- Open-World Objectness Modeling Unifies Novel Object Detection
- AI-Driven Optimization of Passenger Flow: Integrating Computer Vision, Machine Learning, and Simulation for Enhanced Efficiency and Revenue Generation
- HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation
- Efficient Detection of Relaxed Maximal Cliques in Large-Scale IoT Networks
- Citrus Sorting Dynamic Control Using Multispectral Computer Vision
- Multiple Object Tracking as ID Prediction
- Segment Any-Quality Images with Generative Latent Space Enhancement
- Gaussian Splatting for Efficient Satellite Image Photogrammetry
- Instant Adversarial Purification with Adversarial Consistency Distillation
- Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation
- Rectified Diffusion Guidance for Conditional Generation
- Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Prediction
- No Thing, Nothing: Highlighting Safety-Critical Classes for Robust LiDAR Semantic Segmentation in Adverse Weather
- MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis
- A Single-Stage Admittance Control Network Based Misalignment Tolerant Inductive Power Transfer System for EV Application
- CrossOver: 3D Scene Cross-Modal Alignment
- MambaIC: State Space Models for High-Performance Learned Image Compression
- MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks
- Exact: Exploring Space-Time Perceptive Clues for Weakly Supervised Satellite Image Time Series Semantic Segmentation
- Understanding multi-layered transmission matrices
- Comparative Analysis of PI and Fuzzy Logic Control in High-Efficiency Triple-Output DC-DC Converters
- Towards Explicit Geometry-Reflectance Collaboration for Generalized LiDAR Segmentation in Adverse Weather
- UCM-VeID V2: A Richer Dataset and A Pre-Training Method for UAV Cross-Modality Vehicle Re-Identification
- Deep Fair Multi-View Clustering with Attention KAN
- HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis
- Enhancing Cluster Scheduling in HPC: A Continuous Transfer Learning for Real-Time Optimization
- Soft Switched Interleaved Buck Converter for High Power Applications
- Investigation of Oscillating Micro U-tube Based Fluid Density Sensor
- CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
- Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels
- DirectTriGS: Triplane-based Gaussian Splatting Field Representation for 3D Generation
- Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction
- Dynamic Estimation of Mental Workload and Operator Accuracy for Time-Constrained Binary Classification Tasks
- FGI: Fast GNN Inference on Multi-Core Systems
- Smart Eye: A Surveillance system
- Power Quality Enhancement Using Diffusion-Probabilistic Least Mean Square Technique
- AssertionForge: Enhancing Formal Verification Assertion Generation with Structured Representation of Specifications and RTL
- Machine Learning-based Trajectory Planning for Single-loop Flatness-based Control of PMSMs
- Navigating the Unseen: Zero-shot Scene Graph Generation via Capsule-Based Equivariant Features
- Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding
- NTFR: A Network Traffic Feature Reduction Method Based on Relational Analysis
- Automated Calculation of Algorithm Statement Execution Frequency Based on Abstract Syntax Tree
- MotionBench: Benchmarking and Improving Fine-Grained Video Motion Understanding for Vision Language Models
- Reduced Common Mode Voltage SVDPWM Strategy with Switching Loss Minimization in Four-Level NPC Inverter
- Digital Products Based on Large Language Models for the Exploration of Graph-Databases in Materials Science and Manufacturing
- NFC in Health Monitoring : A New Era of Medical Cards and Application
- TaskSimLF: Efficient Leader-Follower Multi-Agent Path Finding With Clustered Pickup and Delivery
- Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generation
- SpiralShard: Highly Concurrent and Secure Blockchain Sharding via Linked Cross-Shard Endorsement
- Sensing depth analysis of different permittivity materials based on open-ended coaxial probes at different input powers
- Methodology for GPU Frequency Switching Latency Measurement
- AI Driven Self-Healing Cybersecurity Systems with Agentic AI for Adaptive Threat Response and Resilience
- StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text
- CoLLM: A Large Language Model for Composed Image Retrieval
- GeoDepth: From Point-to-Depth to Plane-to-Depth Modeling for Self-Supervised Monocular Depth Estimation
- CGMatch: A Different Perspective of Semi-supervised Learning
- Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera
- Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration
- Exploring the Implications of Digital Tools for Participatory Ergonomics: Reflections Based on Three Case Studies
- Joint retrieval of ozone profile in near-space based on the atmospheric and near infrared atmospheric bands of O 2 airglow
- DDoS Protection System for Cloud using AWS and Machine Learning
- Calico: Part-Focused Semantic Co-Segmentation with Large Vision-Language Models
- Cancer Survival Prognosis From Whole Slide Images Using Hopfield Network
- PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Möbius Spatial Augmentation
- Reconstructing Animals and the Wild
- Buck-Converter-Based Inductor Loss Emulator for Multiple Power Electronics Applications
- Parametric Point Cloud Completion for Polygonal Surface Reconstruction
- Multifrequency Model of Sinusoidal PWM by DIDR Methodology
- Vision-Guided Action: Enhancing 3D Human Motion Prediction with Gaze-informed Affordance in 3D Scenes
- Volume Tells: Dual Cycle-Consistent Diffusion for 3D Fluorescence Microscopy De-noising and Super-Resolution
- Energy-Neutral Ultra-Wideband Asset Tracking Tag for Museums
- Research on Life Prediction of Surge Protective Device Based on Machine Learning
- Task Singular Vectors: Reducing Task Interference in Model Merging
- SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving
- Gen3DEval: Using vLLMs for Automatic Evaluation of Generated 3D Objects
- Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation
- VELOCITI: Benchmarking Video-Language Compositional Reasoning with Strict Entailment
- LT3SD: Latent Trees for 3D Scene Diffusion
- DRPL: A Distributed Forwarding Strategy for Enhanced P2P Communication in RPL-Based Low-Power and Lossy Networks
- BizGen: Advancing Article-level Visual Text Rendering for Infographics Generation
- Loop Splitting Optimization Via Semi-Invariance Analysis in Static Single Assignment Form
- LD-RPMNet: Near-Sensor Diagnosis for Railway Point Machines
- Locality-Aware Zero-Shot Human-Object Interaction Detection
- Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction
- Leveraging Large Language Models for Automated XR Instructional Content Generation
- RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images
- Discrete to Continuous: Generating Smooth Transition Poses from Sign Language Observations
- Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation
- Graph-Embedded Structure-Aware Perceptual Hashing for Neural Network Protection and Piracy Detection
- DiTASK: Multi-Task Fine-Tuning with Diffeomorphic Transformations
- Effective Cloud Removal for Remote Sensing Images by an Improved Mean-Reverting Denoising Model with Elucidated Design Space
- Perturb-and-Revise: Flexible 3D Editing with Generative Trajectories
- Research on Ship Energy Management Strategy of Equivalent Minimum Consumption Based on Ant-Lion Optimization Algorithm
- Effect of Substrate Bias in Ohmic p-Gate GaN-HEMTs on Unclamped Inductive Switching Capability
- OpenSIEM:A Unified Open Source Security Management Framework
- TADFormer: Task-Adaptive Dynamic TransFormer for Efficient Multi-Task Learning
- A Review of Research on Privacy Breaches in Federated Learning
- FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation
- Fingerprinting Denoising Diffusion Probabilistic Models
- A Framework for Automated Waste Classification System using Machine Learning and Deep Learning Techniques