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。
- Scaling Multi-Identity Consistency for Image Customization via Multi-to-Multi Matching Paradigm
日本大学: 関与なし(対象大学)
- Scaling Parallel Sequence Models to Vision Foundation Models
日本大学: 関与なし(対象大学)
- Scaling Self-Supervised and Cross-Modal Pretraining for Volumetric CT Transformers
日本大学: 関与なし(対象大学)
- Scaling Spatial Intelligence with Multimodal Foundation Models
日本大学: 関与なし(対象大学)
- Scaling Test-Time Robustness of Vision-Language Models via Self-Critical Inference Framework
日本大学: 関与なし(対象大学)
- Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes
日本大学: 関与なし(対象大学)
- Scaling View Synthesis Transformers
日本大学: 関与なし(対象大学)
- Scaling Zero-Shot Reference-to-Video Generation
日本大学: 関与なし(対象大学)
- Scaling the Long Video Understanding of Multimodal Large Language Models via Visual Memory Mechanism
日本大学: 関与なし(対象大学)
- Scaling-Aware Data Selection for End-to-End Autonomous Driving Systems
日本大学: 関与なし(対象大学)
- Scaling4D: Pushing the Frontier of Video Novel View Synthesis through Large-Scale Monocular Videos
日本大学: 関与なし(対象大学)
- Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restoration
日本大学: 関与なし(対象大学)
- SceMoS: Scene-Aware 3D Human Motion Synthesis by Planning with Geometry-Grounded Tokens
日本大学: 関与なし(対象大学)
- ScenDi: 3D-to-2D Scene Diffusion Cascades for Urban Generation
日本大学: 関与なし(対象大学)
- Scene Grounding in the Wild
日本大学: 関与なし(対象大学)
- Scene Reconstruction as Mapping Priors for 3D Detection
日本大学: 関与なし(対象大学)
- Scene-Centric Unsupervised Video Panoptic Segmentation
日本大学: 関与なし(対象大学)
- SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model
日本大学: 関与なし(対象大学)
- SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations
日本大学: 関与なし(対象大学)
- SceneTok: A Compressed, Diffusable Token Space for 3D Scenes
日本大学: 関与なし(対象大学)
- Scenes as Tokens: Multi-Scale Normal Distributions Transform Tokenizer for General 3D Vision-Language Understanding
日本大学: 関与なし(対象大学)
- SciEducator: Scientific Video Understanding and Educating via Deming-Cycle Multi-Agent System
日本大学: 関与なし(対象大学)
- Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling
日本大学: 関与なし(対象大学)
- Score2Instruct: Scaling Up Video Quality-Centric Instructions via Automated Dimension Scoring
日本大学: 関与なし(対象大学)
- Sculpt4D: Generating 4D Shapes via Sparse-Attention Diffusion Transformers
日本大学: 関与なし(対象大学)
- SeD-UD: An Influence-Driven and Hierarchically-Decoupled Information Bottleneck for Multimodal Intent Recognition
日本大学: 関与なし(対象大学)
- SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models
日本大学: 関与なし(対象大学)
- SearchAD: Large-Scale Rare Image Retrieval Dataset for Autonomous Driving
日本大学: 関与なし(対象大学)
- See Further, Think Deeper: Advancing VLM's Reasoning Ability with Low-level Visual Cues and Reflection
日本大学: 関与なし(対象大学)
- See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs
日本大学: 関与なし(対象大学)
- See Less, See Right: Bi-directional Perceptual Shaping For Multimodal Reasoning
日本大学: 関与なし(対象大学)
- See Through the Noise: Improving Domain Generalization in Gaze Estimation
日本大学: 関与なし(対象大学)
- See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding
日本大学: 関与なし(対象大学)
- See What We Cannot See: A Geo-guided Reasoning Benchmark for Object Counting under Adverse Earth Observation Conditions
日本大学: 関与なし(対象大学)
- See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis
日本大学: 関与なし(対象大学)
- See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles
日本大学: 関与なし(対象大学)
- SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Grouping
日本大学: 関与なし(対象大学)
- SeeThrough3D: Occlusion Aware 3D Control in Text-to-Image Generation
日本大学: 関与なし(対象大学)
- SeeU: Seeing the Unseen World via 4D Dynamics-aware Generation
日本大学: 関与なし(対象大学)
- Seeing Beyond 8bits: Subjective and Objective Quality Assessment of HDR-UGC Videos
日本大学: 関与なし(対象大学)
- Seeing Beyond: Extrapolative Domain Adaptive Panoramic Segmentation
日本大学: 関与なし(対象大学)
- Seeing Both Sides: Towards Bidirectional Semantic Alignment for Open-Vocabulary Camouflaged Object Segmentation
日本大学: 関与なし(対象大学)
- Seeing Clearly, Reasoning Confidently: Plug-and-Play Remedies for Vision Language Model Blindness
日本大学: 関与なし(対象大学)
- Seeing Conversations: Communication Context Identification in Egocentric Video
日本大学: 関与なし(対象大学)
- Seeing Depth Through Frequency and Motion: A Progressive Training Paradigm for Monocular Depth Estimation
日本大学: 関与なし(対象大学)
- Seeing Motion Through Polarity for Event-based Action Recognition
日本大学: 関与なし(対象大学)
- Seeing Through Blur: Tackling Defocus in Spike-Based Imaging
日本大学: 関与なし(対象大学)
- Seeing Through Touch: Tactile-Driven Visual Localization of Material Regions
日本大学: 関与なし(対象大学)
- Seeing Through the Noise: Improving Infrared Small Target Detection and Segmentation from Noise Suppression Perspective
日本大学: 関与なし(対象大学)
- Seeing Through the Shift: Causality-Inspired Robust Generalized Category Discovery
日本大学: 関与なし(対象大学)
- Seeing What Matters: A Training-Free Self-Guided Framework for Multimodal Detail Perception and Reasoning
日本大学: 関与なし(対象大学)
- Seeing What Matters: Visual Preference Policy Optimization for Visual Generation
日本大学: 関与なし(対象大学)
- Seeing as Experts Do: A Knowledge-Augmented Agent for Open-Set Fine-Grained Visual Understanding
日本大学: 関与なし(対象大学)
- Seeing is Improving: Visual Feedback for Iterative Text Layout Refinement
日本大学: 関与なし(対象大学)
- Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark
日本大学: 関与なし(対象大学)
- Seeing through Light and Darkness: Sensor-Physics Grounded Deblurring HDR NeRF from Single-Exposure Images and Events
日本大学: 関与なし(対象大学)
- Seeing through boxes: Non-Line-of-Sight 3D Reconstruction from Radar Signals
日本大学: 関与なし(対象大学)
- Seeing without Pixels: Perception from Camera Trajectories
日本大学: 関与なし(対象大学)
- Seele: A Unified Acceleration Framework for Real-Time Gaussian Splatting on Mobile Devices
日本大学: 関与なし(対象大学)
- SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentation
日本大学: 関与なし(対象大学)
- SegEarth-R2: Towards Comprehensive Language-guided Segmentation for Remote Sensing Images
日本大学: 関与なし(対象大学)
- SegGBC: Justifiable Coarse-to-Fine Granular-Ball Computing for Enhancing Clustering Image Segmentation
日本大学: 関与なし(対象大学)
- SegMo: Co-Designing Content-Aware Sparsity and Locally-Cohesive Segment Parallelism for Efficient VLM Inference
日本大学: 関与なし(対象大学)
- SegMoTE: Token-Level Mixture of Experts for Medical Image Segmentation
日本大学: 関与なし(対象大学)
- SegQuant: A Semantics-Aware and Generalizable Quantization Framework for Diffusion Models
日本大学: 関与なし(対象大学)
- SelecTKD: Selective Token-Weighted Knowledge Distillation for LLMs
日本大学: 関与なし(対象大学)
- Select Less, Reason More: Prioritizing Evidence Purity for Video Reasoning
日本大学: 関与なし(対象大学)
- Select, Hypothesize and Verify: Towards Verified Neuron Concept Interpretation
日本大学: 関与なし(対象大学)
- Selection-as-Nonlinearity: Bridging Attention and Activation via a Joint Game-Decision Lens for Interpretable, Discriminative Visual Representations
日本大学: 関与なし(対象大学)
- Selective Amnesia using Contrastive Subnet Erasure for Class Level Unlearning in Vision Models
日本大学: 関与なし(対象大学)
- Selective, Regularized, and Calibrated: Harnessing Vision Foundation Models for Cross-Domain Few-Shot Semantic Segmentation
日本大学: 関与なし(対象大学)
- Selectively Extracting and Injecting Visual Attributes into Text-to-Image Models
日本大学: 関与なし(対象大学)
- Self-Attention Driven Tensor Representation for High-Order Data Recovery
日本大学: 関与なし(対象大学)
- Self-Consistency for LLM-Based Motion Trajectory Generation and Verification
日本大学: 関与なし(対象大学)
- Self-Corrected Image Generation with Explainable Latent Rewards
日本大学: 関与なし(対象大学)
- Self-Critical Distillation Network for Video-based Commonsense Captioning
日本大学: 関与なし(対象大学)
- Self-Diffusion Driven Blind Imaging
日本大学: 関与なし(対象大学)
- Self-Evaluation Unlocks Any-Step Text-to-Image Generation
日本大学: 関与なし(対象大学)
- Self-Paced and Self-Corrective Masked Prediction for Movie Trailer Generation
日本大学: 関与なし(対象大学)
- Self-guided Semantic Inspection for Zero-Shot Composed Image Retrieval
日本大学: 関与なし(対象大学)
- Self-supervised Dynamic Heterogeneous Degradation Modeling for Unified Zero-Shot Image Restoration
日本大学: 関与なし(対象大学)
- SelfHVD: Self-Supervised Handheld Video Deblurring
日本大学: 関与なし(対象大学)
- Selfi: Self-improving Reconstruction Engine via 3D Geometric Feature Alignment
日本大学: 関与なし(対象大学)
- SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detection
日本大学: 関与なし(対象大学)
- SemLayer: Semantic-aware Generative Segmentation and Layer Construction for Abstract Icons
日本大学: 関与なし(対象大学)
- SemVideo: Reconstructs What You Watch from Brain Activity via Hierarchical Semantic Guidance
日本大学: 関与なし(対象大学)
- Semantic Alignment for Pose-Invariant Identity Preserving Diffusion
日本大学: 関与なし(対象大学)
- Semantic Audio-Visual Navigation in Continuous Environments
日本大学: 関与なし(対象大学)
- Semantic Context Matters: Improving Conditioning for Autoregressive Models
日本大学: 関与なし(対象大学)
- Semantic Derivative Flow: Graph-Guided Diffusion for Controllable Instance Interactions
日本大学: 関与なし(対象大学)
- Semantic Foam: Unifying Spatial and Semantic Scene Decomposition
日本大学: 関与なし(対象大学)
- Semantic Noise Reduction via Teacher-Guided Dual-Path Audio-Visual Representation Learning
日本大学: 関与なし(対象大学)
- Semantic Scale Space: A Framework for Controllable Image Abstraction
日本大学: 関与なし(対象大学)
- Semantic-Adaptive Diffusion for Dynamic Spatiotemporal Fusion
日本大学: 関与なし(対象大学)
- Semantic-Guided Global-Local Collaborative Prompt Learning for Few-Shot Class Incremental Learning
日本大学: 関与なし(対象大学)
- SemanticVLA: Towards Semantic Reasoning over Action Memorization via Synergistic Explicit Trace and Latent Action Planning
日本大学: 関与なし(対象大学)
- Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion
日本大学: 関与なし(対象大学)
- Semi-Supervised Conformal Prediction With Unlabeled Nonconformity Score
日本大学: 関与なし(対象大学)
- Semi-supervised Echocardiography Video Segmentation via Anchor Semantic Awareness and Continuous Pseudo-label Reforging
日本大学: 関与なし(対象大学)
- SemiGDA: Generative Dual-distribution Alignment for Semi-Supervised Medical Image Segmentation
日本大学: 関与なし(対象大学)