Danijel Skočaj

7 papers · 2021–2026 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze

Venues

ECCV (2) ICCV (2) WACV (2) CVPR (1)

Top co-authors

Vitjan Zavrtanik (7) Matic Fučka (4) Matej Kristan (3)

Research topics

Computer Vision (5) Analysis (5) Machine Learning (2) Core Methods (2) Deep Learning (1) Domain-Specific (1) Learning Types · Deep Learning (1) Learning Types · Machine Learning (1) Models (1)

Keywords

logical anomaly detection (2) anomaly detection (1) bipartite matching (1) depth estimation (1) 3d vision (1) synthetic data generation (1) generative model (1) vision foundation model (1) parameter-efficient adaptation (1) 3d anomaly detection (1) discriminative model (1) low-rank adapter (1) semantic relationship (1) discrete autoencoder (1) surface defect detection (1) zero-shot anomaly detection (1) anomaly localization (1) pretrained feature (1) object representation (1) composition information (1)

Papers

AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors CVPR 2026 ObjectCore - Efficient Few-shot Logical Anomaly Detection using Object Representations WACV 2026 SALAD -- Semantics-Aware Logical Anomaly Detection ICCV 2025 Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulation WACV 2024 TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection ECCV 2024 DSR – A Dual Subspace Re-Projection Network for Surface Anomaly Detection ECCV 2022 DRAEM - A Discriminatively Trained Reconstruction Embedding for Surface Anomaly Detection ICCV 2021