Odjel za obradu signala uključuje znanstvena područja poput teorije signala i sustava, teorije i primjene kodiranja, uporabe filtara, prijenosa signala, estimacije, detekcije, analize, prepoznavanja, sinteze te reprodukcije signala digitalnim ili analognim uređajima i tehnikama. Pojam signala uključuje audio i video signale, govor, slike, komunikacije, signal sonara, radara kao i medicinske, glazbene i druge signale.
Odjel za obradu signala
Poštovane članice i članovi Hrvatske sekcije IEEE,
pozivamo Vas na predavanje u suorganizaciji Odjela za obradu signala, Odjela za računarstvo, i Odjela za računalnu inteligenciju Hrvatske sekcije IEEE te Centra izvrsnosti za računalni vid koje će održati
prof. dr. sc. Siniša Šegvić
u srijedu 20. listopada 2021. godine u 11:15 sati uživo u Sivoj vijećnici uz prijenos preko Microsoftovih Teamsa.
Naslov predavanja je
Elements of Learning Algorithms for Natural Scene Understanding
Zbog ograničenog kapaciteta Sive vijećnice za sudjelovanje na predavanju uživo molimo vas da se prijavite preko poveznice https://forms.gle/oGWUCbfw2NDfyyjQA.
Poveznica za prijednost predavanja i virtualno sudjelovanje je https://teams.microsoft.com/l/meetup-join/19%3aqVfC8f4s6oDkzAxfcSZfy_fwNDV4kaoq08YMSC9g7-w1%40thread.tacv2/1634312486406?context=%7b%22Tid%22%3a%22ca71eddc-cc7b-4e5b-95bd-55b658e696be%22%2c%22Oid%22%3a%22e20c832e-fcb0-4b71-946b-ac8de75374b4%22%7d.
Predavanje je otvoreno za sve zainteresirane, a posebno pozivamo studente.
Osim na predavanje pozivamo vas i na sudjelovanje u radu Devete hrvatske radionice o računalnom vidu.
Program radionice je dostupan na https://www.fer.unizg.hr/crv/ccvw2021/program.
Sažetak/Abstract
Deep learning has led to unprecedented improvement of computer vision, natural language processing and other fields of artificial intelligence. However, our models still underperform on unusual and adversarial test examples, while offering limited interpretability and explainability. Nevertheless, experienced practitioners seldom regard their models as black boxes. Instead, they promote desired behaviour through suitable kinds of inductive bias and careful exploitation of available data. I will illustrate these concepts by describing elements of learning algorithms which have been extensively exploited within my research group in the past few years.
The second part of my talk will describe our ongoing collaborations with the local industry. I will point out advantages of such arrangements for all involved parties. The talk will conclude with a brief overview of current challenges and opportunities in our field.
Kratki životopis/Short Biography
Siniša Šegvić was a postdoc researcher at IRISA, Rennes and at TU Graz. He led three research projects of the Croatian Science Foundation (MultiCLOD, MASTIF, ADEPT) as well as several industrial research projects funded by local companies. He has participated in the research center of excellence DataCross, and several ERDF projects (SafeTram, A-UNIT). His research and professional interests include computer vision, visual recognition, dense semantic prediction and forecasting, as well as generative modelling with normalizing flows. He has published several papers at top conferences on computer vision and artificial intelligence. He has participated in industrial development as a technical consultant. He advises several full-time PhD students funded by EU projects, national projects and private companies. His research group has achieved notable results while participating at computer vision challenges such as WildDash, Robust vision challenge, Fishyscapes and Cityscapes.
Repozitorij
MODELING AND CODING OF SPEECH AND AUDIO SIGNALS [268,28 KiB]Bastiaan Kleijn KTH School of Electrical Engineering Stockholm- Flexible Quantization [186,41 KiB]Bastiaan Kleijn KTH School of Electrical Engineering Stockholm
- Robust Source Coding [259,82 KiB]Bastiaan Kleijn KTH School of Electrical Engineering Stockholm
- Signal Enhancement [197,02 KiB]Bastiaan Kleijn KTH School of Electrical Engineering Stockholm
- ArdbegVectorProcessorOct?2008 [327,7 KiB]Prezentacija Mladen Wilder
Veliki hadronski sudarivač - vrhunska tehnologija za vrhunsku znanost [19,89 MiB]Prezentacija prof. Guy Paić
