Conferences · eligible papers
ECCV
2022–2026 LIVE
2026 · 2,834 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。
- FedDO: Dynamic Client Optimization for Adaptive Federated Learning
日本大学: 関与なし(対象大学)
- FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration
日本大学: 関与なし(対象大学)
- FedMental: Topology-Aware Federated Prototype Learning for Polymorphic Multimodal Psychiatry
日本大学: 関与なし(対象大学)
- FedNASP: Federated Vision-Language Navigation with Adaptive Step-wise Personalization
日本大学: 関与なし(対象大学)
- FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs
日本大学: 東京大学
- Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples
日本大学: 関与なし(対象大学)
- Fidelity- and Perception-Aware Local Implicit Attention for Arbitrary-Scale Image Super-Resolution
日本大学: 関与なし(対象大学)
- Fill2SR: Repurposing Inpainting Diffusion Transformers for Real-World Super-Resolution
日本大学: 関与なし(対象大学)
- FillGS: Filling Observation Gaps in 4D Gaussian Splatting via Viewpoint-Time Selection and Generative Refinement
日本大学: 東京大学
- Filterless Snapshot Hyperspectral Imaging using Guided Patch Diffusion
日本大学: 関与なし(対象大学)
- Finding Highlight Images In Your Albums:From Benchmark To MLLM
日本大学: 関与なし(対象大学)
- FindingDory: A Benchmark to Evaluate Memory in Embodied Agents
日本大学: 関与なし(対象大学)
- Fine-Grained Text-to-Video Retrieval for Camera-Trap Data
日本大学: 関与なし(対象大学)
- FineEdit: Fine-Grained Image Edit with Bounding Box Guidance
日本大学: 関与なし(対象大学)
- FingerCap: Fine-grained Finger-level Hand Motion Captioning
日本大学: 関与なし(対象大学)
- Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models
日本大学: 関与なし(対象大学)
- Fisher-Routed Mixture of Experts for Federated Class-Incremental Learning
日本大学: 関与なし(対象大学)
- Fisheye3R: Adapting Unified 3D Feed-Forward Foundation Models to Fisheye Lenses
日本大学: 関与なし(対象大学)
- FitControler: Toward Fit-Aware Virtual Try-On
日本大学: 関与なし(対象大学)
- FixAnything: 3D-Consistent Rendering Refinement via Video Generative Priors
日本大学: 関与なし(対象大学)
- Fixed Reality, Diffused Possibility: Disentangling Stochastic and Deterministic Latent for Cluttered Grasping
日本大学: 関与なし(対象大学)
- Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models
日本大学: 関与なし(対象大学)
- Flash-DD: An Ultra Parameter-Efficient Approach to Dataset Distillation
日本大学: 関与なし(対象大学)
- Flash-Refine: Frustum-Guided Local Incremental Learning for Efficient 3D Gaussian Splatting Completion
日本大学: 関与なし(対象大学)
- FlashBEV: Fast and Memory-Efficient Exact BEV Transformation with IO-Awareness
日本大学: 早稲田大学
- FlashVLM: Text-Guided Visual Token Selection for Large Multimodal Models
日本大学: 関与なし(対象大学)
- FlexAM: Flexible Appearance-Motion Decomposition for Versatile Video Generation Control
日本大学: 関与なし(対象大学)
- FlexComposer: Unified Video Compositing from Images to Dynamic Footage with Flexible Trajectory Control
日本大学: 関与なし(対象大学)
- FlexiAvatar: Unified 3D Gaussian Human Avatars Under Arbitrary Body Visibility
日本大学: 関与なし(対象大学)
- FlexiBrain: Resolution-Agnostic Voxel-Level Encoding for Native fMRI
日本大学: 関与なし(対象大学)
- Flexible Control of 3D CT Generation via Text and Semantically-Defined Segmentation Prompts
日本大学: 関与なし(対象大学)
- Flow Straight to Reality: Perceptually Consistent Flow Matching for Efficient Image Restoration
日本大学: 関与なし(対象大学)
- Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow
日本大学: 関与なし(対象大学)
- FlowCIR: Semantic Transport via Flow Matching for Zero-Shot Composed Image Retrieval
日本大学: 関与なし(対象大学)
- FlowDec: Temporal Conditional Flow Decorruptor for Robust Continuous Vision-Language Navigation
日本大学: 関与なし(対象大学)
- FlowFace: Rectifying Identity Conditioning with Riemannian Geometry for Face Generation
日本大学: 関与なし(対象大学)
- FlowInOne: Unifying Multimodal Generation as Image-in, Image-out Flow Matching
日本大学: 関与なし(対象大学)
- FlowLess: Controlling Abstract Image Generation
日本大学: 関与なし(対象大学)
- FlowPainter: Inpainting Optical Flow via Confidence-Guided Completion
日本大学: 関与なし(対象大学)
- FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation
日本大学: 関与なし(対象大学)
- Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning
日本大学: 関与なし(対象大学)
- Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoE
日本大学: 関与なし(対象大学)
- Follow-Your-Mind: Towards Inversion-Free Brain-Driven Visual Context Synthesis and Editing
日本大学: 関与なし(対象大学)
- Following Motion for Sequential Modeling in Video Frame Interpolation
日本大学: 関与なし(対象大学)
- Following the Flow: Advection-Consistent Modeling for Event-based Small Object Detection
日本大学: 関与なし(対象大学)
- FontCopilot: Towards Generalist Multimodal Large Language Models for Holistic Chinese Font Engineering
日本大学: 関与なし(対象大学)
- ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance
日本大学: 関与なし(対象大学)
- Forecasting Animal Motion
日本大学: 関与なし(対象大学)
- Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-View Videos
日本大学: 関与なし(対象大学)
- FoundDP: Revisiting Weak Disparity Observability in Dual-Pixel Depth Estimation
日本大学: 関与なし(対象大学)
- FoundYou: A Unified Model for Personalized Segmentation and Retrieval
日本大学: 関与なし(対象大学)
- Foundation Model Selection for Remote Sensing via a Constraint-Aware Agent
日本大学: 関与なし(対象大学)
- Foundation-Guided Representation Alignment for Multimodal Medical Image Registration
日本大学: 関与なし(対象大学)
- FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry
日本大学: 関与なし(対象大学)
- Fourier Compressor: Frequency-Domain Visual Token Compression for Vision-Language Models
日本大学: 関与なし(対象大学)
- Fourier Self-Supervision for Fine-Grained Generalized Category Discovery
日本大学: 関与なし(対象大学)
- Fourier Splatting: Generalized Fourier encoded primitives for scalable radiance fields
日本大学: 関与なし(対象大学)
- Foveated Reasoning: Stateful, Action-based Visual Focusing for Vision-Language Models
日本大学: 関与なし(対象大学)
- Fragmented Text Is Insufficient for Image Representation: Fine-Grained Correspondence in Multimodal Dataset Distillation
日本大学: 関与なし(対象大学)
- Frames2Residual: Spatiotemporal Decoupling for Self-Supervised Video Denoising
日本大学: 関与なし(対象大学)
- Free-Lunch Augmentation by Revisiting Diffusion-Based Data Generation for Cross-Domain Few-Shot Object Detection
日本大学: 関与なし(対象大学)
- Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction
日本大学: 関与なし(対象大学)
- FreeFlow: A Bias-free Hierarchical Transformer for Optical Flow Estimation
日本大学: 関与なし(対象大学)
- FreeGen: Feed-Forward Reconstruction–Generation Co-Training for Free-Viewpoint Driving Scene Synthesis
日本大学: 関与なし(対象大学)
- FreeSwim: Revisiting Sliding-Window Attention Mechanisms for Training-Free Ultra-High-Resolution Video Generation
日本大学: 関与なし(対象大学)
- Free‑CD: Probabilistically Decoupled Training-Free Open-Vocabulary Change Detection with Resolution-Invariant Feature Inversion
日本大学: 関与なし(対象大学)
- FreqOrtho-SR: Frequency-Guided Orthogonal Expert Learning for Real-World Image Super-Resolution
日本大学: 関与なし(対象大学)
- FreqPhys: Repurposing Implicit Physiological Frequency Prior for Robust Remote Photoplethysmography
日本大学: 関与なし(対象大学)
- Freqformer: Image-Demoiréing Transformer via Effective Frequency Decomposition
日本大学: 関与なし(対象大学)
- Frequency Director: Learnable Mixture of Frequency Experts for Unified Concealed Scene Segmentation
日本大学: 関与なし(対象大学)
- From Blobs to Spokes: High-Fidelity Surface Reconstruction via Oriented Gaussians
日本大学: 関与なし(対象大学)
- From Draft to Draft-Free: One-Step Video Object Removal via Privileged Distillation and Fast Planting
日本大学: 関与なし(対象大学)
- From Drop-off to Recovery: A Mechanistic Analysis of Segmentation in MLLMs
日本大学: 関与なし(対象大学)
- From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for Video Generative Models
日本大学: 関与なし(対象大学)
- From Gaze to Meaning: An AI Agent for Unified Zero-Shot Grounding and Explanation
日本大学: 関与なし(対象大学)
- From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP
日本大学: 関与なし(対象大学)
- From Illusion to Intention: Visual Rationale Learning for Reliable Evidence Acquisition
日本大学: 関与なし(対象大学)
- From Local Geometry to Global Pseudo-Labeling for Robust Positive–Unlabeled Learning under Covariate Shift
日本大学: 関与なし(対象大学)
- From Local Windows to Adaptive Candidates via Individualized Exploratory: Rethinking Attention for Image Super-Resolution
日本大学: 関与なし(対象大学)
- From Local to Global: A Progressive Reconstruction Network for Diffractive Snapshot Spectral Imaging
日本大学: 関与なし(対象大学)
- From Macro to Micro: Benchmarking Microscopic Spatial Intelligence on Molecules via Vision-Language Models
日本大学: 関与なし(対象大学)
- From Masks to Pixels and Meaning: A New Taxonomy, Benchmark and Metrics for VLM Image Tampering
日本大学: 関与なし(対象大学)
- From Minimal Clinical Prompts to 3D: Spacing-Aware Prompt Propagation for Multimodal Prostate Lesion Segmentation in bpMRI
日本大学: 関与なし(対象大学)
- From Multi-Resolution Cells to Gigapixel Whole Slide Images Foundation Model for Computational Pathology
日本大学: 関与なし(対象大学)
- From Noise to Events: Conditional Diffusion for Event Data Augmentation
日本大学: 関与なし(対象大学)
- From One-to-One to Many-to-Many: Dynamic Cross-Layer Injection for Deep Vision-Language Fusion
日本大学: 関与なし(対象大学)
- From Open Loop to Closed Loop: A Test-Time Iterative Optimization Framework for Reference-Consistent Image Generation
日本大学: 関与なし(対象大学)
- From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation
日本大学: 関与なし(対象大学)
- From Perspective to Fisheye Depth Estimation and Open-Vocabulary Segmentation
日本大学: 関与なし(対象大学)
- From Phase to Phenomenon: Self-Supervised Learning of Subsurface Scattering with Minimal Phase-shift Inputs
日本大学: 関与なし(対象大学)
- From Predictions to Embeddings: Dual Knowledge Distillation for Instance-Dependent Partial Label Learning
日本大学: 関与なし(対象大学)
- From Reasoning to Pixels: Grounded Medical Multimodal LLMs for VQA and Segmentation
日本大学: 関与なし(対象大学)
- From Reconstruction to Decision: A Post-Encoder Plug-in Adapter for Curvilinear Segmentation
日本大学: 関与なし(対象大学)
- From Script to Shot: A Benchmark for Grounding Screenplays in Movies
日本大学: 関与なし(対象大学)
- From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space
日本大学: 関与なし(対象大学)
- From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation
日本大学: 関与なし(対象大学)
- From Visual Primitives to Semantic Masks: Fine-Grained Visual-Linguistic Alignment for Open-Vocabulary Remote Sensing Image Segmentation
日本大学: 関与なし(対象大学)
- From smooth to sharp: Frequency-Decoupled Latent Optimization for Realistic Image Generation
日本大学: 関与なし(対象大学)
- Frozen CLIP Priors for Robust Self-Supervised Poisson Inverse Problems
日本大学: 関与なし(対象大学)
- FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model
日本大学: 関与なし(対象大学)