Zobrazeno 1 - 10
of 59
pro vyhledávání: '"Siniša Šegvić"'
Publikováno v:
Sensors, Vol 24, Iss 4, p 1248 (2024)
Standard machine learning is unable to accommodate inputs which do not belong to the training distribution. The resulting models often give rise to confident incorrect predictions which may lead to devastating consequences. This problem is especially
Externí odkaz:
https://doaj.org/article/1e0f819a0d6d46c58b7b716cc7615056
Publikováno v:
Remote Sensing, Vol 15, Iss 8, p 1968 (2023)
Dense panoptic prediction is a key ingredient in many existing applications such as autonomous driving, automated warehouses, or remote sensing. Many of these applications require fast inference over large input resolutions on affordable or even embe
Externí odkaz:
https://doaj.org/article/a3f736253516449d81ce02241ff5edfc
Publikováno v:
Sensors, Vol 23, Iss 2, p 940 (2023)
Semi-supervised learning is an attractive technique in practical deployments of deep models since it relaxes the dependence on labeled data. It is especially important in the scope of dense prediction because pixel-level annotation requires substanti
Externí odkaz:
https://doaj.org/article/4333a27bfbfc48f698d3bb6982fff0a4
Publikováno v:
Applied Sciences, Vol 13, Iss 1, p 400 (2022)
Anticipation of per-pixel semantics in a future unobserved frame is also known as dense semantic forecasting. State-of-the-art methods are based on single-level regression of a subsampled abstract representation of a recognition model. However, singl
Externí odkaz:
https://doaj.org/article/ed804b8d96a44933adee9fb2b7d49bcf
Publikováno v:
IEEE Transactions on Intelligent Transportation Systems. 21:336-345
Visual cues can be used alongside GPS positioning and digital maps to improve understanding of vehicle environment in fleet management systems. Such systems are limited both in terms of bandwidth and storage space, so minimizing the size of transmitt
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::47c559bd44bdf745c821d6beb71902cf
https://doi.org/10.1109/tits.2019.2891995
https://doi.org/10.1109/tits.2019.2891995
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198052
Anomaly detection can be conceived either through generative modelling of regular training data or by discriminating with respect to negative training data. These two approaches exhibit different failure modes. Consequently, hybrid algorithms present
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9335528c0b767525b3e3426ee1fa70a7
https://www.bib.irb.hr/1236654
https://www.bib.irb.hr/1236654
Autor:
Siniša Šegvić
Most machine learning applications leverage discriminative models and supervised learning. However, discriminative models are unable to generate new content or measure plausibility of the data. Additionally, they are prone to learning simple decision
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=57a035e5b1ae::80ac115a7f0dabd320b41b20346ded91
https://www.bib.irb.hr/1236838
https://www.bib.irb.hr/1236838
Autor:
Iva M. Tolić, Ivana Ponjavić, Ivan Barišić, Monika Trupinić, Siniša Šegvić, Barbara Kokanović, Arian Ivec
Publikováno v:
Current Biology
Mechanical forces produced by motor proteins and microtubule dynamics within the mitotic spindle are crucial for the movement of chromosomes and their segregation into the daughter cells. In addition to linear forces, rotational forces or torques are
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f358735e0513cae5d979a1a4bda72cbe
https://doi.org/10.1016/j.cub.2022.04.035
https://doi.org/10.1016/j.cub.2022.04.035
Autor:
Monika Trupinić, Barbara Kokanović, Ivana Ponjavić, Ivan Barišić, Siniša Šegvić, Arian Ivec, Iva Tolić
Publikováno v:
SSRN Electronic Journal.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::96e078c50601a2b13300ccb8d2b869c8
https://doi.org/10.2139/ssrn.3931649
https://doi.org/10.2139/ssrn.3931649
Publikováno v:
MVA
Semi-supervised learning is especially interesting in the dense prediction context due to high cost of pixel-level ground truth. Unfortunately, most such approaches are evaluated on outdated architectures which hamper research due to very slow traini
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::78f0ef7a9c13911838f51defd620cc26
https://doi.org/10.23919/mva51890.2021.9511402
https://doi.org/10.23919/mva51890.2021.9511402