Yuming Fang
YOU?
Author Swipe
View article: Make Identity Unextractable yet Perceptible: Synthesis-Based Privacy Protection for Subject Faces in Photos
Make Identity Unextractable yet Perceptible: Synthesis-Based Privacy Protection for Subject Faces in Photos Open
Deep learning-based face recognition (FR) technology exacerbates privacy concerns in photo sharing. In response, the research community developed a suite of anti-FR methods to block identity extraction by unauthorized FR systems. Benefitin…
View article: Construction and validation of a perioperative blood transfusion model for patients undergoing total hip arthroplasty with osteonecrosis of the femoral head based on machine learning
Construction and validation of a perioperative blood transfusion model for patients undergoing total hip arthroplasty with osteonecrosis of the femoral head based on machine learning Open
Background This study aimed to construct a predictive model utilizing multiple machine learning (ML) models to estimate the likelihood of perioperative blood transfusion in patients with osteonecrosis of the femoral head (ONFH) who underwe…
View article: Spinal cord injury-derived exosomes exacerbate damage: miR-155-5p mediates inflammatory responses
Spinal cord injury-derived exosomes exacerbate damage: miR-155-5p mediates inflammatory responses Open
Spinal cord injury (SCI) is a critical event characterized by intricate pathogenic mechanisms. Although recent studies have highlighted tissue exosomes as key mediators of inflammatory responses in diverse organs and tissues, their role in…
View article: PSReg: Prior-guided Sparse Mixture of Experts for Point Cloud Registration
PSReg: Prior-guided Sparse Mixture of Experts for Point Cloud Registration Open
The discriminative feature is crucial for point cloud registration. Recent methods improve the feature discriminative by distinguishing between non-overlapping and overlapping region points. However, they still face challenges in distingui…
View article: Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation
Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation Open
Category-agnostic pose estimation aims to locate keypoints on query images according to a few annotated support images for arbitrary novel classes. Existing methods generally extract support features via heatmap pooling, and obtain interac…
View article: Computational Analysis of Degradation Modeling in Blind Panoramic Image Quality Assessment
Computational Analysis of Degradation Modeling in Blind Panoramic Image Quality Assessment Open
Blind panoramic image quality assessment (BPIQA) has recently brought a new challenge to the visual quality community, due to the complex interaction between immersive content and human behavior. Although many efforts have been made to adv…
View article: Microglia-derived CXCL2 induced neuronal ferroptosis via CXCR2/Jun axis in sepsis-associated encephalopathy
Microglia-derived CXCL2 induced neuronal ferroptosis via CXCR2/Jun axis in sepsis-associated encephalopathy Open
Background Neuronal ferroptosis is a characteristic pathological change of sepsis-associated encephalopathy (SAE), which can be induced by activated microglia. CXCL2 is mainly secreted by inflammatory cells (neutrophil and microglia) and i…
View article: Computational Analysis of Degradation Modeling in Blind Panoramic Image Quality Assessment
Computational Analysis of Degradation Modeling in Blind Panoramic Image Quality Assessment Open
Blind panoramic image quality assessment (BPIQA) has recently brought new challenge to the visual quality community, due to the complex interaction between immersive content and human behavior. Although many efforts have been made to advan…
View article: Max360IQ: Blind Omnidirectional Image Quality Assessment with Multi-axis Attention
Max360IQ: Blind Omnidirectional Image Quality Assessment with Multi-axis Attention Open
Omnidirectional image, also called 360-degree image, is able to capture the entire 360-degree scene, thereby providing more realistic immersive feelings for users than general 2D image and stereoscopic image. Meanwhile, this feature brings…
View article: Detecting Malicious Concepts Without Image Generation in AIGC
Detecting Malicious Concepts Without Image Generation in AIGC Open
The task of text-to-image generation has achieved tremendous success in practice, with emerging concept generation models capable of producing highly personalized and customized content. Fervor for concept generation is increasing rapidly …
View article: Subjective and Objective Quality Assessment of Non-Uniformly Distorted Omnidirectional Images
Subjective and Objective Quality Assessment of Non-Uniformly Distorted Omnidirectional Images Open
Omnidirectional image quality assessment (OIQA) has been one of the hot topics in IQA with the continuous development of VR techniques, and achieved much success in the past few years. However, most studies devote themselves to the uniform…
View article: Multitask Auxiliary Network for Perceptual Quality Assessment of Non-Uniformly Distorted Omnidirectional Images
Multitask Auxiliary Network for Perceptual Quality Assessment of Non-Uniformly Distorted Omnidirectional Images Open
Omnidirectional image quality assessment (OIQA) has been widely investigated in the past few years and achieved much success. However, most of existing studies are dedicated to solve the uniform distortion problem in OIQA, which has a natu…
View article: PSReg: Prior-guided Sparse Mixture of Experts for Point Cloud Registration
PSReg: Prior-guided Sparse Mixture of Experts for Point Cloud Registration Open
The discriminative feature is crucial for point cloud registration. Recent methods improve the feature discriminative by distinguishing between non-overlapping and overlapping region points. However, they still face challenges in distingui…
View article: Video Quality Assessment for Online Processing: From Spatial to Temporal Sampling
Video Quality Assessment for Online Processing: From Spatial to Temporal Sampling Open
With the rapid development of multimedia processing and deep learning technologies, especially in the field of video understanding, video quality assessment (VQA) has achieved significant progress. Although researchers have moved from desi…
View article: Texture‐Aware Network for Enhancing Inner Smoke Representation in Visual Smoke Density Estimation
Texture‐Aware Network for Enhancing Inner Smoke Representation in Visual Smoke Density Estimation Open
Smoke often appears before visible flames in the early stages of fire disasters, making accurate pixel‐wise detection essential for fire alarms. Although existing segmentation models effectively identify smoke pixels, they generally treat …
View article: Image Privacy Protection: A Survey
Image Privacy Protection: A Survey Open
Images serve as a crucial medium for communication, presenting information in a visually engaging format that facilitates rapid comprehension of key points. Meanwhile, during transmission and storage, they contain significant sensitive inf…
View article: Improving Image Aesthetic Assessment via Multiple Image Joint Learning
Improving Image Aesthetic Assessment via Multiple Image Joint Learning Open
Image Aesthetic Assessment (IAA) is an emerging paradigm that predicts aesthetic score as the popular aesthetic taste for an image. Previous IAA approaches take a single image as input to predict the aesthetic score of the image. However, …
View article: Multiscale Sliced Wasserstein Distances as Perceptual Color Difference Measures
Multiscale Sliced Wasserstein Distances as Perceptual Color Difference Measures Open
Contemporary color difference (CD) measures for photographic images typically operate by comparing co-located pixels, patches in a ``perceptually uniform'' color space, or features in a learned latent space. Consequently, these measures in…
View article: Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors
Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors Open
Arbitrary-scale video super-resolution (AVSR) aims to enhance the resolution of video frames, potentially at various scaling factors, which presents several challenges regarding spatial detail reproduction, temporal consistency, and comput…
View article: Trustworthy AIGC Copyright Management with Full Lifecycle Recording and Multi-party Supervision in Blockchain
Trustworthy AIGC Copyright Management with Full Lifecycle Recording and Multi-party Supervision in Blockchain Open
As artificial intelligence technology becomes increasingly widespread, AI-generated content (AIGC) is gradually penetrating into many fields. Although AIGC plays an increasingly prominent role in business and cultural communication, the is…
View article: Enhancing Incomplete Multi-modal Brain Tumor Segmentation with Intra-modal Asymmetry and Inter-modal Dependency
Enhancing Incomplete Multi-modal Brain Tumor Segmentation with Intra-modal Asymmetry and Inter-modal Dependency Open
Deep learning-based brain tumor segmentation (BTS) models for multi-modal MRI images have seen significant advancements in recent years. However, a common problem in practice is the unavailability of some modalities due to varying scanning…
View article: Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare
Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare Open
While recent advancements in large multimodal models (LMMs) have significantly improved their abilities in image quality assessment (IQA) relying on absolute quality rating, how to transfer reliable relative quality comparison outputs to c…
View article: Benchmarking deep models on retinal fundus disease diagnosis and a large-scale dataset
Benchmarking deep models on retinal fundus disease diagnosis and a large-scale dataset Open
Retinal fundus imaging contributes to monitoring the vision of patients by providing views of the interior surface of the eyes. Machine learning models greatly aided ophthalmologists in detecting retinal disorders from color fundus images.…
View article: Comprehensive Visual Grounding for Video Description
Comprehensive Visual Grounding for Video Description Open
The grounding accuracy of existing video captioners is still behind the expectation. The majority of existing methods perform grounded video captioning on sparse entity annotations, whereas the captioning accuracy often suffers from degene…
View article: Meta-Point Learning and Refining for Category-Agnostic Pose Estimation
Meta-Point Learning and Refining for Category-Agnostic Pose Estimation Open
Category-agnostic pose estimation (CAPE) aims to predict keypoints for arbitrary classes given a few support images annotated with keypoints. Existing methods only rely on the features extracted at support keypoints to predict or refine th…
View article: Perceptual Quality Assessment of Virtual Reality Videos in the Wild
Perceptual Quality Assessment of Virtual Reality Videos in the Wild Open
Investigating how people perceive virtual reality (VR) videos in the wild ( i.e ., those captured by everyday users) is a crucial and challenging task in VR-related applications due to complex authentic distortionslocalizedinspaceandtime.E…
View article: 2AFC Prompting of Large Multimodal Models for Image Quality Assessment
2AFC Prompting of Large Multimodal Models for Image Quality Assessment Open
While abundant research has been conducted on improving high-level visual understanding and reasoning capabilities of large multimodal models~(LMMs), their visual quality assessment~(IQA) ability has been relatively under-explored. Here we…
View article: Natural Product Quercetin-3-methyl ether Promotes Colorectal Cancer Cell Apoptosis by Downregulating Intracellular Polyamine Signaling
Natural Product Quercetin-3-methyl ether Promotes Colorectal Cancer Cell Apoptosis by Downregulating Intracellular Polyamine Signaling Open
Dysregulation of cellular metabolism is a key marker of cancer, and it is suggested that metabolism should be considered as a targeted weakness of colorectal cancer. Increased polyamine metabolism is a common metabolic change in tumors. Th…