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。
- PolarGuide-GSDR: 3D Gaussian Splatting Driven by Polarization Priors and Deferred Reflection for Real-World Reflective Scenes
日本大学: 関与なし(対象大学)
- Polarization State Tracing for Reflection Removal and Color-Consistent Reconstruction
日本大学: 関与なし(対象大学)
- PolySLGen: Online Multimodal Speaking-Listening Reaction Generation in Polyadic Interaction
日本大学: 関与なし(対象大学)
- Polyphony: Diffusion-based Dual-Hand Action Segmentation with Alternating Vision Transformer and Semantic Conditioning
日本大学: 関与なし(対象大学)
- Portable Active Learning for Object Detection
日本大学: 関与なし(対象大学)
- PortraitDirector: A Hierarchical Disentanglement Framework for Controllable and Real-time Facial Reenactment
日本大学: 関与なし(対象大学)
- Pose-Free Omnidirectional Gaussian Splatting for 360-Degree Videos with Consistent Depth Priors
日本大学: 関与なし(対象大学)
- Pose-guided Enriched Feature Learning for Federated-by-camera Person Re-identification
日本大学: 関与なし(対象大学)
- PoseAnything: General Pose-guided Video Generation with Part-aware Temporal Coherence
日本大学: 関与なし(対象大学)
- PoseD-Flow: Versatile and Guided Flow Matching Model of Human Pose
日本大学: 関与なし(対象大学)
- PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning
日本大学: 関与なし(対象大学)
- PoseGaussian: 6D Pose Estimation for Unseen Objects via Sparse-View Object-Level 3D Gaussian Splatting
日本大学: 関与なし(対象大学)
- PoseMaster: A Unified 3D Native Framework for Stylized Pose Generation
日本大学: 関与なし(対象大学)
- PositionIC: Unified Position and Identity Consistency for Image Customization
日本大学: 関与なし(対象大学)
- Post-training Feature Pruning for Fundus Images Classification
日本大学: 関与なし(対象大学)
- PosterIQ: A Design Perspective Benchmark for Poster Understanding and Generation
日本大学: 関与なし(対象大学)
- PosterOmni: Generalized Artistic Poster Creation via Task Distillation and Unified Reward Feedback
日本大学: 関与なし(対象大学)
- PosterReward: Unlocking Accurate Evaluation for High-Quality Graphic Design Generation
日本大学: 関与なし(対象大学)
- PowerCLIP: Powerset Alignment for Contrastive Pre-Training
日本大学: 東京科学大学
- PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Urban Scenes
日本大学: 関与なし(対象大学)
- Precise Object and Effect Removal with Adaptive Target-Aware Attention
日本大学: 関与なし(対象大学)
- Predict Before You Explore: Predictive Planning with Specialized Memory for Embodied Question Answering
日本大学: 関与なし(対象大学)
- Predicting Spatial Transcriptomics from Histology Images via High-Order Multi-Cell Interaction Modeling
日本大学: 関与なし(対象大学)
- Predictive Regularization Against Visual Representation Degradation in Multimodal Large Language Models
日本大学: 関与なし(対象大学)
- Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy
日本大学: 関与なし(対象大学)
- Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models
日本大学: 関与なし(対象大学)
- Premier: Personalized Preference Modulation with Learnable User Embedding in Text-to-Image Generation
日本大学: 関与なし(対象大学)
- Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality
日本大学: 関与なし(対象大学)
- Pressure2Motion: Hierarchical Human Motion Reconstruction from Ground Pressure with Text Guidance
日本大学: 関与なし(対象大学)
- PriVi: Towards a General-Purpose Video Model for Primate Behavior in the Wild
日本大学: 関与なし(対象大学)
- Prime Once, then Reprogram Locally: An Efficient Alternative to Black-Box Service Model Adaptation
日本大学: 関与なし(対象大学)
- Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models
日本大学: 関与なし(対象大学)
- PrivSynth: Alternating and Control-Based Optimization for Privacy and Utility in Synthetic Data
日本大学: 関与なし(対象大学)
- PrivateEyes: Gaze-Preserving Anonymization for Data Sharing
日本大学: 関与なし(対象大学)
- ProFocus: Proactive Perception and Focused Reasoning in Vision-and-Language Navigation
日本大学: 関与なし(対象大学)
- ProM3E: Probabilistic Masked MultiModal Embedding Model for Ecology
日本大学: 関与なし(対象大学)
- ProOOD: Prototype-Guided Out-of-Distribution 3D Occupancy Prediction
日本大学: 関与なし(対象大学)
- ProPhy: Progressive Physical Alignment for Dynamic World Simulation
日本大学: 関与なし(対象大学)
- ProSoftArena: Benchmarking Hierarchical Capabilities of Multi-modal Agents in Professional Software Environments
日本大学: 関与なし(対象大学)
- ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence On Mobile Devices
日本大学: 関与なし(対象大学)
- Probabilistic Concept Graph Reasoning for Multimodal Misinformation Detection
日本大学: 関与なし(対象大学)
- Probabilistic Discrepancy Learning for Roadside LiDAR Scene Completion
日本大学: 関与なし(対象大学)
- Probabilistic Precipitation Nowcasting with Rectified Flow Transformers
日本大学: 関与なし(対象大学)
- Probabilistic Prompt Adaptation for Unified Image Aesthetics and Quality Assessment
日本大学: 関与なし(対象大学)
- Probing and Bridging Geometry-Interaction Cues for Affordance Reasoning in Vision Foundation Models
日本大学: 関与なし(対象大学)
- ProcessMaker: A Generalized Process Visualization Framework with Adaptive Sequence Steps on Diffusion Transformers
日本大学: 関与なし(対象大学)
- ProgTrack: A Multi-Object Tracking Algorithm with Progressive Matching Strategy
日本大学: 関与なし(対象大学)
- Progress by Pieces: Test-Time Scaling for Autoregressive Image Generation
日本大学: 関与なし(対象大学)
- Progress-Think: Semantic Progress Reasoning for Vision-Language Navigation
日本大学: 関与なし(対象大学)
- Progressive Cross-Modal Causal Intervention for Long-Term Action Recognition
日本大学: 関与なし(対象大学)
- Progressive Guessing to Fixed Point: Rethinking Human Motion Prediction with Deep Equilibrium Models
日本大学: 関与なし(対象大学)
- Progressive Mask Distillation for Self-supervised Video Representation
日本大学: 関与なし(対象大学)
- Progressive Multi-cue Alignment for Unaligned RGBT Tracking
日本大学: 関与なし(対象大学)
- Progressive Neural Architecture Generation
日本大学: 関与なし(対象大学)
- Progressive Supernet Training for Efficient Visual Autoregressive Modeling
日本大学: 関与なし(対象大学)
- ProgressiveAvatars: Progressive Animatable 3D Gaussian Avatars
日本大学: 関与なし(対象大学)
- ProjFlow: Projection Sampling with Flow Matching for Zero-Shot Exact Spatial Motion Control
日本大学: 早稲田大学
- Prompt Yourself: Awakening Textual Semantics in 1D Visual Tokenizers
日本大学: 関与なし(対象大学)
- Prompt-Anchored Vision-Text Distillation for Lifelong Person Re-identification
日本大学: 関与なし(対象大学)
- Prompt-Free Universal Region Proposal Network
日本大学: 関与なし(対象大学)
- Prompt-Free Unknown Label Generation for Open World Detection in Remote Sensing
日本大学: 関与なし(対象大学)
- PromptDepth: Efficient and Promptable Geometric 3D Vision Model for Embodied Intelligence
日本大学: 関与なし(対象大学)
- PromptEnhancer: Taming Your Rewriter for Text-to-Image Generation via Fine-Grained Reward
日本大学: 関与なし(対象大学)
- PromptLoop: Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment
日本大学: 関与なし(対象大学)
- PromptMoE: A Segmentation Refinement Framework Leveraging Mixture of Experts for Improved Prompting
日本大学: 関与なし(対象大学)
- PromptStereo: Zero-Shot Stereo Matching via Structure and Motion Prompts
日本大学: 関与なし(対象大学)
- Proof-of-Perception: Certified Tool-Using Multimodal Reasoning with Compositional Conformal Guarantees
日本大学: 関与なし(対象大学)
- PropFly: Learning to Propagate via On-the-Fly Supervision from Pre-trained Video Diffusion Models
日本大学: 関与なし(対象大学)
- Property-Informed Diffusion-Based Text-to-Microstructure Generation
日本大学: 関与なし(対象大学)
- Prospective Dynamic 3D MRI Reconstruction via Latent-Space Motion Tracking from Single Measurement
日本大学: 関与なし(対象大学)
- Protect to Adapt: Orthogonal Subspace Control with Ranked Negative-Prompt Curriculum for Few-Shot Action Recognition
日本大学: 関与なし(対象大学)
- Protego: User-Centric Pose-Invariant Privacy Protection Against Face Recognition-Induced Digital Footprint Exposure
日本大学: 関与なし(対象大学)
- Prototype-Guided Concept Erasure in Diffusion Models
日本大学: 関与なし(対象大学)
- Prototype-as-Prompt: Multimodal Sentiment Prototypes Endowing Large Language Models the Capability to Perform Multimodal Sentiment Analysis
日本大学: 関与なし(対象大学)
- Prototype-based Causal Intervention for Multi-Label Image Classification
日本大学: 関与なし(対象大学)
- Prototypical Action Reasoning Facilitated by Vision-Language Alignment for Egocentric Action Anticipation
日本大学: 関与なし(対象大学)
- Proxy-GS: Unified Occlusion Priors for Training and Inference in Structured 3D Gaussian Splatting
日本大学: 関与なし(対象大学)
- Proxy-Tuning: Tailoring Multimodal Autoregressive Models for Subject-Driven Image Generation
日本大学: 関与なし(対象大学)
- Proxy3D: Efficient 3D Representations for Vision-Language Models via Semantic Clustering and Alignment
日本大学: 関与なし(対象大学)
- ProxyFL: A Proxy-Guided Framework for Federated Semi-Supervised Learning
日本大学: 関与なし(対象大学)
- Prune Wisely, Reconstruct Sharply: Compact 3D Gaussian Splatting via Adaptive Pruning and Difference-of-Gaussian Primitives
日本大学: 関与なし(対象大学)
- Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving
日本大学: 関与なし(対象大学)
- PureCC: Pure Learning for Text-to-Image Concept Customization
日本大学: 関与なし(対象大学)
- PureProof: Diffusion-Resistant Black-box Targeted Attack on Large Vision-Language Models
日本大学: 関与なし(対象大学)
- Push-and-Step: From RL-Based Balance Recovery to Physical Simulation of Dense Crowds
日本大学: 関与なし(対象大学)
- Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning
日本大学: 関与なし(対象大学)
- PvP: Data-Efficient Humanoid Robot Learning with Proprioceptive-Privileged Contrastive Representations
日本大学: 関与なし(対象大学)
- PyraTok: Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation
日本大学: 関与なし(対象大学)
- PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inference
日本大学: 関与なし(対象大学)
- QD-PCQA: Quality-Aware Domain Adaptation for Point Cloud Quality Assessment
日本大学: 関与なし(対象大学)
- QUANTIPHY: A Quantitative Benchmark Evaluating Physical Reasoning Abilities of Vision-Language Models
日本大学: 関与なし(対象大学)
- QVGGT: Post-Training Quantized Visual Geometry Grounded Transformer
日本大学: 関与なし(対象大学)
- QuCNet: Quantum Deep Learning Driven Multi-Circuit Network for Remote Sensing Image Classification
日本大学: 関与なし(対象大学)
- QuadSync: Quadrifocal Tensor Synchronization via Tucker Decomposition
日本大学: 関与なし(対象大学)
- Quant Experts: Token-aware Adaptive Error Reconstruction with Mixture of Experts for Large Vision-Language Models Quantization
日本大学: 関与なし(対象大学)
- QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models
日本大学: 関与なし(対象大学)
- Quantized Residuals to Continuous Prompts for Few-Shot Class Incremental Learning in Vision-Language Models
日本大学: 関与なし(対象大学)
- Quantum-Gated Task-interaction Knowledge Distillation for Pre-trained Model-based Class-Incremental Learning
日本大学: 関与なし(対象大学)
- Query2Uncertainty: Robust Uncertainty Quantification and Calibration for 3D Object Detection under Distribution Shift
日本大学: 関与なし(対象大学)
- QueryMe: Query-Driven Open-Vocabulary 3D Object Affordances Grounding from Multimodal Evidence
日本大学: 関与なし(対象大学)