing Segment Anything Model for Infrared Small Target Detection
The recent Segment Anything Model (SAM) is a significant advancement in natural image segmentation, exhibiting potent zero-shot performance suitable for various downstream image segmentation tasks.
SUMix: Mixup with Semantic and Uncertain Information
Mixup data augmentation approaches have been applied for various tasks of deep learning to improve the generalization ability of deep neural networks.
Federated Face Forgery Detection Learning with Personalized Representation
In addition, a personalized federated learning training strategy is utilized to update the parameters of the distributed detection model.
Imperceptible Face Forgery Attack via Adversarial Semantic Mask
With the great development of generative model techniques, face forgery detection draws more and more attention in the related field.
Improving Adversarial Robustness via Decoupled Visual Representation Masking
The robust feature of intra-class samples can maintain appropriate diversity; 2) \textbf{Discriminability}.
CLIP-Driven Cloth-Agnostic Feature Learning for Cloth-Changing Person Re-Identification
Specifically, IFP is designed to extract fine-grained semantic features unrelated to clothes from the raw image, guided by the cloth-agnostic text prompts.
Pulmonary Embolism Mortality Prediction Using Multimodal Learning Based on Computed Tomography Angiography and Clinical Data
Imaging features and/or clinical variables were then incorporated into DL models to predict survival outcomes.
An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition
Significant action recognition performance is achieved when evaluated on the challenging NTU RGB+D, NTU RGB+D 120, and PKU-MMD benchmarks and validate that multi-granularity semantic features facilitate the differentiation of action clusters with similar visual features.
MindSemantix: Deciphering Brain Visual Experiences with a Brain-Language Model
MindSemantix generates high-quality captions that are deeply rooted in the visual and semantic information derived from brain activity.
Multi-modality Regional Alignment Network for Covid X-Ray Survival Prediction and Report Generation
In response to the worldwide COVID-19 pandemic, advanced automated technologies have emerged as valuable tools to aid healthcare professionals in managing an increased workload by improving radiology report generation and prognostic analysis.
Region-specific Risk Quantification for Interpretable Prognosis of COVID-19
The COVID-19 pandemic has strained global public health, necessitating accurate diagnosis and intervention to control disease spread and reduce mortality rates.
Weakly Supervised LiDAR Semantic Segmentation via Scatter Image Annotation
Specifically, we propose employing scatter images to annotate LiDAR point clouds, combining a pre-trained optical flow estimation network with a foundation image segmentation model to rapidly propagate manual annotations into dense labels for both images and point clouds.
Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks
Despite providing high-performance solutions for computer vision tasks, the deep neural network (DNN) model has been proved to be extremely vulnerable to adversarial attacks.
InstructBrush: Learning Attention-based Instruction Optimization for Image Editing
Two key techniques are introduced into InstructBrush, Attention-based Instruction Optimization and Transformation-oriented Instruction Initialization, to address the limitations of the previous method in terms of inversion effects and instruction generalization.
An Open-World, Diverse, Cross-Spatial-Temporal Benchmark for Dynamic Wild Person Re-Identification
Person re-identification (ReID) has made great strides thanks to the data-driven deep learning techniques.
Semi-Supervised Learning for Anomaly Traffic Detection via Bidirectional Normalizing Flows
We consider the problem of anomaly network traffic detection and propose a three-stage anomaly detection framework using only normal traffic.
Are Dense Labels Always Necessary for 3D Object Detection from Point Cloud?
Current state-of-the-art (SOTA) 3D object detection methods often require a large amount of 3D bounding box annotations for training.
DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusion
To effectively mine the complementary information and adapt to misalignment situations, we propose a Multispectral Deformable Cross-attention module to adaptively sample and aggregate multi-semantic level features of infrared and visible images for each object.
Diffusion Model Based Visual Compensation Guidance and Visual Difference Analysis for No-Reference Image Quality Assessment
Firstly, we devise a new diffusion restoration network that leverages the produced enhanced image and noise-containing images, incorporating nonlinear features obtained during the denoising process of the diffusion model, as high-level visual information.
Jailbreaking Attack against Multimodal Large Language Model
This paper focuses on jailbreaking attacks against multi-modal large language models (MLLMs), seeking to elicit MLLMs to generate objectionable responses to harmful user queries.
Exploring Homogeneous and Heterogeneous Consistent Label Associations for Unsupervised Visible-Infrared Person ReID
While prior work focuses on establishing cross-modality pseudo-label associations to bridge the modality-gap, they ignore maintaining the instance-level homogeneous and heterogeneous consistency between the feature space and the pseudo-label space, resulting in coarse associations.
Bridging Generative and Discriminative Models for Unified Visual Perception with Diffusion Priors
Our purpose is to establish a unified visual perception framework, capitalizing on the potential synergies between generative and discriminative models.
AFD: Mitigating Feature Gap for Adversarial Robustness by Feature Disentanglement
We introduce a feature disentangler to separate out the specific latent features from the features of the adversarial samples, thereby boosting robustness by eliminating the specific latent features.
Masked Attribute Description Embedding for Cloth-Changing Person Re-identification
To address this, we mask the clothing and color information in the personal attribute description extracted through an attribute detection model.
EmMixformer: Mix transformer for eye movement recognition
To this end, we propose a mixed block consisting of three modules, transformer, attention Long short-term memory (attention LSTM), and Fourier transformer.
Disentangled Prompt Representation for Domain Generalization
Although there is a growing focus on VFM-based domain prompt tuning for DG effectively learning prompts that disentangle invariant features across all domains remains a major challenge.
Point Deformable Network with Enhanced Normal Embedding for Point Cloud Analysis
Additional offsets and modulation scalars are learned on the whole point features, which shift the deformable reference points to the regions of interest.
Adversarial AutoMixup
In this paper, we propose AdAutomixup, an adversarial automatic mixup augmentation approach that generates challenging samples to train a robust classifier for image classification, by alternatively optimizing the classifier and the mixup sample generator.
Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model
Adversarial attacks involve adding perturbations to the source image to cause misclassification by the target model, which demonstrates the potential of attacking face recognition models.
A Dual Domain Multi-exposure Image Fusion Network based on the Spatial-Frequency Integration
Specifically, we introduce a Spatial-Frequency Fusion Block to facilitate efficient interaction between dual domains and capture complementary information from input images with different exposures.
Symmetrical Bidirectional Knowledge Alignment for Zero-Shot Sketch-Based Image Retrieval
In this paper, we propose a novel Symmetrical Bidirectional Knowledge Alignment for zero-shot sketch-based image retrieval (SBKA).
Multi-Scene Generalized Trajectory Global Graph Solver with Composite Nodes for Multiple Object Tracking
In addition to the previous method of treating objects as nodes, the network innovatively treats object trajectories as nodes for information interaction, improving the graph neural network's feature representation capability.
DeepFidelity: Perceptual Forgery Fidelity Assessment for Deepfake Detection
Considering the complexity of the quality distribution of both real and fake faces, we propose a novel Deepfake detection framework named DeepFidelity to adaptively distinguish real and fake faces with varying image quality by mining the perceptual forgery fidelity of face images.
A Multi-scale Information Integration Framework for Infrared and Visible Image Fusion
In this study, we propose a multi-scale dual attention (MDA) framework for infrared and visible image fusion, which is designed to measure and integrate complementary information in both structure and loss function at the image and patch level.
EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Model
To further clarify the noise of expanded boundaries, we combine mutual learning with a tailored proposal-level contrastive objective to use a learnable approach to harmonize a balance between incomplete yet clean (initial) and comprehensive yet noisy (expanded) boundaries for more precise ones.
CatVersion: Concatenating Embeddings for Diffusion-Based Text-to-Image Personalization
We propose CatVersion, an inversion-based method that learns the personalized concept through a handful of examples.
HFORD: High-Fidelity and Occlusion-Robust De-identification for Face Privacy Protection
To disentangle the latent codes in the GAN inversion space, we introduce an Identity Disentanglement Module (IDM).
GazeForensics: DeepFake Detection via Gaze-guided Spatial Inconsistency Learning
DeepFake detection is pivotal in personal privacy and public safety.
Shape-centered Representation Learning for Visible-Infrared Person Re-identification
One pertains to the dependence on auxiliary models for shape feature extraction in the inference phase, along with the errors in generated infrared shapes due to the intrinsic modality disparity.
Ranking-based Adaptive Query Generation for DETRs in Crowded Pedestrian Detection
Moreover, to train the rank prediction head better, we propose Soft Gradient L1 Loss.
Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteria
Deep neural networks are vulnerable to adversarial noise.
Ranked #1 on
Adversarial Defense
on CIFAR-100
Gradient constrained sharpness-aware prompt learning for vision-language models
This paper targets a novel trade-off problem in generalizable prompt learning for vision-language models (VLM), i. e., improving the performance on unseen classes while maintaining the performance on seen classes.
Diff-Privacy: Diffusion-based Face Privacy Protection
In this paper, we unify the task of anonymization and visual identity information hiding and propose a novel face privacy protection method based on diffusion models, dubbed Diff-Privacy.
Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentation
The most recent methods of this kind measure the uncertainty of each pre-divided region for manual labelling but they suffer from redundant information and require additional efforts for region division.
ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution
Single hyperspectral image super-resolution (single-HSI-SR) aims to restore a high-resolution hyperspectral image from a low-resolution observation.
Attention Consistency Refined Masked Frequency Forgery Representation for Generalizing Face Forgery Detection
Due to the successful development of deep image generation technology, visual data forgery detection would play a more important role in social and economic security.
PRO-Face S: Privacy-preserving Reversible Obfuscation of Face Images via Secure Flow
This paper proposes a novel paradigm for facial privacy protection that unifies multiple characteristics including anonymity, diversity, reversibility and security within a single lightweight framework.
MMNet: Multi-Collaboration and Multi-Supervision Network for Sequential Deepfake Detection
Advanced manipulation techniques have provided criminals with opportunities to make social panic or gain illicit profits through the generation of deceptive media, such as forged face images.
SMC-UDA: Structure-Modal Constraint for Unsupervised Cross-Domain Renal Segmentation
Medical image segmentation based on deep learning often fails when deployed on images from a different domain.
SAR-to-Optical Image Translation via Thermodynamics-inspired Network
Synthetic aperture radar (SAR) is prevalent in the remote sensing field but is difficult to interpret in human visual perception.
Efficient Bilateral Cross-Modality Cluster Matching for Unsupervised Visible-Infrared Person ReID
To this end, we propose a novel bilateral cluster matching-based learning framework to reduce the modality gap by matching cross-modality clusters.
Unsupervised Visible-Infrared Person ReID by Collaborative Learning with Neighbor-Guided Label Refinement
Unsupervised learning visible-infrared person re-identification (USL-VI-ReID) aims at learning modality-invariant features from unlabeled cross-modality dataset, which is crucial for practical applications in video surveillance systems.
Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition
Also, humans have brain regions dedicated to understanding the minds of others and analyzing their intentions, such as the medial prefrontal cortex of the temporal lobe.
Ranked #3 on
Skeleton Based Action Recognition
on NTU RGB+D 120
(using extra training data)
Selecting Learnable Training Samples is All DETRs Need in Crowded Pedestrian Detection
However, in crowded pedestrian detection, the performance of DETRs is still unsatisfactory due to the inappropriate sample selection method which results in more false positives.
Rethinking k-means from manifold learning perspective
Although numerous clustering algorithms have been developed, many existing methods still leverage k-means technique to detect clusters of data points.
Adapt and Align to Improve Zero-Shot Sketch-Based Image Retrieval
Zero-shot sketch-based image retrieval (ZS-SBIR) is challenging due to the cross-domain nature of sketches and photos, as well as the semantic gap between seen and unseen image distributions.
Boosting Weakly-Supervised Temporal Action Localization with Text Information
For the discriminative objective, we propose a Text-Segment Mining (TSM) mechanism, which constructs a text description based on the action class label, and regards the text as the query to mine all class-related segments.
Weakly-Supervised Temporal Action Localization with Bidirectional Semantic Consistency Constraint
The proposed Bi-SCC firstly adopts a temporal context augmentation to generate an augmented video that breaks the correlation between positive actions and their co-scene actions in the inter-video; Then, a semantic consistency constraint (SCC) is used to enforce the predictions of the original video and augmented video to be consistent, hence suppressing the co-scene actions.
Weakly-supervised Temporal Action Localization
Weakly Supervised Temporal Action Localization
SAWU-Net: Spatial Attention Weighted Unmixing Network for Hyperspectral Images
To this end, we put forward a spatial attention weighted unmixing network, dubbed as SAWU-Net, which learns a spatial attention network and a weighted unmixing network in an end-to-end manner for better spatial feature exploitation.
Granular-ball computing: an efficient, robust, and interpretable adaptive multi-granularity representation and computation method
This mechanism inherently possesses an adaptive multi-granularity description capacity, resulting in computational traits such as efficiency, robustness, and interpretability.
Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detection
State-of-the-art 3D object detectors are usually trained on large-scale datasets with high-quality 3D annotations.
Multi-View Clustering via Semi-non-negative Tensor Factorization
Multi-view clustering (MVC) based on non-negative matrix factorization (NMF) and its variants have received a huge amount of attention in recent years due to their advantages in clustering interpretability.
Research on Efficient Fuzzy Clustering Method Based on Local Fuzzy Granular balls
In recent years, the problem of fuzzy clustering has been widely concerned.
GBMST: An Efficient Minimum Spanning Tree Clustering Based on Granular-Ball Computing
We construct coarsegrained granular-balls, and then use granular-balls and MST to implement the clustering method based on "large-scale priority", which can greatly avoid the influence of outliers and accelerate the construction process of MST.
Few-shot Font Generation by Learning Style Difference and Similarity
To address this issue, we propose a novel font generation approach by learning the Difference between different styles and the Similarity of the same style (DS-Font).
DLBD: A Self-Supervised Direct-Learned Binary Descriptor
Since their binarization processes are not a component of the network, the learning-based binary descriptor cannot fully utilize the advances of deep learning.
MCF: Mutual Correction Framework for Semi-Supervised Medical Image Segmentation
Inspired by the plain contrast idea, MCF introduces two different subnets to explore and utilize the discrepancies between subnets to correct cognitive bias of the model.
Hierarchical Forgery Classifier On Multi-modality Face Forgery Clues
Face forgery detection plays an important role in personal privacy and social security.
Multi-adversarial Faster-RCNN with Paradigm Teacher for Unrestricted Object Detection
Our proposed MAF has two distinct contributions: (1) The Hierarchical Domain Feature Alignment (HDFA) module is introduced to minimize the image-level domain disparity, where Scale Reduction Module (SRM) reduces the feature map size without information loss and increases the training efficiency.
All-to-key Attention for Arbitrary Style Transfer
In this paper, we propose a novel all-to-key attention mechanism -- each position of content features is matched to stable key positions of style features -- that is more in line with the characteristics of style transfer.
Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE
This technical report briefly describes our JDExplore d-team's Vega v2 submission on the SuperGLUE leaderboard.
Ranked #1 on
Common Sense Reasoning
on ReCoRD
Neighbour Consistency Guided Pseudo-Label Refinement for Unsupervised Person Re-Identification
In this paper, we propose a Neighbour Consistency guided Pseudo Label Refinement (NCPLR) framework, which can be regarded as a transductive form of label propagation under the assumption that the prediction of each example should be similar to its nearest neighbours'.
Class-Dependent Label-Noise Learning with Cycle-Consistency Regularization Feature Space
We show that the cycle-consistency regularization helps to minimize the volume of the transition matrix T indirectly without exploiting the estimated noisy class posterior, which could further encourage the estimated transition matrix T to converge to its optimal solution.
Multi-view Multi-label Anomaly Network Traffic Classification based on MLP-Mixer Neural Network
In this paper, we propose an MLP-Mixer based multi-view multi-label neural network for network traffic classification.
Contextual Learning in Fourier Complex Field for VHR Remote Sensing Images
By stacking various layers of CSA blocks, we propose the Fourier Complex Transformer (FCT) model to learn global contextual information from VHR aerial images following the hierarchical manners.
Granular-Ball Fuzzy Set and Its Implementation in SVM
Most existing fuzzy set methods use points as their input, which is the finest granularity from the perspective of granular computing.
FedForgery: Generalized Face Forgery Detection with Residual Federated Learning
Experiments conducted on publicly available face forgery detection datasets prove the superior performance of the proposed FedForgery.
GBSVM: Granular-ball Support Vector Machine
Furthermore, a particle swarm optimization algorithm is designed to solve the dual model.
Hiding Visual Information via Obfuscating Adversarial Perturbations
Growing leakage and misuse of visual information raise security and privacy concerns, which promotes the development of information protection.
LKD-Net: Large Kernel Convolution Network for Single Image Dehazing
The designed DLKCB can split the deep-wise large kernel convolution into a smaller depth-wise convolution and a depth-wise dilated convolution without introducing massive parameters and computational overhead.
Seeking Subjectivity in Visual Emotion Distribution Learning
In psychology, the \textit{Object-Appraisal-Emotion} model has demonstrated that each individual's emotion is affected by his/her subjective appraisal, which is further formed by the affective memory.
Improving Adversarial Robustness via Mutual Information Estimation
To alleviate this negative effect, in this paper, we investigate the dependence between outputs of the target model and input adversarial samples from the perspective of information theory, and propose an adversarial defense method.
TransFA: Transformer-based Representation for Face Attribute Evaluation
The multiple branches transformer is employed to explore the inter-correlation between different attributes in similar semantic regions for attribute feature learning.
Spatial-Temporal Frequency Forgery Clue for Video Forgery Detection in VIS and NIR Scenario
In recent years, with the rapid development of face editing and generation, more and more fake videos are circulating on social media, which has caused extreme public concerns.
Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation
In label-noise learning, estimating the transition matrix has attracted more and more attention as the matrix plays an important role in building statistically consistent classifiers.
Do Deep Neural Networks Always Perform Better When Eating More Data?
Data has now become a shortcoming of deep learning.
Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation
The state-of-the-art deep learning-based methods often simply concatenate the raw geometric attributes (i. e., coordinates and normal vectors) of mesh cells to train a single-stream network for automatic intra-oral scanner image segmentation.
Robust Single Image Dehazing Based on Consistent and Contrast-Assisted Reconstruction
To properly address this problem, we propose a novel density-variational learning framework to improve the robustness of the image dehzing model assisted by a variety of negative hazy images, to better deal with various complex hazy scenarios.
Towards Semi-Supervised Deep Facial Expression Recognition with An Adaptive Confidence Margin
In this paper, we learn an Adaptive Confidence Margin (Ada-CM) to fully leverage all unlabeled data for semi-supervised deep facial expression recognition.
Facial Expression Recognition
Facial Expression Recognition (FER)
SSCU-Net: Spatial-Spectral Collaborative Unmixing Network for Hyperspectral Images
Important findings on the use of spatial and spectral information in the autoencoder framework are discussed.
Semi-parametric Makeup Transfer via Semantic-aware Correspondence
The large discrepancy between the source non-makeup image and the reference makeup image is one of the key challenges in makeup transfer.
An Efficient and Adaptive Granular-ball Generation Method in Classification Problem
In addition, this paper first provides the mathematical models for the granular-ball covering.
A Unified Granular-ball Learning Model of Pawlak Rough Set and Neighborhood Rough Set
The granular-ball rough set can simultaneously represent Pawlak rough sets, and the neighborhood rough set, so as to realize the unified representation of the two.
SS3D: Sparsely-Supervised 3D Object Detection From Point Cloud
In the meantime, we design a reliable background mining module and a point cloud filling data augmentation strategy to generate the confident data for iteratively learning with reliable supervision.
An Efficient and Accurate Rough Set for Feature Selection, Classification and Knowledge Representation
This paper present a strong data mining method based on rough set, which can realize feature selection, classification and knowledge representation at the same time.
Image-specific Convolutional Kernel Modulation for Single Image Super-resolution
Recently, deep-learning-based super-resolution methods have achieved excellent performances, but mainly focus on training a single generalized deep network by feeding numerous samples.
Event Data Association via Robust Model Fitting for Event-based Object Tracking
In EDA, we first asynchronously fuse the event data based on its information entropy.
SOLVER: Scene-Object Interrelated Visual Emotion Reasoning Network
Inspired by this, we propose a novel Scene-Object interreLated Visual Emotion Reasoning network (SOLVER) to predict emotions from images.
Self-supervised Contrastive Attributed Graph Clustering
Thus, for the OOS nodes, SCAGC can directly calculate their clustering labels.
Infrared Small-Dim Target Detection with Transformer under Complex Backgrounds
We adopt the self-attention mechanism of the transformer to learn the interaction information of image features in a larger range.
Hybrid Dynamic Contrast and Probability Distillation for Unsupervised Person Re-Id
However, since person Re-Id is an open-set problem, the clustering based methods often leave out lots of outlier instances or group the instances into the wrong clusters, thus they can not make full use of the training samples as a whole.
Single Image Dehazing with An Independent Detail-Recovery Network
In this paper, we propose a single image dehazing method with an independent Detail Recovery Network (DRN), which considers capturing the details from the input image over a separate network and then integrates them into a coarse dehazed image.
Stimuli-Aware Visual Emotion Analysis
Then, we design three specific networks, i. e., Global-Net, Semantic-Net and Expression-Net, to extract distinct emotional features from different stimuli simultaneously.
Support-Set Based Cross-Supervision for Video Grounding
The contrastive objective aims to learn effective representations by contrastive learning, while the caption objective can train a powerful video encoder supervised by texts.
Effective and Efficient Graph Learning for Multi-view Clustering
Despite the impressive clustering performance and efficiency in characterizing both the relationship between data and cluster structure, existing graph-based multi-view clustering methods still have the following drawbacks.
Multiple Graph Learning for Scalable Multi-view Clustering
Specifically, we construct a hidden and tractable large graph by anchor graph for each view and well exploit complementary information embedded in anchor graphs of different views by tensor Schatten p-norm regularizer.
A Circular-Structured Representation for Visual Emotion Distribution Learning
Visual Emotion Analysis (VEA) has attracted increasing attention recently with the prevalence of sharing images on social networks.
Learning the Non-Differentiable Optimization for Blind Super-Resolution
Instead of considering iterative strategy, we make the blur kernel predictor trainable in the whole blind SR model, in which AMNet is well-trained.
TSGCNet: Discriminative Geometric Feature Learning With Two-Stream Graph Convolutional Network for 3D Dental Model Segmentation
State-of-the-art methods directly concatenate the raw attributes of 3D inputs, namely coordinates and normal vectors of mesh cells, to train a single-stream network for fully-automated tooth segmentation.
Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training
However, pre-processing methods may suffer from the robustness degradation effect, in which the defense reduces rather than improving the adversarial robustness of a target model in a white-box setting.
Towards Defending against Adversarial Examples via Attack-Invariant Features
However, given the continuously evolving attacks, models trained on seen types of adversarial examples generally cannot generalize well to unseen types of adversarial examples.
Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Report
Video super-resolution has recently become one of the most important mobile-related problems due to the rise of video communication and streaming services.
Removing Adversarial Noise in Class Activation Feature Space
Then, we train a denoising model to minimize the distances between the adversarial examples and the natural examples in the class activation feature space.
Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer
Inspired by the common painting process of drawing a draft and revising the details, we introduce a novel feed-forward method named Laplacian Pyramid Network (LapStyle).
Transitional Learning: Exploring the Transition States of Degradation for Blind Super-resolution
Being extremely dependent on iterative estimation of the degradation prior or optimization of the model from scratch, the existing blind super-resolution (SR) methods are generally time-consuming and less effective, as the estimation of degradation proceeds from a blind initialization and lacks interpretable degradation priors.
Syncretic Modality Collaborative Learning for Visible Infrared Person Re-Identification
Visible infrared person re-identification (VI-REID) aims to match pedestrian images between the daytime visible and nighttime infrared camera views.
ADD-Defense: Towards Defending Widespread Adversarial Examples via Perturbation-Invariant Representation
Motivated by this observation, we propose a defense framework ADD-Defense, which extracts the invariant information called \textit{perturbation-invariant representation} (PIR) to defend against widespread adversarial examples.
TSGCNet: Discriminative Geometric Feature Learning with Two-Stream GraphConvolutional Network for 3D Dental Model Segmentation
State-of-the-art methods directly concatenate the raw attributes of 3D inputs, namely coordinates and normal vectors of mesh cells, to train a single-stream network for fully-automated tooth segmentation.
D-Unet: A Dual-encoder U-Net for Image Splicing Forgery Detection and Localization
The unfixed encoder autonomously learns the image fingerprints that differentiate between the tampered and non-tampered regions, whereas the fixed encoder intentionally provides the direction information that assists the learning and detection of the network.
LRA: an accelerated rough set framework based on local redundancy of attribute for feature selection
Based on the theorem, we propose the LRA framework for accelerating rough set algorithms.
Interpretable Detail-Fidelity Attention Network for Single Image Super-Resolution
To solve them, we propose a purposeful and interpretable detail-fidelity attention network to progressively process these smoothes and details in divide-and-conquer manner, which is a novel and specific prospect of image super-resolution for the purpose on improving the detail fidelity, instead of blindly designing or employing the deep CNNs architectures for merely feature representation in local receptive fields.
Robust Person Re-Identification through Contextual Mutual Boosting
The mask recalibrates the features to amplify the valuable characteristics and diminish the noise.
AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results.
Tasks Integrated Networks: Joint Detection and Retrieval for Image Search
The traditional object retrieval task aims to learn a discriminative feature representation with intra-similarity and inter-dissimilarity, which supposes that the objects in an image are manually or automatically pre-cropped exactly.
Weakly Supervised Temporal Action Localization with Segment-Level Labels
Specifically, we devise a partial segment loss regarded as a loss sampling to learn integral action parts from labeled segments.
Weakly-supervised Temporal Action Localization
Weakly Supervised Temporal Action Localization
Collaborative Boundary-aware Context Encoding Networks for Error Map Prediction
Further, we propose a context encoding module to utilize the global predictor from the error map to enhance the feature representation and regularize the networks.
Multi-Margin based Decorrelation Learning for Heterogeneous Face Recognition
Heterogeneous face recognition (HFR) refers to matching face images acquired from different domains with wide applications in security scenarios.
NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results.
Facial Attribute Capsules for Noise Face Super Resolution
In the SR processing, we first generated a group of FACs from the input LR face, and then reconstructed the HR face from this group of FACs.
Video Face Super-Resolution with Motion-Adaptive Feedback Cell
Current state-of-the-art CNN methods usually treat the VSR problem as a large number of separate multi-frame super-resolution tasks, at which a batch of low resolution (LR) frames is utilized to generate a single high resolution (HR) frame, and running a slide window to select LR frames over the entire video would obtain a series of HR frames.
Asynchronous Tracking-by-Detection on Adaptive Time Surfaces for Event-based Object Tracking
To achieve this goal, we present an Adaptive Time-Surface with Linear Time Decay (ATSLTD) event-to-frame conversion algorithm, which asynchronously and effectively warps the spatio-temporal information of asynchronous retinal events to a sequence of ATSLTD frames with clear object contours.
Image Fine-grained Inpainting
Besides, we devise a geometrical alignment constraint item to compensate for the pixel-based distance between prediction features and ground-truth ones.
Ranked #1 on
Facial Inpainting
on FFHQ
AIM 2019 Challenge on Real-World Image Super-Resolution: Methods and Results
For training, only one set of source input images is therefore provided in the challenge.
Lightweight Image Super-Resolution with Information Multi-distillation Network
In recent years, single image super-resolution (SISR) methods using deep convolution neural network (CNN) have achieved impressive results.
Ranked #16 on
Image Super-Resolution
on Manga109 - 3x upscaling
Progressive Perception-Oriented Network for Single Image Super-Resolution
In this paper, we propose a novel perceptual image super-resolution method that progressively generates visually high-quality results by constructing a stage-wise network.
Ranked #14 on
Image Super-Resolution
on BSD100 - 4x upscaling
(SSIM metric)
Reconstructing Perceived Images from Brain Activity by Visually-guided Cognitive Representation and Adversarial Learning
In addition, we introduce a novel three-stage learning approach which enables the (cognitive) encoder to gradually distill useful knowledge from the paired (visual) encoder during the learning process.
A sparse annotation strategy based on attention-guided active learning for 3D medical image segmentation
3D image segmentation is one of the most important and ubiquitous problems in medical image processing.
An Attention-Guided Deep Regression Model for Landmark Detection in Cephalograms
We train the deep encoder-decoder for landmark detection, and combine global landmark configuration with local high-resolution feature responses.
Deep Multi-scale Discriminative Networks for Double JPEG Compression Forensics
In this area, extracting effective statistical characteristics from a JPEG image for classification remains a challenge.
Triplet-Based Deep Hashing Network for Cross-Modal Retrieval
Given the benefits of its low storage requirements and high retrieval efficiency, hashing has recently received increasing attention.
Transfer Adaptation Learning: A Decade Survey
Domain is referred to as the state of the world at a certain moment.
A Gated Peripheral-Foveal Convolutional Neural Network for Unified Image Aesthetic Prediction
The former aims to mimic the functions of peripheral vision to encode the holistic information and provide the attended regions.
Channel-wise and Spatial Feature Modulation Network for Single Image Super-Resolution
To capture more informative features and maintain long-term information for image super-resolution, we propose a channel-wise and spatial feature modulation (CSFM) network in which a sequence of feature-modulation memory (FMM) modules is cascaded with a densely connected structure to transform low-resolution features to high informative features.
Saliency deep embedding for aurora image search
In this paper, we aim to explore a new search method for images captured with circular fisheye lens, especially the aurora images.
Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval
In addition, we harness a self-supervised semantic network to discover high-level semantic information in the form of multi-label annotations.
Fast and Accurate Single Image Super-Resolution via Information Distillation Network
Recently, deep convolutional neural networks (CNNs) have been demonstrated remarkable progress on single image super-resolution.
Ranked #4 on
Image Super-Resolution
on IXI
Single Image Super-Resolution via Cascaded Multi-Scale Cross Network
To improve information flow and to capture sufficient knowledge for reconstructing the high-frequency details, we propose a cascaded multi-scale cross network (CMSC) in which a sequence of subnetworks is cascaded to infer high resolution features in a coarse-to-fine manner.
Restricting Greed in Training of Generative Adversarial Network
Generative adversarial network (GAN) has gotten wide re-search interest in the field of deep learning.
Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding
We address the problem of dense visual-semantic embedding that maps not only full sentences and whole images but also phrases within sentences and salient regions within images into a multimodal embedding space.
Random Sampling for Fast Face Sketch Synthesis
The most time-consuming or main computation complexity for exemplar-based face sketch synthesis methods lies in the neighbor selection process.
Sparse Graphical Representation based Discriminant Analysis for Heterogeneous Face Recognition
An adaptive sparse graphical representation scheme is designed to represent heterogeneous face images, where a Markov networks model is constructed to generate adaptive sparse vectors.
Ordinal Regression With Multiple Output CNN for Age Estimation
To address the non-stationary property of aging patterns, age estimation can be cast as an ordinal regression problem.
Training-Free Synthesized Face Sketch Recognition Using Image Quality Assessment Metrics
In this paper, we proposed a synthesized face sketch recognition framework based on full-reference image quality assessment metrics.
Graphical Representation for Heterogeneous Face Recognition
Heterogeneous face recognition (HFR) refers to matching face images acquired from different sources (i. e., different sensors or different wavelengths) for identification.
Facial Feature Point Detection: A Comprehensive Survey
CLM-based methods consist of a shape model and a number of local experts, each of which is utilized to detect a facial feature point.
Semi-supervised Relational Topic Model for Weakly Annotated Image Recognition in Social Media
In such way, we can efficiently leverage the loosely related tags, and build an intermediate level representation for a collection of weakly annotated images.
Learning to Rank for Blind Image Quality Assessment
The proposed BIQA method is one of learning to rank.
