Visual Cognitive Systems Laboratory
Večna pot 113
tel.: +386 1 479 8245
The Visual Cognitive Systems Laboratory is involved in basic research in visually enabled cognitive systems, with emphasis on visual learning and recognition.
Research focuses on various theories about requirements, architectures, forms of representation, and varieties of mechanisms relevant to integration and control of vision systems.
Applications include tracking, learning, recognition and categorisation of objects and scenes in visual cognitive tasks, such as surveillance and smart vision-based positioning as well as in other applications of cognitive systems, such as mobile robots and cognitive assistants.
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.
February 2018 - The Discriminative Correlation Filter Tracker with Channel and Spatial Reliability now available in the OpenCV contrib repository (tracking module, CSRT tracker).
January 2018 - Discriminative Correlation Filter Tracker with Channel and Spatial Reliability accepted to IJCV.
December 2017 - Vicos member Alan Lukežič received Faculty of computer science student research award for his work on deformable parts models for visual tracking.
December 2017 - Vicos member Borja Bovcon received faculty Prešeren's award for his work on autonomous vessels.
July 2017 - Beyond standard benchmarks: Parameterizing performance evaluation in visual object tracking accepted to International Conference on Computer Vision, ICCV2017.
July 2017 - Deformable Parts Correlation Filters for Robust Visual Tracking accepted to IEEE Transactions on Cybernetics.
July 2017 - Improving vision-based obstacle detection on USV using inertial sensor accepted to ISPA2017.
April 2017 - Project ViAMaRo, an ARRS basic research project on robust computer vision for unmanned surface vehicles, accepted! The project received top scored in computer science and only top two were accepted in Slovenia!.
March 2017 - Learning part-based spatial models for laser-vision-based room categorization accepted to International Journal of Robotics Research.
March 2017 - Discriminative Correlation Filter with Channel and Spatial Reliability accepted to Computer vision and pattern recognition, CVPR2017.