PristupačnostNa FER-u postoji više zaposlenika s imenom
Weakly Supervised Training of Universal Visual Concepts for Multi-domain Semantic Segmentation
MC-PanDA: Mask Confidence for Panoptic Domain Adaptation
Panoptic SwiftNet: Pyramidal Fusion for Real-Time Panoptic Segmentation
On Advantages of Mask-level Recognition for Outlier-aware Segmentation
Združeno prognoziranje značajki i njihova pomaka za predviđanje semantičke budućnosti u videu
Multi-domain semantic segmentation with overlapping labels
Dense Semantic Forecasting with Multi-Level Feature Warping
Dense Semantic Forecasting in Video by Joint Regression of Features and Feature Motion
Multi-domain semantic segmentation with pyramidal fusion
Multimodal semantic forecasting based on conditional generation of future features
Warp to the Future: Joint Forecasting of Features and Feature Motion
Single Level Feature-to-Feature Forecasting with Deformable Convolutions
Usmjeravanje u programski upravljanoj mreži zasnovano na heurističkoj funkciji puta
Nastava
Sveučilišni preddiplomski
- Oblikovni obrasci u programiranju (Auditorne vježbe, Laboratorijske vježbe, Auditorne vježbe, Laboratorijske vježbe)
- Arhitektura računala 2 (Laboratorijske vježbe, Laboratorijske vježbe)
Sveučilišni diplomski
- Duboko učenje 1 (Laboratorijske vježbe)
Kompetencije
-
Computational and artificial intelligence
Artificial intelligence Autonomous systems Learning (artificial intelligence) Backpropagation Semisupervised learning Supervised learning Unsupervised learning Machine learning Machine intelligence Pattern analysis Neural networks Feedforward neural networks Multi-layer neural network -
Robotics and automation
Computer vision