Wen Gao
YOU?
Author Swipe
View article: Multimorbidity management and systemic reform: constructing a Chinese paradigm of geriatrics — An interview with Professor Cuntai Zhang, Chairman of the Geriatrics Branch of the Chinese Medical Association
Multimorbidity management and systemic reform: constructing a Chinese paradigm of geriatrics — An interview with Professor Cuntai Zhang, Chairman of the Geriatrics Branch of the Chinese Medical Association Open
View article: SoftSignSGD(S3): An Enhanced Optimizer for Practical DNN Training and Loss Spikes Minimization Beyond Adam
SoftSignSGD(S3): An Enhanced Optimizer for Practical DNN Training and Loss Spikes Minimization Beyond Adam Open
Adam has proven remarkable successful in training deep neural networks, but the mechanisms underlying its empirical successes and limitations remain underexplored. In this study, we demonstrate that the effectiveness of Adam stems largely …
View article: TinySplat: Feedforward Approach for Generating Compact 3D Scene Representation
TinySplat: Feedforward Approach for Generating Compact 3D Scene Representation Open
The recent development of feedforward 3D Gaussian Splatting (3DGS) presents a new paradigm to reconstruct 3D scenes. Using neural networks trained on large-scale multi-view datasets, it can directly infer 3DGS representations from sparse i…
View article: Lightweighting of kiwifruit root soil water content inversion model based on novel vegetation indices
Lightweighting of kiwifruit root soil water content inversion model based on novel vegetation indices Open
View article: CALLIC: Content Adaptive Learning for Lossless Image Compression
CALLIC: Content Adaptive Learning for Lossless Image Compression Open
Learned lossless image compression has achieved significant advancements in recent years. However, existing methods often rely on training amortized generative models on massive datasets, resulting in sub-optimal probability distribution e…
View article: A Joint Visual Compression and Perception Framework for Neuralmorphic Spiking Camera
A Joint Visual Compression and Perception Framework for Neuralmorphic Spiking Camera Open
The advent of neuralmorphic spike cameras has garnered significant attention for their ability to capture continuous motion with unparalleled temporal resolution.However, this imaging attribute necessitates considerable resources for binar…
View article: Predicting Satisfied User and Machine Ratio for Compressed Images: A Unified Approach
Predicting Satisfied User and Machine Ratio for Compressed Images: A Unified Approach Open
Nowadays, high-quality images are pursued by both humans for better viewing experience and by machines for more accurate visual analysis. However, images are usually compressed before being consumed, decreasing their quality. It is meaning…
View article: CALLIC: Content Adaptive Learning for Lossless Image Compression
CALLIC: Content Adaptive Learning for Lossless Image Compression Open
Learned lossless image compression has achieved significant advancements in recent years. However, existing methods often rely on training amortized generative models on massive datasets, resulting in sub-optimal probability distribution e…
View article: MGMNet: Mutual-Guidance Mechanism for Joint Classification of Multisource Remote Sensing Data
MGMNet: Mutual-Guidance Mechanism for Joint Classification of Multisource Remote Sensing Data Open
The joint classification of multisource remote sensing data has shown significant potential in the precise interpretation of land cover. Existing methods mainly employ a dual-stream architecture to independently extract features, subsequen…
View article: Rethinking Bjøntegaard Delta for Compression Efficiency Evaluation: Are We Calculating It Precisely and Reliably?
Rethinking Bjøntegaard Delta for Compression Efficiency Evaluation: Are We Calculating It Precisely and Reliably? Open
For decades, the Bjøntegaard Delta (BD) has been the metric for evaluating codec Rate-Distortion (R-D) performance. Yet, in most studies, BD is determined using just 4-5 R-D data points, could this be sufficient? As codecs and quality metr…
View article: MADE: Multicurvature Adaptive Embedding for Temporal Knowledge Graph Completion
MADE: Multicurvature Adaptive Embedding for Temporal Knowledge Graph Completion Open
Temporal knowledge graphs (TKGs) are receiving increased attention due to their time-dependent properties and the evolving nature of knowledge over time. TKGs typically contain complex geometric structures, such as hierarchical, ring, and …
View article: GroupedMixer: An Entropy Model With Group-Wise Token-Mixers for Learned Image Compression
GroupedMixer: An Entropy Model With Group-Wise Token-Mixers for Learned Image Compression Open
Transformer-based entropy models have gained prominence in recent years due\nto their superior ability to capture long-range dependencies in probability\ndistribution estimation compared to convolution-based methods. However,\nprevious tra…
View article: An Improved Coppersmith Algorithm Based on Block Preprocessing
An Improved Coppersmith Algorithm Based on Block Preprocessing Open
Since Coppersmith proposed the use of the LLL algorithm to solve univariate modular polynomial equations at EUROCRYPT’96, it has sparked a fervent research interest in lattice analysis among cryptographers. Despite its polynomial-time natu…
View article: Understanding the Wettability and Solubility Properties of Ticx-Steel Systems
Understanding the Wettability and Solubility Properties of Ticx-Steel Systems Open
View article: Peptide generative design with weakly order-dependent autoregressive language model and lifelong learning
Peptide generative design with weakly order-dependent autoregressive language model and lifelong learning Open
Bioactive peptides have become strong candidates for a variety of clinical therapies due to their diverse advantages, which promotes the development of deep generative models for peptide design. Considering that existing methods cannot eff…
View article: Faster Person Re-Identification: One-Shot-Filter and Coarse-to-Fine Search
Faster Person Re-Identification: One-Shot-Filter and Coarse-to-Fine Search Open
Fast person re-identification (ReID) aims to search person images quickly and accurately. The main idea of recent fast ReID methods is the hashing algorithm, which learns compact binary codes and performs fast Hamming distance and counting…
View article: E2VD: a unified evolution-driven framework for virus variation drivers prediction
E2VD: a unified evolution-driven framework for virus variation drivers prediction Open
The increasing frequency of emerging viral infections necessitates a rapid human response, highlighting the cost-effectiveness of computational methods. However, existing computational approaches are limited by their input forms or incompl…
View article: Lightweight super resolution network for point cloud geometry compression
Lightweight super resolution network for point cloud geometry compression Open
This paper presents an approach for compressing point cloud geometry by leveraging a lightweight super-resolution network. The proposed method involves decomposing a point cloud into a base point cloud and the interpolation patterns for re…
View article: MPAI-EEV: Standardization Efforts of Artificial Intelligence based End-to-End Video Coding
MPAI-EEV: Standardization Efforts of Artificial Intelligence based End-to-End Video Coding Open
The rapid advancement of artificial intelligence (AI) technology has led to the prioritization of standardizing the processing, coding, and transmission of video using neural networks. To address this priority area, the Moving Picture, Aud…
View article: A Survey on Temporal Knowledge Graph Completion: Taxonomy, Progress, and Prospects
A Survey on Temporal Knowledge Graph Completion: Taxonomy, Progress, and Prospects Open
Temporal characteristics are prominently evident in a substantial volume of knowledge, which underscores the pivotal role of Temporal Knowledge Graphs (TKGs) in both academia and industry. However, TKGs often suffer from incompleteness for…
View article: Large-scale Multi-modal Pre-trained Models: A Comprehensive Survey
Large-scale Multi-modal Pre-trained Models: A Comprehensive Survey Open
With the urgent demand for generalized deep models, many pre-trained big models are proposed, such as bidirectional encoder representations (BERT), vision transformer (ViT), generative pre-trained transformers (GPT), etc. Inspired by the s…
View article: Multiscale Attention Fusion for Depth Map Super-Resolution Generative Adversarial Networks
Multiscale Attention Fusion for Depth Map Super-Resolution Generative Adversarial Networks Open
Color images have long been used as an important supplementary information to guide the super-resolution of depth maps. However, how to quantitatively measure the guiding effect of color images on depth maps has always been a neglected iss…
View article: Optimum sampling window size and vegetation index selection for low-altitude multispectral estimation of root soil moisture content for Xuxiang Kiwifruit
Optimum sampling window size and vegetation index selection for low-altitude multispectral estimation of root soil moisture content for Xuxiang Kiwifruit Open
Early detection of water stress is essential for orchard management; however, existing methods are unable to accurately monitor individual plant water status over large areas, and the shaded nature of kiwifruit orchards further complicates…
View article: Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation Open
In this paper, a novel Diffusion-based 3D Pose estimation (D3DP) method with Joint-wise reProjection-based Multi-hypothesis Aggregation (JPMA) is proposed for probabilistic 3D human pose estimation. On the one hand, D3DP generates multiple…
View article: Keynote Speaker: Immersive Video Reality—Technology, Standard and Application
Keynote Speaker: Immersive Video Reality—Technology, Standard and Application Open
Due to recent advances and convergence of image processing, broadbandnetwork, XR displaying device, and deep learning, immersivevideo reality has become a topic of great interest in recent years.Compared with traditional 2D video display, …
View article: General Chairs Message
General Chairs Message Open
It is our great pleasure to welcome you to the 30th IEEE Conference on Virtual Reality and 3D User Interfaces (IEEE VR), the premier international conference focused on research in the continuous spectrum of extended reality, including vir…
View article: Experimental Exploration of Multi-dimensional Remote Sensing Technology Applied to Target Aviation Search and Rescue
Experimental Exploration of Multi-dimensional Remote Sensing Technology Applied to Target Aviation Search and Rescue Open
Optical sensing system is developing from the original intensity image/video sensing mode to multi-dimensional sensing mode, and people pay more and more attention to the spectral characteristics and polarization characteristics of the tar…
View article: Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey
Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey Open
With the urgent demand for generalized deep models, many pre-trained big models are proposed, such as BERT, ViT, GPT, etc. Inspired by the success of these models in single domains (like computer vision and natural language processing), th…
View article: Learning to Compress Unmanned Aerial Vehicle (UAV) Captured Video: Benchmark and Analysis
Learning to Compress Unmanned Aerial Vehicle (UAV) Captured Video: Benchmark and Analysis Open
During the past decade, the Unmanned-Aerial-Vehicles (UAVs) have attracted increasing attention due to their flexible, extensive, and dynamic space-sensing capabilities. The volume of video captured by UAVs is exponentially growing along w…
View article: Symptomatic and Asymptomatic SARS-CoV-2 Infection and Follow-up of Neutralizing Antibody Levels.
Symptomatic and Asymptomatic SARS-CoV-2 Infection and Follow-up of Neutralizing Antibody Levels. Open