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。
- Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors
日本大学: 関与なし(対象大学)
- Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models
日本大学: 関与なし(対象大学)
- Towards Reliable Evaluation of Adversarial Robustness for Spiking Neural Networks
日本大学: 関与なし(対象大学)
- Towards Robust Multi-Modal Semantic Segmentation with Teacher-Student Framework and Hybrid Prototype Distillation
日本大学: 関与なし(対象大学)
- Towards Robust Multimodal Large Language Models Against Jailbreak Attacks
日本大学: 関与なし(対象大学)
- Towards Robust Sequential Decomposition for Complex Image Editing
日本大学: 東京大学
- Towards Robust Vision Transformers: Path Dependency Analysis and a Simple Two-Stage Adversarial Training
日本大学: 関与なし(対象大学)
- Towards Sparse Video Understanding and Reasoning
日本大学: 関与なし(対象大学)
- Towards Stable Federated Continual Test-Time Adaptation in Wild World
日本大学: 関与なし(対象大学)
- Towards Stable Self-Supervised Object Representations in Unconstrained Egocentric Video
日本大学: 関与なし(対象大学)
- Towards Stealthy and Effective Backdoor Attacks on Lane Detection: A Naturalistic Data Poisoning Approach
日本大学: 関与なし(対象大学)
- Towards Storytelling Animations: Joint Synthesis of Human and Camera Motions
日本大学: 関与なし(対象大学)
- Towards Streaming Referring Video Segmentation via Large Language Model
日本大学: 関与なし(対象大学)
- Towards Training-free Scene Text Editing
日本大学: 関与なし(対象大学)
- Towards Uncertainty-aware Unsupervised Domain Adaptation for Videos and Time-Series with Causal Optimal Transport
日本大学: 関与なし(対象大学)
- Towards Unified Human Perception and Machine Understanding: Token Flow Guided Compression Framework
日本大学: 関与なし(対象大学)
- Towards Universal Computational Aberration Correction in Photographic Cameras: A Comprehensive Benchmark Analysis
日本大学: 関与なし(対象大学)
- Towards Visual Query Localization in the 3D World
日本大学: 関与なし(対象大学)
- Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspective
日本大学: 関与なし(対象大学)
- TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos
日本大学: 関与なし(対象大学)
- TrackMAE: Video Representation Learning via Track Mask and Predict
日本大学: 関与なし(対象大学)
- Tracking by Predicting 3-D Gaussians Over Time
日本大学: 関与なし(対象大学)
- Tracking through Severe Occlusion via Event-Derived Transient Cues
日本大学: 関与なし(対象大学)
- Tracking-Guided 4D Generation: Foundation-Tracker Motion Priors for 3D Model Animation
日本大学: 関与なし(対象大学)
- TrafficAlign: Aligning Large Language Models for Traffic Scenario Generation
日本大学: 関与なし(対象大学)
- Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers
日本大学: 関与なし(対象大学)
- Training High-Level Schedulers with Execution-Feedback Reinforcement Learning for Long-Horizon GUI Automation
日本大学: 関与なし(対象大学)
- Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning
日本大学: 関与なし(対象大学)
- Training-Free Open-Vocabulary Camouflaged Object Segmentation via Fine-Grained Object Binding and Adaptive Hybrid Prompt
日本大学: 関与なし(対象大学)
- Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adapters
日本大学: 関与なし(対象大学)
- Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods
日本大学: 関与なし(対象大学)
- Training-free Mixed-Resolution Latent Upsampling for Spatially Accelerated Diffusion Transformers
日本大学: 関与なし(対象大学)
- Training-free Motion Factorization for Compositional Video Generation
日本大学: 関与なし(対象大学)
- Training-free, Perceptually Consistent Low-Resolution Previews with High-Resolution Image for Efficient Workflows of Diffusion Models
日本大学: 関与なし(対象大学)
- TrajRAG: Retrieving Geometric-Semantic Experience for Zero-Shot Object Navigation
日本大学: 関与なし(対象大学)
- TransPrune: Token Transition Pruning for Efficient Large Vision-Language Model
日本大学: 関与なし(対象大学)
- Transform to Transfer: Boosting Adversarial Attack Transferability on Vision-Language Pre-training Models
日本大学: 関与なし(対象大学)
- Transition Matching Distillation for Fast Video Generation
日本大学: 関与なし(対象大学)
- Transition Models: Rethinking the Generative Learning Objective
日本大学: 関与なし(対象大学)
- Translating Signals to Languages for sEMG-Based Activity Recognition
日本大学: 関与なし(対象大学)
- TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration
日本大学: 関与なし(対象大学)
- Tri-Modal Fusion Transformers for UAV-based Object Detection
日本大学: 関与なし(対象大学)
- Tri-Subspaces Disentanglement for Multimodal Sentiment Analysis
日本大学: 関与なし(対象大学)
- TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection
日本大学: 関与なし(対象大学)
- TriLite: Efficient Weakly Supervised Object Localization with Universal Visual Features and Tri-Region Disentanglement
日本大学: 関与なし(対象大学)
- TriSim: Tri-Dimensional Similarity Modeling with Extreme Value Theory for False-Negative Mitigation in Remote Sensing Image-Text Retrieval
日本大学: 関与なし(対象大学)
- TruckDrive: Long-Range Autonomous Highway Driving Dataset
日本大学: 関与なし(対象大学)
- Trust-calibrated Collaborative Learning for Long-Tailed Visual Recognition
日本大学: 関与なし(対象大学)
- Tunable Soft Equivariance with Guarantees
日本大学: 関与なし(対象大学)
- Turbo-GS: Accelerating 3D Gaussian Fitting for High-Resolution Radiance Fields
日本大学: 関与なし(対象大学)
- Turning Pre-Trained Vision Transformers into End-to-End Histopathology Whole Slide Image Models for Survival Prediction
日本大学: 関与なし(対象大学)
- Tutor-Student Reinforcement Learning: A Dynamic Curriculum for Robust Deepfake Detection
日本大学: 関与なし(対象大学)
- Twin-T & TwintVQA: A Reliable Structure-Detail Separating VLM and a Comprehensive Benchmark for Chart and Table Tasks
日本大学: 関与なし(対象大学)
- U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation
日本大学: 関与なし(対象大学)
- U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences
日本大学: 関与なし(対象大学)
- UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement
日本大学: 関与なし(対象大学)
- UAST: Unified Active Search and Tracking for Arbitrary Targets with UAVs
日本大学: 関与なし(対象大学)
- UAV-CB: A Complex-Background RGB-T Dataset and Local Frequency Bridge Network for UAV Detection
日本大学: 関与なし(対象大学)
- UAVLight: A Benchmark for Illumination-Robust 3D Reconstruction in Unmanned Aerial Vehicle (UAV) Scenes
日本大学: 関与なし(対象大学)
- UCAN: Unified Convolutional Attention Network for Expansive Receptive Fields in Lightweight Super-Resolution
日本大学: 関与なし(対象大学)
- UCMNet: Uncertainty-Aware Context Memory Network for Under-Display Camera Image Restoration
日本大学: 関与なし(対象大学)
- UDAPose: Unsupervised Domain Adaptation for Low-Light Human Pose Estimation
日本大学: 関与なし(対象大学)
- UETrack: A Unified and Efficient Framework for Single Object Tracking
日本大学: 関与なし(対象大学)
- UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling
日本大学: 関与なし(対象大学)
- UFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models
日本大学: 関与なし(対象大学)
- UI-Lens: Assessing General MLLMs' Potential to Automate UI Display Quality Assurance
日本大学: 関与なし(対象大学)
- UIKA: Fast Universal Head Avatar from Pose-Free Images
日本大学: 関与なし(対象大学)
- ULF-Loc: Unbiased Landmark Feature for Robust Visual Localization with 3D Gaussian Splatting
日本大学: 関与なし(対象大学)
- UNI-OOD: Unified Object- and Image-level Out-of-Distribution Detection via Cross-Context Attentive Vision-Language Modeling
日本大学: 関与なし(対象大学)
- UNICBench: UNIfied Counting Benchmark for MLLM
日本大学: 関与なし(対象大学)
- UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders
日本大学: 関与なし(対象大学)
- URICA: A Uniformity Region Affine Identifier Capture Algorithm for Arbitrary Region Retrieval in Pathology Images
日本大学: 関与なし(対象大学)
- URScenes: A Multi-scenario Dataset for Unstructured Road Environments
日本大学: 関与なし(対象大学)
- UST-Hand: An Uncertainty-aware Spatiotemporal Point Cloud Interaction Network for 3D Self-supervised Hand Pose Estimation
日本大学: 関与なし(対象大学)
- UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking
日本大学: 関与なし(対象大学)
- UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm
日本大学: 関与なし(対象大学)
- UZ3DVG: Unaided Zero-Shot 3D Visual Grounding with Generated Language Conditions
日本大学: 関与なし(対象大学)
- U^2Flow: Uncertainty-Aware Unsupervised Optical Flow Estimation
日本大学: 関与なし(対象大学)
- Ultra Diffusion Poser: Diffusion-Based Human Motion Tracking from Sparse Inertial Sensors and Ranging-based Between-sensor Distances
日本大学: 関与なし(対象大学)
- Ultra-Fast Neural Video Compression
日本大学: 関与なし(対象大学)
- Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoder
日本大学: 関与なし(対象大学)
- UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios
日本大学: 関与なし(対象大学)
- Ultrasound-CLIP: Semantic-Aware Contrastive Pre-training for Ultrasound Image-Text Understanding
日本大学: 関与なし(対象大学)
- UnReflectAnything: RGB-Only Highlight Removal by Rendering Synthetic Specular Supervision
日本大学: 関与なし(対象大学)
- Unblur-SLAM: Dense Neural SLAM for Blurry Inputs
日本大学: 関与なし(対象大学)
- Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Models
日本大学: 関与なし(対象大学)
- Uncertainty-Aware Knowledge Distillation for Multimodal Large Language Models
日本大学: 関与なし(対象大学)
- Uncertainty-Aware Modality Fusion for Unaligned RGB-T Salient Object Detection
日本大学: 関与なし(対象大学)
- Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Field
日本大学: 関与なし(対象大学)
- Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models
日本大学: 関与なし(対象大学)
- Underground Plant Exploration: Non-Destructive 3D Root Assessment with GPR Based on Point Graph Neural Network
日本大学: 関与なし(対象大学)
- Understanding Counting Mechanisms in Large Language and Vision-Language Models
日本大学: 関与なし(対象大学)
- Understanding Task Transfer in Vision-Language Models
日本大学: 関与なし(対象大学)
- Understanding Temporal Logic Consistency in Video-Language Models through Cross-Modal Attention Discriminability
日本大学: 関与なし(対象大学)
- Understanding and Enforcing Weight Disentanglement in Task Arithmetic
日本大学: 関与なし(対象大学)
- Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Models
日本大学: 関与なし(対象大学)
- Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models
日本大学: 関与なし(対象大学)
- Understanding, Accelerating, and Improving MeanFlow Training
日本大学: 関与なし(対象大学)
- Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation
日本大学: 関与なし(対象大学)
- Uni-Encoder Meets Multi-Encoders: Representation Before Fusion for Brain Tumor Segmentation with Missing Modalities
日本大学: 東京大学