Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 1236816

Natural image understanding: principles, challenges and research outlook


Siniša Šegvić
Natural image understanding: principles, challenges and research outlook // AI2Future 2018
Zagreb, Hrvatska, 2018. (pozvano predavanje, nije recenziran, pp prezentacija, stručni)


CROSBI ID: 1236816 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Natural image understanding: principles, challenges and research outlook

Autori
Siniša Šegvić

Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, pp prezentacija, stručni

Skup
AI2Future 2018

Mjesto i datum
Zagreb, Hrvatska, 11-12.10.2018

Vrsta sudjelovanja
Pozvano predavanje

Vrsta recenzije
Nije recenziran

Ključne riječi
computer vision

Sažetak
Development of supervised convolutional models has resulted in tremendous advances of visual recognition. Today we are able to design systems which classify images, detect faces and recognize people at a near human level. However, challenges such as cross-dataset generalization or adversarial examples indicate that further work is required to reach truly intelligent artificial vision. In this talk I will present current state of visual recognition: operational principles, current performance, main challenges, as well as research directions which promise to push the limits even further.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo



POVEZANOST RADA


Projekti:
HRZZ-IP-2013-11-1395 - Detekcija objekata više razreda za pametna vozila i sigurnije ceste (MULTICLOD) (Šegvić, Siniša, HRZZ ) ( CroRIS)

Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb

Profili:

Avatar Url Siniša Šegvić (autor)

Poveznice na cjeloviti tekst rada:

www.zemris.fer.hr

Citiraj ovu publikaciju:

Siniša Šegvić
Natural image understanding: principles, challenges and research outlook // AI2Future 2018
Zagreb, Hrvatska, 2018. (pozvano predavanje, nije recenziran, pp prezentacija, stručni)
Siniša Šegvić (2018) Natural image understanding: principles, challenges and research outlook. U: AI2Future 2018.
@article{article, year = {2018}, keywords = {computer vision}, title = {Natural image understanding: principles, challenges and research outlook}, keyword = {computer vision}, publisherplace = {Zagreb, Hrvatska} }
@article{article, year = {2018}, keywords = {computer vision}, title = {Natural image understanding: principles, challenges and research outlook}, keyword = {computer vision}, publisherplace = {Zagreb, Hrvatska} }




Contrast
Increase Font
Decrease Font
Dyslexic Font