Na FER-u postoji više zaposlenika s imenom
MC-PanDA: Mask Confidence for Panoptic Domain Adaptation
Backdoor Defense through Self-Supervised and Generative Learning
Quantile-Based Maximum Likelihood Training for Outlier Detection
Quantile-Based Maximum Likelihood Training for Outlier Detection
Dense Out-of-Distribution Detection by Robust Learning on Synthetic Negative Data
Hybrid Open-set Segmentation with Synthetic Negative Data
Weakly Supervised Training of Universal Visual Concepts for Multi-domain Semantic Segmentation
Outlier detection by ensembling uncertainty with negative objectness
Dynamic Loss Balancing and Sequential Enhancement for Road-Safety Assessment and Traffic Scene Classification
Hybrid Open-Set Segmentation With Synthetic Negative Data
Identifying Label Errors in Object Detection Datasets by Loss Inspection
Panoptic SwiftNet: Pyramidal Fusion for Real-Time Panoptic Segmentation
Revisiting Consistency for Semi-Supervised Semantic Segmentation
Normalizing Flow based Feature Synthesis for Outlier-Aware Object Detection
On Advantages of Mask-level Recognition for Outlier-aware Segmentation
Applications of generative approaches for artificial intelligence
Dense open-set recognition based on training with noisy negative images
Automatic universal taxonomies for multi-domain semantic segmentation
Združeno prognoziranje značajki i njihova pomaka za predviđanje semantičke budućnosti u videu
Dense Semantic Forecasting with Multi-Level Feature Warping
Multi-domain semantic segmentation with overlapping labels
The chirality of the mitotic spindle provides a mechanical response to forces and depends on microtubule motors and augmin
DenseHybrid: Hybrid Anomaly Detection for Dense Open-Set Recognition
Dense open-set recognition with synthetic outliers generated by Real NVP
A baseline for semi-supervised learning of efficient semantic segmentation models
Densely connected normalizing flows
Convolutional architecture for efficient semantic segmentation of large images
Efficient semantic segmentation with pyramidal fusion
Efficient semantic image segmentation using pyramidal fusion
Elements of Learning Algorithms for Natural Scene Understanding
Dense Semantic Forecasting in Video by Joint Regression of Features and Feature Motion
Centar izvrsnosti za računalni vid
Detekcija izvandistribucijskih dijelova slike primjenom generativnih modela
Efficient Ladder-Style DenseNets for Semantic Segmentation of Large Images
Perceptual Autoencoder for Compressive Sensing Image Reconstruction
Multimodal semantic forecasting based on conditional generation of future features
Traffic Scene Classification on a Representation Budget
Multi-Task Learning for iRAP Attribute Classification and Road Safety Assessment
Multi-domain semantic segmentation with pyramidal fusion
Warp to the Future: Joint Forecasting of Features and Feature Motion
Convolutional models for image understanding
Lightweight convolutional models for real-time dense prediction and forecasting
Improving fleet management systems by computer vision
In Defense of Pre-Trained ImageNet Architectures for Real-Time Semantic Segmentation of Road-Driving Images
Pedestrian Tracking by Probabilistic Data Association and Correspondence Embeddings
Single Level Feature-to-Feature Forecasting with Deformable Convolutions
Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shift
Natural image understanding: principles, challenges and research outlook
Convolutional Models for Segmentation and Localization
Sparse weakly supervised models for object localization in road environment
Ladder-style DenseNets for Semantic Segmentation of Large Natural Images
Bottom-up object localization with Fisher vectors
Patch-level Spatial Layout for Classification and Weakly Supervised Localization
Convolutional Scale Invariance for Semantic Segmentation
Weakly-Supervised Semantic Segmentation by Redistributing Region Scores Back to the Pixels
Python za znatiželjne
Improving the Egomotion Estimation by Correcting the Calibration Bias
Weakly Supervised Object Localization with Large Fisher Vectors
Weakly Supervised Object Localization, Fisher Vectors, Sparse Classification Models.
Robust Traffic Scene Recognition with a Limited Descriptor Length
Fast Approximate GMM Soft-Assign for Fine-Grained Image Classification with Large Fisher Vectors
Detekcija prisutnosti vozila ugrađenim računalom
Temporal Ensemble of Shape Functions
Image Representations on a Budget: Traffic Scene Classification in a Restricted Bandwidth Scenario
Multi-Label Classification of Traffic Scenes
Convolutional Neural Networks for Croatian Traffic Signs Recognition
Recognizing 3D Objects from a Limited Number of Views using Temporal Ensembles of Shape Functions
Experimental Evaluation of Vehicle Detection Based on Background Modelling in Daytime and Night-Time Video
Exploiting temporal and spatial constraints in traffic sign detection from a moving vehicle
Combining Spatio-Temporal Appearance Descriptors and Optical Flow for Human Action Recognition in Video Data
Classifying Traffic Scenes Using The GIST Image Descriptor
Multiclass Road Sign Detection using Multiplicative Kernel
A Novel Georeferenced Dataset for Stereo Visual Odometry
Napredno estimiranje strukture i gibanja kalibriranim parom kamera
Sliding Window Object Detection without Spatial Clustering of Raw Detection Responses
Towards Space-Time Semantics in Two Frames
Estimating OD matrices at intersections in airborne video - a pilot study
Strojno očitanje natpisa na prometnim znakovima
Preliminary experiments in multi-view video stitching
Detecting and recognizing centerlines as parabolic sections of the steerable filter response
Using GPS positioning to recover a comprehensive road appearance mosaic
Recent advances in traffic sign detection
Histogram-Based Description of Local Space-Time Appearance
Addressing false alarms and localization inaccuracy in traffic sign detection and recognition
Experimental Evaluation of Autonomous Driving Based on Visual Memory and Image Based Visual Servoing
A computer vision assisted geoinformation inventory for traffic infrastructure
Generative modeling of spatio-temporal traffic sign trajectories
Recovering a comprehensive road appearance mosaic from video
Streamlining collection of training samples for object detection and classification in video
A mapping and localization framework for scalable appearance-based navigation
Towards automatic assessment and mapping of traffic infrastructure by adding vision capabilities to a geoinformation inventory
Traffic sign detection as a component of an automated traffic infrastructure inventory system
Online/Realtime Structure and Motion for General Camera Models
A Framework for Scalable Vision-Only Navigation
Performance evaluation of the five-point relative pose with emphasis on planar scenes
Large scale vision based navigation without an accurate global reconstruction
Outdoor Visual Path Following Experiments
Influence of the numerical conditioning to the accuracy of relative orientation
Experimental evaluation of an urban visual path following framework
Enhancing the Point Feature Tracker by Adaptive Modelling of the Feature Support
A Multimodal Image Registration Technique for Structured Polygonal Scenes
Real-time Active Visual Tracking System
Višeagentsko praćenje objekata aktivnim računarskim vidom
A Software Architecture for Distributed Visual Tracking in a Global Vision Localization System
Detecting Salient Curvature Features Using the Local Control of the Feature Support
Determining the absolute orientation in a corridor using projective geometry and active vision
Extracting the Canonical Set of Closed Contours Using the Best-First Search Algorithm
A Software Architecture for Image Acquisition and Camera Control in an Active Vision System
Locally adaptive thresholding of the sequence of image frames
Uporaba projekcijske geometrije i aktivnog vida u tumačenju scena
Self-localisation procedure for autonomous navigation through corridors
Using vanishing points for purposive adjustment of viewing direction
Segmentacija u stvarnom vremenu uporabom dinamičkog uspoređivanja s lokalno prilagodljivim pragom
Robust Extraction of Line Segments from Colour Images by an Iterative Weighted Polarised Hough Transform
Nastava
Sveučilišni preddiplomski
- Arhitektura računala 2 (Nositelj, Nositelj)
- Arhitektura računala 2 (Nositelj)
- Oblikovni obrasci u programiranju (Nositelj, Nositelj)
- Oblikovni obrasci u programiranju (Nositelj)
- Skriptni jezici (Nositelj, Nositelj)
- Skriptni jezici (Nositelj)
- Projekt iz programske potpore (Predavanja)
- Projekt iz programske potpore (Predavanja)
- Projekt iz programske potpore (Predavanja)
- Projekt R (Predavanja)
- Završni rad (Predavanja)
- Završni rad (Predavanja)
- Završni rad (Predavanja)
Sveučilišni diplomski
- Duboko učenje 1 (Nositelj)
- Duboko učenje 1 (Nositelj)
- Programiranje na visokoj razini apstrakcije (Nositelj)
- Računalni vid (Nositelj)
- Trodimenzionalni računalni vid (Nositelj)
- Diplomski projekt (Predavanja)
- Diplomski projekt (Predavanja)
- Diplomski projekt (Predavanja)
- Diplomski rad (Predavanja)
- Istraživački seminar (Predavanja)
- Projekt (Predavanja)
- Seminar 1 (Predavanja)
- Seminar 2 (Predavanja)
Poslijediplomski doktorski
- Analiza dinamičkih scena (Nositelj)
- Modeli za predstavljanje slike i videa (Nositelj)
Kompetencije
-
Computational and artificial intelligence
Artificial intelligence Cognitive systems Autonomous systems Learning (artificial intelligence) Distance learning Semisupervised learning Supervised learning Machine learning Probabilistic logic Machine intelligence Pattern analysis -
Computational and artificial intelligence
Artificial intelligence Cognitive systems Autonomous systems Learning (artificial intelligence) Distance learning Semisupervised learning Supervised learning Machine learning Probabilistic logic Machine intelligence Pattern analysis