- Spatial-Spectral Texture-Preserved Total Variation: A Novel Regularization for Hyperspectral Image Denoising
- Shadow Generation Using Diffusion Model with Geometry Prior
- Where’s the liability in the Generative Era? Recovery-based Black-Box Detection of AI-Generated Content
- AMSnet 2.0: A Large AMS Database with AI Segmentation for Net Detection
- BIP3D: Bridging 2D Images and 3D Perception for Embodied Intelligence
- Towards Consistent Multi-Task Learning: Unlocking the Potential of Task-Specific Parameters
- Implementation of Network Traffic Anomaly Detection Based on Autoencoder
- Design and simulation analysis of ship automatic anti-interference heading controller
- PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization
- VIRES: Video Instance Repainting via Sketch and Text Guided Generation
- PICD: Versatile Perceptual Image Compression with Diffusion Rendering
- Abnormal Flow Monitoring Method of Power Grid Equipment Based on Isolation Forest Technology
- Comparative Study of Planar Ag/AgCl Quasi-Reference Electrodes Developed on PCB
- Multitwine: Multi-Object Compositing with Text and Layout Control
- Modeling Thousands of Human Annotators for Generalizable Text-to-Image Person Re-identification
- Towards community-based influence spread prediction (CIP) for edge changes in large-scale dynamic social networks
- JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration
- Animate and Sound an Image
- Emotion Recognition Using Affective Touch: A Survey
- Annotation Ambiguity Aware Semi-Supervised Medical Image Segmentation
- Universal Scene Graph Generation
- Simulation Framework for Assessing VWC Performance in Low-Cost Smart Agriculture Sensors
- Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models
- Single Receiver Positioning Method Based on TDOA/AOA
- MADDPG-Based Collaborative Anti-Jamming Strategy for Joint Frequency-Power Allocation in Networked Radars
- RANGE: Retrieval Augmented Neural Fields for Multi-Resolution Geo-Embeddings
- GenAssets: Generating in-the-wild 3D Assets in Latent Space
- VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?
- Thalassa: Transforming Symbolic PDEs into Tensor-Based Solvers Running on ML Accelerators
- FDTD-Based Electric-Field Analysis of a Small-Scale Airplane Model Under a Thundercloud
- GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimation
- Revisiting and Extending the Estimation of Parasitic Capacitance in Inductors
- Removing Reflections from RAW Photos
- HiFi-Portrait: Zero-shot Identity-preserved Portrait Generation with High-fidelity Multi-face Fusion
- Frequency-Biased Synergistic Design for Image Compression and Compensation
- HybridMQA: Exploring Geometry-Texture Interactions for Colored Mesh Quality Assessment
- Multi-scale Semantically Modulated Mixed Convolutional Networks for Sub-pixel Mapping
- A Tale of Two Classes: Adapting Supervised Contrastive Learning to Binary Imbalanced Datasets
- Classifier-guided CLIP Distillation for Unsupervised Multi-label Classification
- Toward Efficient Asynchronous Single-Source Shortest Path
- Coupling Study in a 2D Gimbal-less Quasi-static Piezoelectrically-Actuated MEMS Mirror
- Steady Progress Beats Stagnation: Mutual Aid of Foundation and Conventional Models in Mixed Domain Semi-Supervised Medical Image Segmentation
- Linear Attention Modeling for Learned Image Compression
- Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level
- CoMBO: Conflict Mitigation via Branched Optimization for Class Incremental Segmentation
- RFSFeat: Advanced Feature Extraction and Recognition for Zhuang Brocade
- Condensing Action Segmentation Datasets via Generative Network Inversion
- ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models
- Toward Performance Prediction in Large-Scale Systems through Temporal System and Application Log Analysis
- Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized?
- A Universal Quantum Phase Slip Logic Gate for Implementing Basic Boolean Functions
- ViiNeuS: Volumetric Initialization for Implicit Neural Surface reconstruction of urban scenes with limited image overlap
- MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities
- VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models
- Smart Metering for Real-Time Power Prediction Price Forecasting and Intelligent Alerts in Modern Living Spaces
- Hybrid CNN-BiLSTM for ISI Mitigation in Molecular Communication for Nanosensors with Imperfect Transmitter
- Probabilistic Generative Approach for Ambiguity-Aware Parameter Extraction
- MambaVO: Deep Visual Odometry Based on Sequential Matching Refinement and Training Smoothing
- PARC: A Quantitative Framework Uncovering the Symmetries within Vision Language Models
- SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removal
- Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs
- All-in-One Single Image Restoration Based on Multi-Scale Hybrid Mamba-Transformer
- Deep Learning-Driven Vulnerability Detection Models for Software Security
- The Method of Library User Profiling and Knowledge Demand Prediction Driven by Big Data
- Adapting Pre-trained 3D Models for Point Cloud Video Understanding via Cross-frame Spatio-temporal Perception
- Can Vision Feel Touch? Tactile-aware Visual Grasping for Transparent Objects
- EgoLife: Towards Egocentric Life Assistant
- Improving Ethereum Mixing Address Linking with Tensor Computation, Neighbor Data Utilization and Asymmetric Information Modeling
- Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models
- Application of Bayesian Price Clearing Auction Model in Enhancing Transactive Energy Systems Vulnerabilities to Cyber Attacks
- Style Evolving along Chain-of-Thought for Unknown-Domain Object Detection
- Ecs: Fresh Air Duct Leakage Detection Model for Embedded Development Environment
- OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation
- HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding
- Encapsulated Composition of Text-to-Image and Text-to-Video Models for High-Quality Video Synthesis
- Harvesting Energy from Subclavian Artery Motion for Self-Powered Implantable Medical Devices
- A Novel Kernel-Based Hilbert Space Framework for Predictive Modeling of lncRNA-miRNA-Disease Interaction Networks
- Optimal Split Capacitor DC-Link Design for Partial Load Multi-Level Inverters
- Enhancing SRAM Efficiency and Stability with Self Pull Up Mechanism and Bitline Charge Sharing
- Strain-Regulated Polarity Switching in Flexible MoTe 2 Transistors
- Method and Implementation of Batch Renaming for Structure Trees Based on CATIA V6 Secondary Development
- An Example of Autism Co-Design: Physiological Sensor-driven Ecological Momentary Assessment Application
- Method for the Operational Weather Window Assessment of Self-Elevating Wind Turbine Installation Vessels
- Font-Agent: Enhancing Font Understanding with Large Language Models
- MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders
- Construction of an Ethical Monitoring System for Public Space Design Based on Quantitative Models
- Experimental Characterization of High-frequency Transformers for Isolated DC-DC Converters
- UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image
- Shape and Texture: What Influences Reliable Optical Flow Estimation?
- HUSH: Holistic Panoramic 3D Scene Understanding using Spherical Harmonics
- Template-Adaptive Content Organization: AI-Driven Personalization for E-Commerce Email Marketing
- Event-Based Adaptive Fault-Tolerant Control for Nonlinear Cyber-Physical Systems via Intermittent Available Signals
- A Novel Three Port Multi-Input Single Inductor DC-DC Bidirectional Boost Converter
- Advancing Manga Analysis: Comprehensive Segmentation Annotations for the Manga109 Dataset
- Active Non-Line-Of-Sight Imaging Based on Fusion of Physical Prior and Deep Learning
- Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens
- A Modulation Scheme for Enhanced Performance of Hybrid Source Inverters in Electric Vehicles Application
- Highly Integrated Communication System for Commercial SAR Satellites Based on On-Board Computers
- Ultra-Efficient Three-Phase Integrated-Active-Filter Isolated Rectifier for AI Data Center Applications
- PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting