Computer Vision - ECCV 2026

MedCAGD: Context-Aware Gated Decoder for Robust Medical Image Segmentation.- ECoSim: Data Efficient Fine-Tuning for Controllable Traffic Simulation.- OccDirector: Language-Guided Behavior and Interaction Generation in 4D Occupancy Space.- Leveraging Dark Knowledge for Intrinsic Multimodal Out-of-Distribution Detection.- Direct Autoregressive Diffusion Distillation via Error-aware Causal Pretraining.- Moving Beyond More Views: Redundancy-Aware Ego–Exo Fusion for Proficiency Estimation.- Efficient Document Tampering Localization with Multi-Level Discrepancy Features and Unified DCT–Quantization Embedding.- Data-Free Client Contribution Estimation via Logit Maximization for Federated Learning.- StructPolicy: Structure-Guided Imitation Learning Robust to Visual Domain Shifts.- Task-Agnostic Incremental Vision-Language Object Detection via Prompt Augmentation and Distribution-Aware Fusion.- Test-time Counterfactual Calibration for Hallucination-Resistant Temporal Grounding.- Whence the Voice? Self-supervised Dual-source Audio-Visual Localisation via Selective Convergence.- CLIMP: Contrastive Language-Image Mamba Pretraining.- DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space.- EchoStyle: Unlocking High-Fidelity Video Stylization with Reverse Data Synthesis.- Rolling Shutter Relative Pose Estimation Made Practical.- FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs.- CollectionLoRA: Collecting 50 Effects in 1 LoRA for Deployment.- MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots.- Adversarial Score Distillation for Stable One-Step Diffusion in Real-World Image Super-Resolution.- MediRound: Multi-Round Entity-Level Reasoning Segmentation in Medical Images.- Zero-Shot Novel Depth Synthesis Using Foundation Models Scene Representations.- Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning.- MirrorPPR: Exemplar-Based Portrait Photo Retouching.- Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning.- VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model.- The Cost of Reasoning: Chain-of-Thought Induces Overconfidence in Vision-Language Models.- UniFusion: Sparse-View 4D Reconstruction via Unified Spatio-temporal Depth Alignment.- Dual-Margin Embedding for Fine-Grained Long-Tailed Plant Taxonomy.- Noise is a Good Teacher: A Noise-Driven Framework for Robust Collaborative Perception.- WildWorld: A Large-Scale Dataset for Action-Conditioned World Modeling with Explicit State Annotations.- Compact Low-Cost Hyperspectral Imaging via Angular-to-Spectral Diversity Conversion.- VLA Knows Its Limits.- Foundation Model Selection for Remote Sensing via a Constraint-Aware Agent.- EgoTraj: Real-World Egocentric Human Trajectory.- CaRe: Critical Parameter Rectification for Efficient Visual Modeling.- Learning with Bilevel-Minimax Optimization for Efficient and Reliable Transfer Attacks.

• Erscheinungsdatum: 10.09.2026
• Autor/Autorin: Paolo Favaro
• Format: E-Book
• Dateiformat: PDF
• Kopierschutz: Wasserzeichen
• Dateigröße: 170.7 MB
• Verlag: SPRINGER
• Sprache: Englisch
• Umfang: 705 Seiten
• ISBN: 9783032371966
• Lieferung: Sofort per Download
• Hinweis: Sofort per Download lieferbar. Kein physischer Versand.
• Kompatibilität: Lesbar auf Geräten und Apps mit PDF-Unterstützung.