Conferences · eligible papers
CVPR
2022–2026 LIVE
2026 · 4,042 papers
このEditionに反映済みのmain full research papersのみ掲載しています。著者リンクは日本の大学への著者別所属根拠がある場合に限ります。
- Few-Step Diffusion Sampling Through Instance-Aware Discretizations
日本大学: 関与なし(対象大学)
- Few-for-Many Personalized Federated Learning
日本大学: 関与なし(対象大学)
- Few-shot Acoustic Synthesis with Multimodal Flow Matching
日本大学: 関与なし(対象大学)
- FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolution
日本大学: 関与なし(対象大学)
- Fighting Hallucinations with Counterfactuals: Diffusion-Guided Perturbations for LVLM Hallucination Suppression
日本大学: 関与なし(対象大学)
- FilterGS: Traversal-Free Parallel Filtering and Adaptive Shrinking for Large-Scale LoD 3D Gaussian Splatting
日本大学: 関与なし(対象大学)
- FinPercep-RM: A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based Real-world Super-Resolution
日本大学: 関与なし(対象大学)
- Finding Distributed Object-Centric Properties in Self-Supervised Transformers
日本大学: 関与なし(対象大学)
- Fine-Grained GRPO for Precise Preference Alignment in Flow Models
日本大学: 関与なし(対象大学)
- Fine-Grained Multi Image Object Hallucination Benchmark
日本大学: 関与なし(対象大学)
- Fine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients
日本大学: 関与なし(対象大学)
- Fine-Tuning Impairs the Balancedness of Foundation Models in Long-tailed Personalized Federated Learning
日本大学: 関与なし(対象大学)
- Fine-VAD: Towards Fine-Grained Video Anomaly Detection via Progressive Cross-Granularity Learning
日本大学: 関与なし(対象大学)
- Fine-grained Image Aesthetic Assessment: Learning Discriminative Scores from Relative Ranks
日本大学: 関与なし(対象大学)
- FireScope: Wildfire Risk Raster Prediction With a Chain-of-Thought Oracle
日本大学: 関与なし(対象大学)
- First Frame Is the Place to Go for Video Content Customization
日本大学: 関与なし(対象大学)
- First Logit Boosting: Visual Grounding Method to Mitigate Object Hallucination in Large Vision-Language Models
日本大学: 関与なし(対象大学)
- FisherPoser: Human Motion Estimation from Sparse Observations with Hierarchical Region-Wise Fisher-Matrix Uncertainty Modeling
日本大学: 関与なし(対象大学)
- Fixed Anchors Are Not Enough: Dynamic Retrieval and Persistent Homology for Dataset Distillation
日本大学: 関与なし(対象大学)
- Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning
日本大学: 関与なし(対象大学)
- FlashCap: Millisecond-Accurate Human Motion Capture via Flashing LEDs and Event-Based Vision
日本大学: 関与なし(対象大学)
- FlashDecoder: Real-Time Latent-to-Pixel Streaming Decoder with Transformers
日本大学: 関与なし(対象大学)
- FlashIn: Fast and Accurate Image Inversion for Real-time Image Editing
日本大学: 関与なし(対象大学)
- FlashLips: 100-FPS Mask-Free Latent Lip-Sync using Reconstruction Instead of Diffusion or GANs
日本大学: 関与なし(対象大学)
- FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation
日本大学: 関与なし(対象大学)
- FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance
日本大学: 関与なし(対象大学)
- FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction
日本大学: 関与なし(対象大学)
- FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention
日本大学: 関与なし(対象大学)
- FlashVSR: Towards Real-time Diffusion-Based Streaming Video Super Resolution
日本大学: 関与なし(対象大学)
- Flat-Pack Bench: Evaluating Spatio-Temporal Understanding in Large Vision-Language Models through Furniture Assembly
日本大学: 関与なし(対象大学)
- FlexAvatar: Flexible Large Reconstruction Model for Animatable Gaussian Head Avatars with Detailed Deformation
日本大学: 関与なし(対象大学)
- FlexAvatar: Learning Complete 3D Head Avatars with Partial Supervision
日本大学: 関与なし(対象大学)
- FlexTraj: Image-to-Video Generation with Flexible Point Trajectory Control
日本大学: 関与なし(対象大学)
- FlexiVideo: Variation-Aware Temporal Dynamics Modeling for Efficient Video Understanding
日本大学: 関与なし(対象大学)
- FloVerse: Floor Plan-Guided Multi-Modal Navigation
日本大学: 関与なし(対象大学)
- FloodDiffusion: Tailored Diffusion Forcing for Streaming Motion Generation
日本大学: 東京大学
- Flow Map Distillation Without Data
日本大学: 関与なし(対象大学)
- Flow Matching for Multimodal Distributions
日本大学: 関与なし(対象大学)
- Flow3r: Factored Flow Prediction for Scalable Visual Geometry Learning
日本大学: 関与なし(対象大学)
- Flow4DGS-SLAM: Optical Flow-Guided 4D Gaussian Splatting SLAM
日本大学: 関与なし(対象大学)
- FlowComposer: Composable Flows for Compositional Zero-Shot Learning
日本大学: 関与なし(対象大学)
- FlowDC: Flow-Based Decoupling-Decay for Complex Image Editing
日本大学: 関与なし(対象大学)
- FlowDIS: Language-Guided Dichotomous Image Segmentation with Flow Matching
日本大学: 関与なし(対象大学)
- FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing
日本大学: 関与なし(対象大学)
- FlowFM: Advancing Dark Optical Flow Estimation with Flow Matching
日本大学: 関与なし(対象大学)
- FlowFixer: Towards Detail-Preserving Subject-Driven Generation
日本大学: 関与なし(対象大学)
- FlowHijack: A Dynamics-Aware Backdoor Attack on Flow-Matching Vision-Language-Action Models
日本大学: 関与なし(対象大学)
- FlowMotion: Training-Free Flow Guidance for Video Motion Transfer
日本大学: 関与なし(対象大学)
- FlowPalm: Optical Flow Driven Non-Rigid Deformation for Geometrically Diverse Palmprint Generation
日本大学: 関与なし(対象大学)
- FlowPortal: Residual-Corrected Flow for Training-Free Video Relighting and Background Replacement
日本大学: 関与なし(対象大学)
- FlowSteer: Guiding Few-Step Image Synthesis with Authentic Trajectories
日本大学: 関与なし(対象大学)
- Flowception: Temporally Expansive Flow Matching for Video Generation
日本大学: 関与なし(対象大学)
- FluidGaussian: Propagating Simulation-Based Uncertainty Toward Functionally-Intelligent 3D Reconstruction
日本大学: 関与なし(対象大学)
- FluoCLIP: Stain-Aware Focus Quality Assessment in Fluorescence Microscopy
日本大学: 関与なし(対象大学)
- FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding
日本大学: 関与なし(対象大学)
- FoSS: Modeling Long-Range Dependencies and Multimodal Uncertainty in Trajectory Prediction via Fourier-State Space Integration
日本大学: 関与なし(対象大学)
- FoV-Net: Rotation-Invariant CAD B-rep Learning via Field-of-View Ray Casting
日本大学: 関与なし(対象大学)
- Focal-General Diffusion Model with Semantic Consistent Guidance for Sign Language Production
日本大学: 関与なし(対象大学)
- Focus on Background: Exploring SAM's Potential in Few-shot Medical Image Segmentation with Background-centric Prompting
日本大学: 関与なし(対象大学)
- Focus, Don't Prune: Identifying Instruction-Relevant Regions for Information-Rich Image Understanding
日本大学: 関与なし(対象大学)
- Focus-to-Perceive Representation Learning: A Cognition-Inspired Hierarchical Framework for Endoscopic Video Analysis
日本大学: 関与なし(対象大学)
- FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection
日本大学: 関与なし(対象大学)
- FoleyDesigner: Immersive Stereo Foley Generation with Precise Spatio-Temporal Alignment for Film Clips
日本大学: 関与なし(対象大学)
- FoleyDirector: Fine-Grained Temporal Steering for Video-to-Audio Generation via Structured Scripts
日本大学: 関与なし(対象大学)
- Follow the Saliency: Supervised Saliency for Retrieval-augmented Dense Video Captioning
日本大学: 関与なし(対象大学)
- FontCrafter: High-Fidelity Element-Driven Artistic Font Creation with Visual In-Context Generation
日本大学: 関与なし(対象大学)
- ForceVLA2: Unleashing Hybrid Force-Position Control with Force Awareness for Contact-Rich Manipulation
日本大学: 関与なし(対象大学)
- ForeAct: Steering Your VLA with Efficient Visual Foresight Planning
日本大学: 関与なし(対象大学)
- ForeHOI: Feed-forward 3D Object Reconstruction from Daily Hand-Object Interaction Videos
日本大学: 関与なし(対象大学)
- Forecast the Principal, Stabilize the Residual: Subspace-Aware Feature Caching for Diffusion Transformers
日本大学: 関与なし(対象大学)
- Forecasting 3D Scanpaths in Egocentric Video
日本大学: 関与なし(対象大学)
- Forensic-Friendly Image Manipulation via Controllable Latent Diffusion
日本大学: 関与なし(対象大学)
- Forging a Dynamic Memory: Retrieval-Guided Continual Learning for Generalist Medical Foundation Models
日本大学: 関与なし(対象大学)
- FoundIR-v2: Optimizing Pre-Training Data Mixtures for Image Restoration Foundation Model
日本大学: 関与なし(対象大学)
- Foundation Encoders Are All You Need for Preference-Aware Personalization
日本大学: 関与なし(対象大学)
- Foundation Model Priors Enhance Object Focus in Feature Space for Source-Free Object Detection
日本大学: 関与なし(対象大学)
- Foundry: Distilling 3D Foundation Models for the Edge
日本大学: 関与なし(対象大学)
- Fourier Angle Alignment for Oriented Object Detection in Remote Sensing
日本大学: 東北大学
- Fractal Camouflage: A Bio-Inspired Approach for Multi-Scale Adversarial Attacks in the Infrared Domain
日本大学: 関与なし(対象大学)
- Frame2Freq: Spectral Adapters for Fine-Grained Video Understanding
日本大学: 関与なし(対象大学)
- Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning
日本大学: 関与なし(対象大学)
- FrankenMotion: Part-level Human Motion Generation and Composition
日本大学: 関与なし(対象大学)
- Free-Grained Hierarchical Visual Recognition
日本大学: 関与なし(対象大学)
- Free-Lunch Long Video Generation via Layer-Adaptive O.O.D Correction
日本大学: 関与なし(対象大学)
- FreeArtGS: Articulated Gaussian Splatting Under Free-moving Scenario
日本大学: 関与なし(対象大学)
- FreeForm: Reduced-Order Deformable Simulation from Particle-Based Skinning Eigenmodes
日本大学: 関与なし(対象大学)
- FreeScale: Scaling 3D Scenes via Certainty-Aware Free-View Generation
日本大学: 関与なし(対象大学)
- FreqEdit: Preserving High-Frequency Features for Robust Multi-Turn Image Editing
日本大学: 関与なし(対象大学)
- FreqSIC: Frequency-aware Stereo Image Compression with Bi-directional Checkerboard Context Model
日本大学: 関与なし(対象大学)
- Frequency Switching Mechanism for Parameter-Efficient Multi-Task Learning
日本大学: 関与なし(対象大学)
- Frequency-Aware Affinity for Weakly Supervised Semantic Segmentation
日本大学: 関与なし(対象大学)
- Frequency-Aware Flow Matching for High-Quality Image Generation
日本大学: 関与なし(対象大学)
- Frequency-domain Manipulation for Face Obfuscation
日本大学: 関与なし(対象大学)
- Fresco: Frequency-Spatial Consistent Optimization for Fine-Grained Head Avatar Modeling
日本大学: 関与なし(対象大学)
- From 2D Alignment to 3D Plausibility: Unifying Heterogeneous 2D Priors and Penetration-Free Diffusion for Occlusion-Robust Two-Hand Reconstruction
日本大学: 関与なし(対象大学)
- From 3D Pose to Prose: Biomechanics-Grounded Vision-Language Coaching
日本大学: 関与なし(対象大学)
- From Attraction to Equilibrium: Physics-Inspired Semantic Gravitons for Zero-Shot Anomaly Detection
日本大学: 関与なし(対象大学)
- From Contrast to Consistency: Rethinking Event-based Continuous-Time Optical Flow Estimation
日本大学: 関与なし(対象大学)
- From Corners to Fiducial Tags: Revisiting Checkerboard Calibration for Event Cameras
日本大学: 関与なし(対象大学)
- From Detection to Association: Learning Discriminative Object Embeddings for Multi-Object Tracking
日本大学: 関与なし(対象大学)