prof. dr. Danijel Skočaj
Redni profesor
Dekan
T: +386 1 479 8225
E:Pošljite sporočilo
Govorilne ure: Četrtek 13:00-14:00 ali po dogovoru
Prostor: R2.57 - Kabinet
Opis

Danijel Skočaj je redni profesor in dekan Fakultete za računalništvo in informatiko Univerze v Ljubljani. Raziskovalno se ukvarja predvsem z računalniškim vidom in spoznavno robotiko. V okviru temeljnih in aplikativnih raziskav razvija in uvaja nove napredne metode globokega učenja in računalniškega vida za reševanje kompleksnih problemov, ki zahtevajo procesiranje vizualne informacije. Zanima ga tudi etični vidik umetne inteligence, strojnega učenja in robotike ter vpliv razvoja teh tehnologij na družbo. Predava predmete s področja računalniškega vida, spoznavne robotike in globokega učenja. Ima bogate izkušnje iz vodenja raziskovalnih in aplikativnih projektov, tako evropskih in nacionalnih, kot tudi projektov financiranih s strani industrijskih partnerjev, v okviru katerih skrbi za prenos raziskovalnih dognanj v prakso. Je član združenja ELLIS, bil pa je tudi predsednik Slovenskega društva za razpoznavanje vzorcev in odbora za računalništvo Computer Society pri IEEE Slovenija.

Nagrade

  • 2024: Nagrada za najboljši članek v reviji Pattern Recognition za leto 2023–2024.

  • 2012, 2023, 2024: Priznanje za izjemni znanstveni dosežek v Republiki Sloveniji (ARIS).

  • 2023: Prvo mesto v kategoriji računalniškega zaznavanja na 2. tekmovanju v robotski manipulaciji tekstila (Cloth Manipulation and Perception Challenge) v okviru 7. tekmovanja v robotskem prijemanju in manipulaciji (Robotic Grasping and Manipulation Competition), ICRA 2023.

  • 2021: Priznanje Prometej znanosti za odličnost v komuniciranju za leto 2020, Slovenska znanstvena fundacija.

  • 2021: Priznanje za enega največkrat prenesenih člankov v letu 2020 v znanstveni reviji Journal of Intelligent Manufacturing.

  • 2020: Zlata plaketa za izjemne zasluge pri razvijanju znanstvenega, pedagoškega ali umetniškega ustvarjanja ter za krepitev ugleda Univerze v Ljubljani.
  • 2019: Posebno priznanje za izjemen raziskovalni dosežek, Fakulteta za računalništvo in informatiko, UL.
  • 2013, 2017, 2019: Nagrada za najboljši prispevek v sekciji Razpoznavanja vzorcev na Mednarodni elektrotehniški in računalniški konferenci ERK 2013, 2017, 2019, Portorož, Slovenija.
  • 2002: Nagrada za članek temelječ na doktorski disertaciji na Enajsti mednarodni Elektrotehniški in računalniški konferenci ERK 2002, Portorož, Slovenija.
  • 2002: Nagrada za najboljši prispevek na 26th Workshop of the Austrian Association for Pattern Recognition (ÖAGM/AAPR), Graz, Austria.

 

Nagrade mojih študentov:

  • 2026: Zlati znak Jožefa Stefana, IJS (Vitjan Zavrtanik)

  • 2026: Nagrada dr. Ane Mayer Kansky za odmevno doktorsko delo, Univerza v Ljubljani (Vitjan Zavrtanik)

  • 2026: Plaketa odličnosti SDRV za odmevno doktorsko delo s področja razpoznavanja vzorcev, Slovensko društvo za razpoznavanje vzorcev (Vitjan Zavrtanik)

  • 2023: Nagrada dr. Uroša Seljaka za najboljšo znanstveno objavo študentov, Univerza v Ljubljani (Jakob Božič)

  • 2020, 2023: Prešernova nagrada študentom Univerze v Ljubljani, Univerza v Ljubljani (Jaka Šircelj, Jakob Božič)

  • 2013, 2019, 2021, 2022, 2024, 2025: Fakultetna Prešernova nagrada, Fakulteta za računalništvo in informatiko Univerze v Ljubljani (Klemen Istenič, Kristian Žarn, Vid Rijavec, Valter Hudovernik, Matic Fučka, Blaž Rolih)

Predmeti
Laboratorij
Projekti
Zaključeni projekti
Publikacije

  • SAMEC, Jaša, RIJAVEC, Vid, PELJHAN, Marko, GRM, Aleksander, ANDROJNA, Andrej, SKOČAJ, Danijel, DOBREVSKI, Matej. ISOPoT : imaging sonar odometry by point tracking. IEEE Robotics and automation letters, ISSN 2377-3766. 23 Oct. 2026.

  • TABERNIK, Domen, NIMAC, Peter, JERIĆEVIĆ, Jan, SKOČAJ, Danijel, GAMS, Andrej. Vision-based 6-DoF grasp pose estimation for robot cloth unfolding. IEEE transactions on cybernetics, ISSN 2168-2275. [Online ed.], Sep. 2026, [in press].

  • ROLIH, Blaž, FUČKA, Matic, SKOČAJ, Danijel. No label left behind : a unified surface defect detection model for all supervision regimes. Journal of intelligent manufacturing, ISSN 0956-5515. Aug. 2026, vol. 37.

  • ŠTEPEC, Dejan, JERŠE, Maja, ĐOKIĆ, Snežana, JERUC, Jera, ZIDAR, Nina, SKOČAJ, Danijel. Patherea : cell detection and classification for the 2020s. Medical Image Analysis, ISSN 1361-8423. [Online ed.], Feb. 2026, vol. 108.

  • KAMŠEK, Ana Rebeka, RUIZ-ZEPEDA, Francisco, TABERNIK, Domen, VIDERGAR, Jan, LOGAR, Anja, KREGAR, Ambrož, SKOČAJ, Danijel, DRAŽIĆ, Goran, HODNIK, Nejc. Large-scale identical-location electron microscopy enables quantifying nanoparticulate electrocatalyst degradation. Nature communications, ISSN 2041-1723. 2026.

  • FUČKA, Matic, ZAVRTANIK, Vitjan, SKOČAJ, Danijel. ObjectCore – efficient few-shot logical anomaly detection using object representations. V: 2026 IEEE/CVF Winter Conference on Applications of Computer Vision : WACV 2026 : proceedings. IEEE Computer Society, 2026. Proceedings (IEEE Workshop on Applications of Computer Vision. Online), ISSN 2642-9381.

  • BOŽIČ, Jakob, FUČKA, Matic, ZAVRTANIK, Vitjan, SKOČAJ, Danijel. Robustness of unsupervised methods for image surface-anomaly detection. Pattern analysis and applications, ISSN 1433-7541. [Print ed.], Jun. 2025, vol. 28.

  • FUČKA, Matic, ZAVRTANIK, Vitjan, SKOČAJ, Danijel. SALAD - semantics-aware logical anomaly detection. V: 2025 IEEE/CVF International Conference on Computer Vision : ICCV 2025 : proceedings. IEEE Computer Society, 2025. Proceedings (IEEE International Conference on Computer Vision. Online), ISSN 2380-7504.

  • FUČKA, Matic, ZAVRTANIK, Vitjan, SKOČAJ, Danijel. TransFusion – a transparency-based diffusion model for anomaly detection. V: LEONARDIS, Aleš (ur.). Computer vision - ECCV 2024. Part 35 : proceedings. Springer, 2025. Lecture notes in computer science, 15093, ISSN 1611-3349.

  • ROLIH, Blaž, FUČKA, Matic, SKOČAJ, Danijel. SuperSimpleNet : unifying unsupervised and supervised learning for fast and reliable surface defect detection. V: ANTONACOPOULOS, Apostolos (ur.). Pattern recognition. Part 10 : ICPR 2024 : proceedings. Springer, 2025. Lecture Notes in Computer Science, 15310, ISSN 1611-3349.

  • TABERNIK, Domen, MUHOVIČ, Jon Natanael, URBAS, Matej, SKOČAJ, Danijel. Center direction network for grasping point localization on cloths. IEEE Robotics and automation letters, ISSN 2377-3766. Oct. 2024, vol. 9.

  • DOBREVSKI, Matej, SKOČAJ, Danijel. Dynamic adaptive dynamic window approach. IEEE transactions on robotics, ISSN 1552-3098. [Print ed.], May 2024, vol. 40.

  • TABERNIK, Domen, MUHOVIČ, Jon Natanael, SKOČAJ, Danijel. Dense center-direction regression for object counting and localization with point supervision. Pattern recognition : the journal of the Pattern Recognition Society, ISSN 0031-3203. [Print ed.], Sep. 2024, vol. 153.

  • ZAVRTANIK, Vitjan, KRISTAN, Matej, SKOČAJ, Danijel. Keep DRÆMing : discriminative 3D anomaly detection through anomaly simulation. Pattern recognition letters : an official publication of the International Association for Pattern Recognition, ISSN 0167-8655. [Print ed.], May 2024, vol. 181.

  • ZAVRTANIK, Vitjan, MAROLT, Matija, KRISTAN, Matej, SKOČAJ, Danijel. Anomalous sound detection by feature-level anomaly simulation. V: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing : proceedings. IEEE, 2024. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (Online), ISSN 2379-190X.

  • ZAVRTANIK, Vitjan, KRISTAN, Matej, SKOČAJ, Danijel. Cheating depth : enhancing 3D surface anomaly detection via depth simulation. V: 2024 IEEE/CVF Winter Conference on Applications of Computer Vision : WACV 2024 : proceedings. IEEE Computer Society, 2024. IEEE Winter Conference on Applications of Computer Vision (Online), ISSN 2472-6796.

  • TABERNIK, Domen, ŠUC, Matic, SKOČAJ, Danijel. Automated detection and segmentation of cracks in concrete surfaces using joined segmentation and classification deep neural network. Construction & building materials, ISSN 0950-0618. [Print ed.], Dec. 2023, vol. 408.

  • ČEHOVIN ZAJC, Luka, REZELJ, Anže, SKOČAJ, Danijel. Low-cost open-source robotic platform for education. IEEE transactions on learning technologies, ISSN 1939-1382. [Online ed.], Feb. 2023, vol. 16.

  • ZAVRTANIK, Vitjan, KRISTAN, Matej, SKOČAJ, Danijel. DSR – a dual subspace re-projection network for surface anomaly detection. V: AVIDAN, Shai (ur.). Computer vision - ECCV 2022 : 17th European Conference : proceedings. Part 31. Springer, 2022. Lecture notes in computer science, 13691, ISSN 1611-3349.

  • ZAVRTANIK, Vitjan, KRISTAN, Matej, SKOČAJ, Danijel. DRAEM – a discriminatively trained reconstruction embedding for surface anomaly detection. V: 2021 IEEE/CVF International Conference on Computer Vision : ICCV 2021 : proceedings. IEEE Computer Society, 2021.

  • BOŽIČ, Jakob, TABERNIK, Domen, SKOČAJ, Danijel. Mixed supervision for surface-defect detection : from weakly to fully supervised learning. Computers in industry, ISSN 0166-3615. [Print ed.], Aug. 2021, vol. 129

  • RAČKI, Domen, TOMAŽEVIČ, Dejan, SKOČAJ, Danijel. Detection of surface defects on pharmaceutical solid oral dosage forms with convolutional neural networks. Neural computing & applications, ISSN 0941-0643, 2021

  • DOBREVSKI, Matej, SKOČAJ, Danijel. Deep reinforcement learning for map-less goal-driven robot navigation. International journal of advanced robotic systems, ISSN 1729-8814, Jan./Feb. 2021, vol. 18, no. 1

  • ZAVRTANIK, Vitjan, KRISTAN, Matej, SKOČAJ, Danijel. Reconstruction by inpainting for visual anomaly detection. Pattern recognition : the journal of the Pattern Recognition Society, ISSN 0031-3203. [Print ed.], Apr. 2021, vol. 112

  • DOBREVSKI, Matej, SKOČAJ, Danijel. Adaptive dynamic window approach for local navigation. V: 2020 IEEE/RSJ IEEE International Conference on Intelligent Robots and Systems (IROS), October, 25-29, 2020, Las Vegas, NV, USA, 2020, str. 6930-6936

  • TABERNIK, Domen, SKOČAJ, Danijel. Deep learning for large-scale traffic-sign detection and recognition. IEEE transactions on intelligent transportation systems, ISSN 1524-9050. [Print ed.], Apr. 2020, vol. 21, no. 4, str. 1427-1440

  • TABERNIK, Domen, ŠELA, Samo, SKVARČ, Jure, SKOČAJ, Danijel. Segmentation-based deep-learning approach for surface-defect detection. Journal of intelligent manufacturing, ISSN 0956-5515, Mar. 2020, vol. 31, no. 3, str. 759-776

  • MAVER, Jasna, SKOČAJ, Danijel. EL: local image descriptor based on extreme responses to partial derivatives of 2D Gaussian function. Mathematical problems in engineering, ISSN 1563-5147, 2019, vol. 2019 

  • URŠIČ, Peter, LEONARDIS, Aleš, SKOČAJ, Danijel, KRISTAN, Matej. Learning part-based spatial models for laser-vision-based room categorization. The international journal of robotics research, ISSN 0278-3649. [Print ed.], 2017, vol. 36, no. 4, str. 379-402

  • SKOČAJ, Danijel, VREČKO, Alen, MAHNIČ, Marko, JANÍČEK, Miroslav, KRUIJFF, Geert-Jan M., HANHEIDE, Marc, HAWES, Nick, WYATT, Jeremy L., KELLER, Thomas, ZHOU, Kai, ZILLICH, Michael, KRISTAN, Matej. An integrated system for interactive continuous learning of categorical knowledge. Journal of experimental & theoretical artificial intelligence, ISSN 0952-813X. [Print ed.], 2016, vol. 28, no. 5, str. 823-848

  • TABERNIK, Domen, LEONARDIS, Aleš, BOBEN, Marko, SKOČAJ, Danijel, KRISTAN, Matej. Adding discriminative power to a generative hierarchical compositional model using histograms of compositions. Computer vision and image understanding, ISSN 1077-3142. [Print ed.], Sep. 2015, vol. 138, str. 102-113

  • RIDGE, Barry, LEONARDIS, Aleš, UDE, Aleš, DENIŠA, Miha, SKOČAJ, Danijel. Self-supervised online learning of basic object push affordances. International journal of advanced robotic systems, ISSN 1729-8814, 2015, vol. 12, str. 24-1-24-18

  • URŠIČ, Peter, TABERNIK, Domen, BOBEN, Marko, SKOČAJ, Danijel, LEONARDIS, Aleš, KRISTAN, Matej. Room categorization based on a hierarchical representation of space. International journal of advanced robotic systems, ISSN 1729-8814, 2013, vol. 10

  • VREČKO, Alen, LEONARDIS, Aleš, SKOČAJ, Danijel. Modeling binding and cross-modal learning in Markov logic networks. Neurocomputing (Amst.). [Print ed.], 2012

  • KRISTAN, Matej, LEONARDIS, Aleš, SKOČAJ, Danijel. Multivariate online kernel density estimation with Gaussian kernels. Pattern recogn.. [Print ed.], 2011, vol. 44, no. 10/11, str. 2630-2642

  • WYATT, Jeremy L., AYDEMIR, Alper, BRENNER, Michael, HANHEIDE, Marc, HAWES, Nick, JENSFELT, Patric, KRISTAN, Matej, KRUIJFF, Geert-Jan M., LISON, Pierre, PRONOBIS, Andrzej, SJÖÖ, Kristoffer, VREČKO, Alen, ZENDER, Hendrik, ZILLICH, Michael, SKOČAJ, Danijel. Self-understanding and self-extension : a systems and representational approach. IEEE trans. auton. ment. dev. (Print). [Print ed.], Dec. 2010, vol. 2, no. 4, str. 282-303

  • KRISTAN, Matej, SKOČAJ, Danijel, LEONARDIS, Aleš. Online kernel density estimation for interactive learning. Image vis. comput.. [Print ed.], Jul. 2010, vol. 28, no. 7, str. 1106-1116

  • SKOČAJ, Danijel, LEONARDIS, Aleš. Incremental and robust learning of subspace representations. Image vis. comput.. [Print ed.], 2008, vol. 26, no. 1, str. 27-38

  • SKOČAJ, Danijel, LEONARDIS, Aleš, BISCHOF, Horst. Weighted and robust learning of subspace representations. Pattern recogn.. [Print ed.], May 2007, vol. 40, no. 5, str. [1556]-1569

  • FIDLER, Sanja, SKOČAJ, Danijel, LEONARDIS, Aleš. Combining reconstructive and discriminative subspace methods for robust classification and regression by subsampling. IEEE trans. pattern anal. mach. intell., Mar. 2006, vol. 28, no. 3, str. 337-350. 

Več