Main Page
Visual Cognitive Systems Laboratory
University of Ljubljana
Faculty of Computer and Information Science
Večna pot 113
SI-1000 Ljubljana
Slovenia
tel.: +386 1 479 8245
About laboratory
The Visual Cognitive Systems Laboratory is involved in basic and applied research of visually enabled intelligent systems addressing various research problems from the fields of computer vision, (deep) machine learning, and cognitive robotics.
The main research tasks include visual object tracking, detection, categorization, and segmentation, applied to various applications such as visual inspection for quality control, visual surveillance, and robot navigation.
News
April 2021 - Mixed supervision for surface-defect detection: from weakly to fully supervised learning published in journal Computers in Industry, 2021.
April 2021 - New dataset for industrial surface defect detection published - KolektorSDD2.
June 2020 - End-to-end training of a two-stage neural network for defect detection accepted to ICPR 2020.
February 2020 - D3S - A Discriminative Single Shot Segmentation Tracker accepted to CVPR 2020.
January 2020 - Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural Networks published in International Journal of Computer Vision, 2020.
January 2020 - A water-obstacle separation and refinement network for unmanned surface vehicles accepted to ICRA 2020.
December 2019 - Our work on deformable object tracking was selected as one of the Excellent research achievements in 2019 by the Slovenian Research Agency.
December 2019 - Vicos members Alan Lukežič, Borja Bovcon and Domen Tabernik received Faculty of computer science student research awards for their work on visual tracking, obstacle detection and traffic sign detection, respectively.
November 2019 - Our latest automated polyp counting in the wild algorithm has been accepted for publication.
September 2019 - Call for paper for 20th Computer Vision Winter Workshop in February 2020 has been published.
July 2019 - A new color-and-depth tracking benchmark -- CDTB accepted to ICCV2019.
June 2019 - The MaSTr1325 dataset for training deep USV obstacle detection models accepted to IROS2019.
May 2019 - Segmentation-Based Deep-Learning Approach for Surface-Defect Detection published in Journal of Intelligent Manufacturing, 2019. Now available code and KolektorSDD dataset.
May 2019 - Deep Learning for Large-Scale Traffic-Sign Detection and Recognition published in IEEE Transactions on Intelligent Transportation Systems, 2019. Now available code and DFG-TSD dataset.
February 2019 - Object Tracking by Reconstruction with View-Specific Discriminative Correlation Filters accepted to CVPR 2019.
February 2019 - Obstacle Tracking for Unmanned Surface Vessels using 3D Point Cloud accepted IEEE Journal of Oceanic Engineering.
December 2018 - FuCoLoT - A Fully-Correlational Long-Term Tracker accepted to Asian Conference on Computer Vision (ACCV) 2018 as an oral presentation.
September 2018 - Towards automated scyphistoma census in underwater imagery: a useful research and monitoring tool accepted to Journal of Sea Research.
July 2018 - TensorFlow implementation of DAU ConvNet from Spatially-Adaptive Filter Units for Deep Neural Networks paper now available.
March 2018 - Spatially-Adaptive Filter Units for Deep Neural Networks accepted to Computer vision and pattern recognition, CVPR2018. Now available code and pre-trained models .
March 2018 - Stereo obstacle detection for unmanned surface vehicles by IMU-assisted semantic segmentation accepted to Robotics and Autonomous Systems.