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。
- Confidence-Guided Multi-Scale Aggregation for Sparse-View High-Resolution 3D Gaussian Splatting
日本大学: 関与なし(対象大学)
- Conflict-Aware Adaptive Cross-Reconstruction for Multimodal Sentiment Analysis
日本大学: 関与なし(対象大学)
- Confusion-Aware Spectral Regularizer for Long-Tailed Recognition
日本大学: 関与なし(対象大学)
- ConsID-Gen: View-Consistent and Identity-Preserving Image-to-Video Generation
日本大学: 関与なし(対象大学)
- Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR
日本大学: 関与なし(対象大学)
- Consensus vs. Controversy: Mapping the Decision Space Where Architectures Diverge
日本大学: 関与なし(対象大学)
- ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation
日本大学: 関与なし(対象大学)
- ConsistCompose: Unified Multimodal Layout Control for Image Composition
日本大学: 関与なし(対象大学)
- Consistency Beyond Contrast: Enhancing Open-Vocabulary Object Detection Robustness via Contextual Consistency Learning
日本大学: 関与なし(対象大学)
- Consistent Instance Field for Dynamic Scene Understanding
日本大学: 関与なし(対象大学)
- Contact-Aware Neural Dynamics
日本大学: 関与なし(対象大学)
- Content-Adaptive Hierarchical Hyperprior for Neural Video Coding
日本大学: 関与なし(対象大学)
- Content-Aware Dynamic Patchification for Efficient Video Diffusion
日本大学: 関与なし(対象大学)
- Content-Aware Frequency Encoding for Implicit Neural Representations with Fourier-Chebyshev Features
日本大学: 関与なし(対象大学)
- Context-Nav: Context-Driven Exploration and Viewpoint-Aware 3D Spatial Reasoning for Instance Navigation
日本大学: 関与なし(対象大学)
- Continual Distillation of Teachers from Different Domains
日本大学: 東京大学
- Continual Learning for fMRI-Based Brain Disorder Diagnosis via Functional Connectivity Matrices Generative Replay
日本大学: 関与なし(対象大学)
- Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis
日本大学: 関与なし(対象大学)
- Contrastive Cross-Bag Augmentation for Multiple Instance Learning-based Whole Slide Image Classification
日本大学: 関与なし(対象大学)
- Controllable Federated Prompt Learning at Test Time
日本大学: 関与なし(対象大学)
- Conversational Image Segmentation: Grounding Abstract Concepts with Scalable Supervision
日本大学: 関与なし(対象大学)
- Convexity-Aware Noise Calibration: A Self-Supervised Framework for Noise-Level-Unknown Image Denoising
日本大学: 関与なし(対象大学)
- Convolutional Neural Networks Driven by Content Similarity
日本大学: 関与なし(対象大学)
- CoopDiff: A Diffusion-Guided Approach for Cooperation under Corruptions
日本大学: 関与なし(対象大学)
- CoordSpeaker: Exploiting Gesture Captioning for Coordinated Caption-Empowered Co-Speech Gesture Generation
日本大学: 関与なし(対象大学)
- Coordinate Denoising for Non-Equilibrium Molecular Representation Learning
日本大学: 関与なし(対象大学)
- Copy-Transform-Paste: Zero-Shot Object-Object Alignment Guided by Vision-Language and Geometric Constraints
日本大学: 関与なし(対象大学)
- Correspondence-Attention Alignment for Multi-View Diffusion Models
日本大学: 関与なし(対象大学)
- CountGD++: Generalized Prompting for Open-World Counting
日本大学: 関与なし(対象大学)
- Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoning
日本大学: 関与なし(対象大学)
- Coupled Diffusion Sampling for Training-Free Multi-View Image Editing
日本大学: 関与なし(対象大学)
- Coupling Liquid Time-Constant Encoders with Modern Hopfield Memory
日本大学: 関与なし(対象大学)
- Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimation
日本大学: 関与なし(対象大学)
- Coverage Optimization for Camera View Selection
日本大学: 関与なし(対象大学)
- CrackSSM: Reviving SSMs for Crack Segmentation via Dynamic Scanning
日本大学: 関与なし(対象大学)
- CraftMesh: High-Fidelity Generative Mesh Manipulation via Poisson Seamless Fusion
日本大学: 関与なし(対象大学)
- Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning on the Edge
日本大学: 関与なし(対象大学)
- Cross from Left to Right Brain: Adaptive Text Dreamer for Vision-and-Language Navigation
日本大学: 関与なし(対象大学)
- Cross-Architecture Adaptation: Cloud-Edge Continual Test-Time Adaptation with Dynamic Sampling and Heterogeneous Distillation
日本大学: 関与なし(対象大学)
- Cross-Axis Feature Fusion with Joint-Wise Motion Difference Prediction for Text-Based 3D Human Motion Editing
日本大学: 関与なし(対象大学)
- Cross-Domain Demo-to-Code via Neurosymbolic Counterfactual Reasoning
日本大学: 関与なし(対象大学)
- Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptation
日本大学: 関与なし(対象大学)
- Cross-Hand Latent Representation for Vision-Language-Action Models
日本大学: 関与なし(対象大学)
- Cross-Instance Gaussian Splatting Registration via Geometry-Aware Feature-Guided Alignment
日本大学: 関与なし(対象大学)
- Cross-Modal Attention Calibration for LVLM Hallucination Mitigation
日本大学: 関与なし(対象大学)
- Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Video
日本大学: 関与なし(対象大学)
- Cross-Modal Guided Visual Synthesis for Data-Efficient Multimodal Depression Recognition
日本大学: 関与なし(対象大学)
- Cross-Scale Pansharpening via ScaleFormer and the PanScale Benchmark
日本大学: 関与なし(対象大学)
- Cross-Slice Knowledge Transfer via Masked Multi-Modal Heterogeneous Graph Contrastive Learning for Spatial Gene Expression Inference
日本大学: 関与なし(対象大学)
- Cross-Subject EEG-to-Video Reconstruction and Beyond
日本大学: 関与なし(対象大学)
- Cross-View Distillation and Adaptive Masking for Incomplete Multi-View Multi-Label Classification
日本大学: 関与なし(対象大学)
- Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Images
日本大学: 関与なし(対象大学)
- Cross-domain Dual-stream Feature Disentanglement for Brain Disorder Prediction with Sparsely Labeled PET
日本大学: 関与なし(対象大学)
- Cross-modal Fuzzy Alignment Network for Text-Aerial Person Retrieval and A Large-scale Benchmark
日本大学: 関与なし(対象大学)
- Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning
日本大学: 関与なし(対象大学)
- Cross-modal Representation Learning for Diffusion-generated Image Detection
日本大学: 関与なし(対象大学)
- CrossEarth-Gate: Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain Remote Sensing Semantic Segmentation
日本大学: 関与なし(対象大学)
- CrossHOI-Bench: A Unified Benchmark for HOI Evaluation across Vision-Language Models and HOI-Specific Methods
日本大学: 関与なし(対象大学)
- CrossHOI: Learning Cross-View Representations for Monocular 3D Human-Object Interaction Reconstruction
日本大学: 関与なし(対象大学)
- CrossVL: Complexity-Aware Feature Routing and Paired Curriculum for Cross-View Vision-Language Detection
日本大学: 関与なし(対象大学)
- CrowdGaussian: Reconstructing High-Fidelity 3D Gaussians for Human Crowd from a Single Image
日本大学: 関与なし(対象大学)
- CryoHype: Reconstructing a thousand cryo-EM structures with transformer-based hypernetworks
日本大学: 関与なし(対象大学)
- CryoKRAQEN: Kernel-Regularized Annealing for Quantized Embedding Networks in Cryo-EM Heterogeneous Reconstruction
日本大学: 関与なし(対象大学)
- CubeComposer: Spatio-Temporal Autoregressive 4K 360deg Video Generation from Perspective Video
日本大学: 関与なし(対象大学)
- Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens
日本大学: 関与なし(対象大学)
- Curriculum Group Policy Optimization: Adaptive Sampling for Unleashing the Potential of Text-to-Image Generation
日本大学: 関与なし(対象大学)
- Curvature-Aware Captioning: Leveraging Geodesic Attention for 3D Scene Understanding
日本大学: 関与なし(対象大学)
- Curvature-Aware Zeroth-Order Optimization for Memory-Efficient Test-Time Adaptation
日本大学: 関与なし(対象大学)
- CustomTex: High-fidelity Indoor Scene Texturing via Multi-Reference Customization
日本大学: 関与なし(対象大学)
- Customized Fusion: A Closed-Loop Dynamic Network for Adaptive Multi-Task-Aware Infrared-Visible Image Fusion
日本大学: 関与なし(対象大学)
- Cut to the Chase: Training-free Multimodal Summarization via Chain-of-Events
日本大学: 関与なし(対象大学)
- Cycle-Consistent Tuning for Layered Image Decomposition
日本大学: 関与なし(対象大学)
- CycleBEV: Regularizing View Transformation Networks via View Cycle Consistency for Bird's-Eye-View Semantic Segmentation
日本大学: 関与なし(対象大学)
- CycleManip: Enabling Cycle-based Manipulation via Effective History Perception and Understanding
日本大学: 関与なし(対象大学)
- D$^2$-FOSA: Dual-Diffusion Guided EEG-to-Image Reconstruction with Frequency-Oriented Semantic Alignment
日本大学: 関与なし(対象大学)
- D-Convexity: A Unified Differentiable Convex Shape Prior via Quasi-Concavity for Data-driven Image Segmentation
日本大学: 関与なし(対象大学)
- D-Prism: Differentiable Primitives for Structured Dynamic Modeling
日本大学: 関与なし(対象大学)
- D2Cache: Second-Order Delta Caching for Higher Video Diffusion Acceleration
日本大学: 関与なし(対象大学)
- D2Dewarp: Dual Dimensions Geometric Representation Learning Based Document Image Dewarping
日本大学: 関与なし(対象大学)
- D2FANet: Enhancing Video Object Detection with Dual-Domain Feature Aggregation Network
日本大学: 関与なし(対象大学)
- D2T2 - Multimodal Automated Planning for Brachytherapy
日本大学: 関与なし(対象大学)
- D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation
日本大学: 関与なし(対象大学)
- DA-Mamba: Learning Domain-Aware State Space Model for Global-Local Alignment in Domain Adaptive Object Detection
日本大学: 関与なし(対象大学)
- DA-VAE: Plug-in Latent Compression for Diffusion via Detail Alignment
日本大学: 関与なし(対象大学)
- DABO: Difficulty-Aware Bayesian Optimization with Diffusion-Learned Priors
日本大学: 関与なし(対象大学)
- DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation
日本大学: 関与なし(対象大学)
- DARC: Dual Adjustment Reasoning with Counterfactuals for Trustworthy Chest X-ray Classification
日本大学: 関与なし(対象大学)
- DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples
日本大学: 関与なし(対象大学)
- DBMSolver: A Training-free Diffusion Bridge Sampler for High-Quality Image-to-Image Translation
日本大学: 関与なし(対象大学)
- DC-Merge: Improving Model Merging with Directional Consistency
日本大学: 関与なし(対象大学)
- DCoAR: Deep Concept Injection into Unified Autoregressive Models for Personalized Text-to-Image Generation
日本大学: 関与なし(対象大学)
- DDSF: Robust Few-Shot Learning via Disentangled Subspaces with Determinantal Point Process
日本大学: 関与なし(対象大学)
- DDT: Decoupled Diffusion Transformer
日本大学: 関与なし(対象大学)
- DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers
日本大学: 関与なし(対象大学)
- DENALI: A Dataset Enabling Non-Line-of-Sight Spatial Reasoning with Low-Cost LiDARs
日本大学: 関与なし(対象大学)
- DETACH : Decomposed Spatio-Temporal Alignment for Exocentric Video and Ambient Sensors with Staged Learning
日本大学: 関与なし(対象大学)
- DEVA: Fine-tuning Multimodal Large Language Models for Visual Perception Tasks
日本大学: 関与なし(対象大学)
- DFD-HR: Generalizable Deepfake Detection via Hierarchical Routing Learning
日本大学: 関与なし(対象大学)
- DF^2-VB: Dual-level Fuzzy Fusion with View-specific Boosting for Multi-view Multi-label Classification
日本大学: 関与なし(対象大学)
- DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images
日本大学: 関与なし(対象大学)