Wenming Yang
YOU?
Author Swipe
View article: DARL: Mitigating Gradient Conflicts in Long-Tailed Out-of-Distribution Learning
DARL: Mitigating Gradient Conflicts in Long-Tailed Out-of-Distribution Learning Open
View article: Towards expert-level autonomous carotid ultrasonography with large-scale learning-based robotic system
Towards expert-level autonomous carotid ultrasonography with large-scale learning-based robotic system Open
View article: Continuous particle method for granular particle flow simulation and its extended application
Continuous particle method for granular particle flow simulation and its extended application Open
This study introduces an application of a continuous particle method, which is the smoothed particle hydrodynamics (SPH) method, in the field of computational geotechnical engineering, enhancing the simulation of granular particle dynamics…
View article: UP-Person: Unified Parameter-Efficient Transfer Learning for Text-based Person Retrieval
UP-Person: Unified Parameter-Efficient Transfer Learning for Text-based Person Retrieval Open
Text-based Person Retrieval (TPR) as a multi-modal task, which aims to retrieve the target person from a pool of candidate images given a text description, has recently garnered considerable attention due to the progress of contrastive vis…
View article: GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution
GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution Open
Implicit neural representations (INRs) have revolutionized arbitrary-scale super-resolution (ASSR) by modeling images as continuous functions. Most existing INR-based ASSR networks first extract features from the given low-resolution image…
View article: DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval
DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval Open
Text-based person retrieval (TPR) has gained significant attention as a fine-grained and challenging task that closely aligns with practical applications. Tailoring CLIP to person domain is now a emerging research topic due to the abundant…
View article: Decoupling Appearance Variations with 3D Consistent Features in Gaussian Splatting
Decoupling Appearance Variations with 3D Consistent Features in Gaussian Splatting Open
Gaussian Splatting has emerged as a prominent 3D representation in novel view synthesis, but it still suffers from appearance variations, which are caused by various factors, such as modern camera ISPs, different time of day, weather condi…
View article: Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network
Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network Open
Current state-of-the-art (SOTA) methods in 3D Human Pose Estimation (HPE) are primarily based on Transformers. However, existing Transformer-based 3D HPE backbones often encounter a trade-off between accuracy and computational efficiency. …
View article: SOVGaussian: Sparse-View 3D Gaussian Splatting for Open-Vocabulary Scene Understanding
SOVGaussian: Sparse-View 3D Gaussian Splatting for Open-Vocabulary Scene Understanding Open
Modeling 3D open-vocabulary language fields is challenging yet highly anticipated. Despite great progress, existing approaches heavily rely on a large number of training views to construct language-embedded 3D scenes, which is unfortunatel…
View article: DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval
DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval Open
Text-based person retrieval (TPR) has gained significant attention as a fine-grained and challenging task that closely aligns with practical applications. Tailoring CLIP to person domain is now a emerging research topic due to the abundant…
View article: GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning
GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning Open
Recent great advances in video generation models have demonstrated their potential to produce high-quality videos, bringing challenges to effective evaluation. Unlike human evaluation, existing automated evaluation metrics lack high-level …
View article: High-speed centrifugation reduces immune rejection by removing bone marrow elements from fresh osteochondral allografts
High-speed centrifugation reduces immune rejection by removing bone marrow elements from fresh osteochondral allografts Open
Our study demonstrated that HSC is a simple, efficient, and safe physical method for removing antigenic components from OCAs, effectively reducing immune rejection and highlighting its clinical potential.
View article: Decoupling Appearance Variations with 3D Consistent Features in Gaussian Splatting
Decoupling Appearance Variations with 3D Consistent Features in Gaussian Splatting Open
Gaussian Splatting has emerged as a prominent 3D representation in novel view synthesis, but it still suffers from appearance variations, which are caused by various factors, such as modern camera ISPs, different time of day, weather condi…
View article: DiffStereo: High-Frequency Aware Diffusion Model for Stereo Image Restoration
DiffStereo: High-Frequency Aware Diffusion Model for Stereo Image Restoration Open
Diffusion models (DMs) have achieved promising performance in image restoration but haven't been explored for stereo images. The application of DM in stereo image restoration is confronted with a series of challenges. The need to reconstru…
View article: CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs
CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs Open
Large Vision-Language Model (LVLM) systems have demonstrated impressive vision-language reasoning capabilities but suffer from pervasive and severe hallucination issues, posing significant risks in critical domains such as healthcare and a…
View article: Geometry-Guided Diffusion Model with Masked Transformer for Robust Multi-View 3D Human Pose Estimation
Geometry-Guided Diffusion Model with Masked Transformer for Robust Multi-View 3D Human Pose Estimation Open
View article: MiniFed : Integrating LLM-based Agentic-Workflow for Simulating FOMC Meeting
MiniFed : Integrating LLM-based Agentic-Workflow for Simulating FOMC Meeting Open
The Federal Funds rate in the United States plays a significant role in both domestic and international financial markets. However, research has predominantly focused on the effects of adjustments to the Federal Funds rate rather than on t…
View article: CONSULT: Contrastive Self-Supervised Learning for Few-shot Tumor Detection
CONSULT: Contrastive Self-Supervised Learning for Few-shot Tumor Detection Open
Artificial intelligence aids in brain tumor detection via MRI scans, enhancing the accuracy and reducing the workload of medical professionals. However, in scenarios with extremely limited medical images, traditional deep learning approach…
View article: RICASSO: Reinforced Imbalance Learning with Class-Aware Self-Supervised Outliers Exposure
RICASSO: Reinforced Imbalance Learning with Class-Aware Self-Supervised Outliers Exposure Open
In real-world scenarios, deep learning models often face challenges from both imbalanced (long-tailed) and out-of-distribution (OOD) data. However, existing joint methods rely on real OOD data, which leads to unnecessary trade-offs. In con…
View article: Iterative Removal of G-PCC Attribute Compression Artifacts Based on a Graph Neural Network
Iterative Removal of G-PCC Attribute Compression Artifacts Based on a Graph Neural Network Open
As a compression standard, Geometry-based Point Cloud Compression (G-PCC) can effectively reduce data by compressing both geometric and attribute information. Even so, due to coding errors and data loss, point clouds (PCs) still face disto…
View article: Development of an image binarization software tool for net occlusion estimations
Development of an image binarization software tool for net occlusion estimations Open
View article: Alignment is All You Need: A Training-free Augmentation Strategy for Pose-guided Video Generation
Alignment is All You Need: A Training-free Augmentation Strategy for Pose-guided Video Generation Open
Character animation is a transformative field in computer graphics and vision, enabling dynamic and realistic video animations from static images. Despite advancements, maintaining appearance consistency in animations remains a challenge. …
View article: FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistant
FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistant Open
The rapid advancement of deepfake technologies has sparked widespread public concern, particularly as face forgery poses a serious threat to public information security. However, the unknown and diverse forgery techniques, varied facial fe…
View article: Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network
Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network Open
Current state-of-the-art (SOTA) methods in 3D Human Pose Estimation (HPE) are primarily based on Transformers. However, existing Transformer-based 3D HPE backbones often encounter a trade-off between accuracy and computational efficiency. …
View article: GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution
GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution Open
Implicit neural representations (INRs) have significantly advanced the field of arbitrary-scale super-resolution (ASSR) of images. Most existing INR-based ASSR networks first extract features from the given low-resolution image using an en…
View article: DRRN: Differential rectification & refinement network for ischemic infarct segmentation
DRRN: Differential rectification & refinement network for ischemic infarct segmentation Open
Accurate segmentation of infarct tissue in ischemic stroke is essential to determine the extent of injury and assess the risk and choose optimal treatment for this life‐threatening disease. With the prior knowledge that asymmetric analysis…
View article: Perspective+ Unet: Enhancing Segmentation with Bi-Path Fusion and Efficient Non-Local Attention for Superior Receptive Fields
Perspective+ Unet: Enhancing Segmentation with Bi-Path Fusion and Efficient Non-Local Attention for Superior Receptive Fields Open
Precise segmentation of medical images is fundamental for extracting critical clinical information, which plays a pivotal role in enhancing the accuracy of diagnoses, formulating effective treatment plans, and improving patient outcomes. A…
View article: Integrated proteomics and metabolomics analysis of sclerosis-related proteins and femoral head necrosis following internal fixation of femoral neck fractures
Integrated proteomics and metabolomics analysis of sclerosis-related proteins and femoral head necrosis following internal fixation of femoral neck fractures Open
Femoral head necrosis (FHN) is a serious complication after femoral neck fractures (FNF), often linked to sclerosis around screw paths. Our study aimed to uncover the proteomic and metabolomic underpinnings of FHN and sclerosis using integ…
View article: BDC-Occ: Binarized Deep Convolution Unit For Binarized Occupancy Network
BDC-Occ: Binarized Deep Convolution Unit For Binarized Occupancy Network Open
Existing 3D occupancy networks demand significant hardware resources, hindering the deployment of edge devices. Binarized Neural Networks (BNN) offer substantially reduced computational and memory requirements. However, their performance d…
View article: Bilateral Event Mining and Complementary for Event Stream Super-Resolution
Bilateral Event Mining and Complementary for Event Stream Super-Resolution Open
Event Stream Super-Resolution (ESR) aims to address the challenge of insufficient spatial resolution in event streams, which holds great significance for the application of event cameras in complex scenarios. Previous works for ESR often p…