List of publications

Multi-domain semantic segmentation with overlapping labels. Petra Bevandić, Marin Oršić, Ivan Grubišić, Josip Šarić, Siniša Šegvić. WACV 2022. (cvf).

Dense Semantic Forecasting in Video by Joint Regression of Features and Feature Motion. Josip Šarić, Sacha Vražić, Siniša Šegvić. IEEE TNNLS 2021. (ieee, arxiv).

A baseline for semi-supervised learning of efficient semantic segmentation models. Ivan Grubisic, Marin Orsic, Sinisa Segvic. MVA 2021. pdf

Densely connected normalizing flows. Matej Grcić, Ivan Grubišić, Siniša Šegvić. NeurIPS 2021. arxiv

Dense open-set recognition with synthetic outliers generated by Real NVP. Matej Grcić, Petra Bevandić, Siniša Šegvić. VISAPP 2021. arxiv

Multi-domain semantic segmentation with overlapping labels Marin Oršić, Petra Bevandić, Ivan Grubišić, Josip Šarić, Siniša Šegvić. arxiv

Multimodal semantic forecasting based on conditional generation of future features. Kristijan Fugošić, Josip Šarić, Siniša Šegvić. GCPR 2020. arxiv

Efficient semantic segmentation with pyramidal fusion. Marin Oršić, Siniša Šegvić. Pattern recognition (accepted).

Multi-Task Learning for iRAP Attribute Classification and Road Safety Assessment. Marin Kačan, Sinisa Segvic, Marko Ševrović. ITSC 2020. pdf

Efficient Ladder-Style DenseNets for Semantic Segmentation of Large Images. Ivan Krešo, Josip Krapac, Siniša Šegvić. T-ITS 2020. pdf

Warp to the Future: Joint Forecasting of Features and Feature Motion. Josip Šarić, Marin Oršić, Tonći Antunović, Sacha Vražić, Siniša Šegvić. CVPR 2020. cvf

Single Level Feature-to-Feature Forecasting with Deformable Convolutions. Josip Šarić, Marin Oršić, Tonći Antunović, Sacha Vražić, and Siniša Šegvić. GCPR 2019. arxiv

Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shift Petra Bevandić, Ivan Krešo, Marin Oršić, and Siniša Šegvić GCPR 2019. pdf

Pedestrian Tracking by Probabilistic Data Association and Correspondence Embeddings Borna Bićanić, Marin Oršić, Ivan Marković, Siniša Šegvić, Ivan Petrović. FUSION 2019. pdf, video

Efficient Ladder-style DenseNets for Semantic Segmentation of Large Images. Ivan Krešo, Josip Krapac, Siniša Šegvić. CoRR abs/1905.05661. arxiv, video1, video2, video3, youtube

In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images. Marin Oršić, Ivan Krešo, Petra Bevandić, Siniša Šegvić. CVPR 2019 (accepted for publication). arxiv

Traffic Scene Classification on a Representation Budget. Ivan Sikirić, Karla Brkić, Petra Bevandić, Ivan Krešo, Josip Krapac, Siniša Šegvić. IEEE Transactions on Intelligent Transportation Systems. 2019. pdf

Sparse weakly supervised models for object localization in road environment. Valentina Zadrija, Josip Krapac, Siniša Šegvić, Jakob Verbeek. Computer Vision and Image Understanding. 2018. pdf

Petra Bevandic, Ivan Kreso, Marin Orsic, Sinisa Segvic: Discriminative out-of-distribution detection for semantic segmentation. CoRR abs/1808.07703. pdf

Ivan Kreso, Marin Orsic, Petra Bevandic, Sinisa Segvic. Robust Semantic Segmentation with Ladder-DenseNet Models. CoRR abs/1806.03465. Runner up prize at CVPR ROB 2018 semantic segmentation challenge (submission ROB_LDN2). pdf

Convolutional Models for Segmentation and Localization. Ivan Krešo, Petra Bevandić, Marin Oršić, Siniša Šegvić. Engineering Power : Bulletin of the Croatian Academy of Engineering, Vol. 13. No. 2. 2018. pdf

Siniša Šegvić. Computer Vision: introduction and overview of current practice Motivational lecture for the Mozgalo contest. pdf

Ivan Krešo, Josip Krapac and Siniša Šegvić. Ladder-style DenseNets for Semantic Segmentation of Large Natural Images ICCV CVRSUAD 2017. pdf

Josip Krapac and Siniša Šegvić. Weakly-supervised semantic segmentation by redistributing region scores back to the pixels. GCPR 2016. pdf

Ivan Krešo, Denis Čaušević, Josip Krapac and Siniša Šegvić. Convolutional Scale Invariance for Semantic Segmentation. GCPR 2016. pdf

Valentina Zadrija, Josip Krapac, Jakob Verbeek and Siniša Šegvić. Patch-level Spatial Layout for Classification and Weakly Supervised Localization. GCPR 2015. pdf

Josip Krapac and Siniša Šegvić. Fast Approximate GMM Soft-Assign for Fine-Grained Image Classification with Large Fisher Vectors. GCPR 2015. pdf

Ivan Sikirić, Karla Brkić, Josip Krapac, Siniša Šegvić. Robust Traffic Scene Recognition with a Limited Descriptor Length. CVPRW 2015 VPRICE. pdf

Ivan Krešo and Siniša Šegvić. Improving the Egomotion Estimation by Correcting the Calibration Bias. VISAPP 2015. (pdf)

Josip Krapac and Siniša Šegvić. Weakly supervised object localization with large Fisher vectors. VISAPP 2015 (pdf)

Ivan Sikirić, Karla Brkić, Ivan Horvatin and Siniša Šegvić. Multi-label classification of traffic scenes. CCVW 2014, Zagreb, Croatia (pdf).

Karla Brkić, Siniša Šegvić, Zoran Kalafatić, Aitor Aldoma and Markus Vincze. Recognizing 3D objects from a limited number of views using temporal ensembles of shape functions. CCVW 2014, Zagreb, Croatia.

Igor Lipovac, Tomislav Hrkać, Karla Brkić, Zoran Kalafatić and Siniša Šegvić. Experimental evaluation of vehicle detection based on background modelling in daytime and night-time video. CCVW 2014, Zagreb, Croatia (pdf).

Vedran Vukotić, Josip Krapac and Siniša Šegvić. Convolutional neural networks for Croatian traffic signs recognition. CCVW 2014, Zagreb, Croatia (pdf).

Valentina Zadrija and Siniša Šegvić. Experimental Evaluation of Multiplicative Kernel SVM Classifiers for Multi-Class Detection. CCVW 2014, Zagreb, Croatia (pdf).

Ivan Sikiric, Karla Brkic, Josip Krapac, Sinisa Segvic. Image Representations on a Budget: Traffic Scene Classification in a Restricted Bandwidth Scenario. IV 2014, Dearborn, Michigan (pdf).

Karla Brkic, Aitor Aldoma, Markus Vincze, Sinisa Segvic, Zoran Kalafatic. Temporal Ensemble of Shape Functions. Eurographics 3DOR 2013, Strasbourg, France (pdf).

Ivan Sikiric, Karla Brkic, Sinisa Segvic. Classifying Traffic Scenes Using The GIST Image Descriptor. CCVW 2013, Zagreb, Croatia (arxiv).

Valentina Zadrija, Sinisa Segvic. Multiclass Road Sign Detection using Multiplicative Kernels. CCVW 2013, Zagreb, Croatia (arxiv).

Ivan Kreso, Marko Sevrovic, Sinisa Segvic. A Novel Georeferenced Dataset for Stereo Visual Odometry. CCVW 2013, Zagreb, Croatia (arxiv).

Karla Brkic, Srdan Rasic, Axel Pinz, Sinisa Segvic, Zoran Kalafatic. Combining Spatio-Temporal Appearance Descriptors and Optical Flow for Human Action Recognition in Video Data. CCVW 2013, Zagreb, Croatia (arxiv).

Sinisa Segvic, Zoran Kalafatic, Ivan Kovacek. Sliding Window Object Detection without Spatial Clustering of Raw Detection Responses. IFAC SYROCO 2012 (pdf).

Karla Brkic Axel Pinz, Zoran Kalafatic, Sinisa Segvic. Towards space-time semantics in two frames. ARTEMIS 2012 (ECCV workshop) (pdf).

Sinisa Segvic, Karla Brkic, Zoran Kalafatic, Axel Pinz. Exploiting temporal and spatial constraints in traffic sign detection from a moving vehicle. Machine Vision and Applications 25(3): 649-665 (2014). (pdf).

Viktor Braut, Vedran Vukotic, Mateja Culjak, Sinisa Segvic, Marko Sevrovic, Hrvoje Gold. Estimating OD matrices at intersections in airborne video - a pilot study. MIPRO, Opatija, Croatia, May 2012 (pdf, video1, video2, video3).

Ivan Sikiric, Ante Majic, Sinisa Segvic. Using GPS positioning to recover a comprehensive road appearance mosaic. MIPRO, Opatija, Croatia, May 2011: 877-882 (pdf, video1, video2).

Petar Palasek, Petra Bosilj, Sinisa Segvic. Detecting and recognizing centerlines as parabolic sections of the steerable filter response. MIPRO, Opatija, Croatia, May 2011: 903-908 (pdf, video1, video2).

Sinisa Segvic, Marko Sevrovic, Goran Kos, Vladimir Stanisavljevic, Ivan Dadic. Preliminary experiments in multi-view video stitching. MIPRO, Opatija, Croatia, May 2011: 892-896 (pdf, video).

A. Diosi, S. Segvic, A. Remazeilles, F. Chaumette. Experimental Evaluation of Autonomous Driving Based on Visual Memory and Image Based Visual Servoing. IEEE Transactions on Intelligent Transportation Systems, 12(3): 870-883 (2011) (pdf).

Karla Brkic, Axel Pinz, Sinisa Segvic, Zoran Kalafatic. Histogram-Based Description of Local State-Time Appearance. SCIA, Ystad Saltsjöbad, Sweden May 2011: 206-217 (pdf).

Igor Bonaci, Ivan Kusalic, Ivan Kovacek, Zoran Kalafatic, Sinisa Segvic. Addressing false alarms and localization inaccuracy in traffic sign detection and recognition. CVWW, Mitterberg, Austria, January 2011: 1-8 (pdf).

Sinisa Segvic, Karla Brkic, Zoran Kalafatic, Vladimir Stanisavljevic, Marko Sevrovic, Damir Budimir and Ivan Dadic. A computer vision assisted geoinformation inventory for traffic infrastructure. ITSC, Madeira, Portugal, September 2010: 66-73 (pdf, video)

Karla Brkic, Sinisa Segvic, Zoran Kalafatic, Ivan Sikiric, Axel Pinz. Generative modeling of spatio-temporal traffic sign trajectories. UCVP (held in conjunction with CVPR), San Francisco, California, June 2010: 1-7 (pdf)

Ana Bulovic, Damir Bucar, Petar Palasek, Bojan Popovic, Ante Trbojevic, Lucija Zadrija, Ivan Kusalic, Karla Brkic, Zoran Kalafatic, Sinisa Segvic. Streamlining collection of training samples for object detection and classification in video. MIPRO, Opatija, Croatia, May 2010: 728-733 (pdf)

Ivan Sikiric, Karla Brkic, Sinisa Segvic. Recovering a comprehensive road appearance mosaic from video. MIPRO, Opatija, Croatia, May 2010: 755-759 (pdf)

Karla Brkic, Axel Pinz and Sinisa Segvic Traffic sign detection as a component of an automated traffic infrastructure inventory system. in Proceedings of the annual Workshop of the Austrian Association for Pattern Recognition (OAGM/AAPR), Stainz, Austria, May 2009: 1-12 (article, poster)

S. Segvic, K. Brkic, Z. Kalafatic, V. Stanisavljevic, D. Budimir and I. Dadic Towards automatic assessment and mapping of traffic infrastructure by adding vision capabilities to a geoinformation inventory. MIPRO, Opatija, Croatia, May 2009: 276-281 (pdf)

S. Segvic, A. Remazeilles, A. Diosi and F. Chaumette A mapping and localization framework for scalable appearance-based navigation. Computer Vision and Image Understanding 113(2): 172-187 (2009) (pdf, doi)

G. Schweighofer, S. Segvic and A. Pinz Online/Realtime Structure and Motion for General Camera Models. in Proceedings of Workshop on Applications of Computer Vision WACV'08, Aspen, CO, February 2008: 1-6 (pdf)

A. Diosi, A. Remazeilles, S. Segvic, F. Chaumette Outdoor Visual Path Following Experiments. in Proceedings of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems IROS'07, San Diego, CA, October 2007: 4265-4270 (pdf, video1, video2)

A. Diosi, A. Remazeilles, S. Segvic, F. Chaumette Experimental evaluation of an urban visual path following framework. in Proceedings of the IFAC Symposium on Intelligent Autonomous Vehicles, Toulouse, France, September 2007. (pdf)

S. Segvic, A. Remazeilles, A. Diosi and F. Chaumette A framework for scalable vision-only navigation. in Advanced Concepts for Intelligent Vision Systems ACIVS'07, Delft, Netherlands, August 2007: 1-12 (pdf, video)

S. Segvic, G. Schweighofer and A. Pinz Influence of the numerical conditioning to the accuracy of relative orientation. in Proceedings of the ISPRS Workshop BenCOS (held in conjunction with CVPR), Minneapolis, Minnesota, June 2007: 1-8 (pdf, slides)

S. Segvic, A. Remazeilles, A. Diosi and F. Chaumette Large scale vision based navigation without an accurate global reconstruction. in Proceedings of CVPR, Minneapolis, Minnesota, June 2007: 1-8 (pdf, video, poster)

S. Segvic, G. Schweighofer and A. Pinz Performance evaluation of the five-point relative pose with emphasis on planar scenes. In Proceedings of AAPR/OAGM, Schloss Krumbach, Austria, May 2007: 33-40 (pdf, slides, code)

S. Segvic, A. Remazeilles and F. Chaumette Enhancing the Point Feature Tracker by Adaptive Modelling of the Feature Support. in Proceedings of the 9th European Conference on Computer Vision, Graz, Austria, 2006: 112-124 (pdf, video, demo)

S. Segvic, A Multimodal Image Registration Technique for Structured Polygonal Scenes. in Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, Zagreb, Croatia, September 2005: 500-505 (pdf, slides)

S. Segvic, Multi-agent Object Tracking by Active Vision. PhD thesis, Fakultet elektrotehnike i racunarstva, Zagreb, Croatia, June 2004. (pdf)

S. Ribaric, G. Adrinek, and S. Segvic, Real-time active visual tracking system. in Proceedings of the 12th IEEE Mediterranean Electrotechnical Conference, Dubrovnik, Croatia, pp. 231-234, May 2004. (pdf)

S. Segvic and S. Ribaric, A software architecture for distributed visual tracking in a global vision localization system. Lecture Notes in Computer Science, vol.2626:365-375, 2003. (pdf)

S. Segvic, Detecting Salient Curvature Features Using the Local Control of the Feature Support. in Proceedings of the 11th IEEE Mediterranean Electrotechnical Conference, Cairo, Egypt, may 2002.

S. Segvic, Z. Kalafatic and S. Ribaric, Extracting the canonical set of closed contours using the best-first search algorithm. in Proceedings of the 1st IEEE International Symposium on Signal Processing and Information Technology, Cairo, Egypt, december 2001. (pdf)

S. Segvic and S. Ribaric, Determining the Absolute Orientation in a Corridor Using Projective Geometry and Active Vision. IEEE Transactions on Industrial Electronics, vol.48(3):696-710, 2001. (pdf)

S. Segvic, V. Stanisavljevic and Z. Kalafatic, A software architecture for image acquisition and camera control in an active computer vision system. in Proceedings of the 22nd International Conference on Information Technology Interfaces, Pula, Croatia, june 2000.

S. Ribaric, S. Segvic and V. Spisic, Locally adaptive thresholding of the sequence of image frames. in Proceedings of the 10th IEEE Mediterranean Electrotechnical Conference Lemesos, Cyprus, may 2000.

S. Segvic, Using Projective Geometry and Active Vision for Scene Interpretation. in Croatian, MS thesis, Faculty of Electrical Engineering and Computing, Zagreb, 2000.

S. Segvic and S. Ribaric, Self-localisation procedure for autonomous navigation through corridors. in Proceedings of the Eighth Electrotechnical and Computer Science Conference, Portoroz, Slovenia, october 1999.

S. Ribaric, S. Segvic and V. Spisic, Real Time Segmentation by Locally Adaptive Dynamic Thresholding. in Croatian, Automatika, vol.40(1-2):43-52, 1999.

S. Segvic, Using vanishing points for purposive adjustment of viewing direction. in Proceedings of the IEEE International Symposium on Industrial Electronics, Bled, Slovenia, june 1999.

S. Segvic, Robust Extraction of Line Segments from Colour Images by an Iterative Weighted Polarised Hough Transform. in Proceedings of 21th International Convention MIPRO '98, Opatija, Croatia, May 1998.

Svi komentari su dobrodo¹li:

Povratak