Workshop: WAWLA (What Are We Looking At)

! English translation below !

𝗦𝗶𝗺𝗼𝗻𝗲 𝗖 𝗡𝗶𝗾𝘂𝗶𝗹𝗹𝗲
𝑊𝐴𝑊𝐿𝐴 (𝑊ℎ𝑎𝑡 𝐴𝑟𝑒 𝑊𝑒 𝐿𝑜𝑜𝑘𝑖𝑛𝑔 𝐴𝑡)
DELAVNICA | 13. maj, 17:00–20:00 | ALUO, Tobačna
✦ aksioma.org/becomingimage/sl/delavnice/wawla/

🔵 𝗨𝗱𝗲𝗹𝗲𝘇̌𝗯𝗮 𝗷𝗲 𝗯𝗿𝗲𝘇𝗽𝗹𝗮𝗰̌𝗻𝗮, 𝗽𝗼𝘁𝗿𝗲𝗯𝗻𝗮 𝗷𝗲 𝗹𝗲 𝗽𝗿𝗶𝗷𝗮𝘃𝗮! > pretix.eu/aksioma/becomingimage/

𝑊𝐴𝑊𝐿𝐴 (𝑊ℎ𝑎𝑡 𝐴𝑟𝑒 𝑊𝑒 𝐿𝑜𝑜𝑘𝑖𝑛𝑔 𝐴𝑡) je delavnica, ki se poglobi v svet računalniškega vida, podatkovnih zbirk za učenje podob in nevidnega človeškega dela, na katerem temelji strojno zaznavanje. Udeleženci se seznanijo s potekom izdelave modela računalniškega vida ter s koraki sestavljanja in priprave podatkovnih zbirk, pri čemer se posebej posvetijo segmentiranju podob. Segmentacija je za računalniški vid ključna, saj »izpostavlja« dele podobe, ki so za sistem relevantni. Na tej stopnji obdelave je podoba vizualno razdeljena na posamezne dele. Z obrisovanjem izbranega objekta (prometni znak, srna, obraz) ali označevanjem določenega območja (cesta, drevo, sence) ti segmenti odločilno oblikujejo način, kako model računalniškega vida zaznava svet. Kaj je segmentirano in kaj ne, je odvisno od različnih dejavnikov – od prihodnje rabe tehnologije do kulturnega konteksta, ločljivosti podobe, jezika, v katerem so podatki označeni, in subjektivne percepcije – ter se lahko razlikuje od našega lastnega branja podobe.

🔹 SORODNI DOGODKI s Simone C Niquille:
+ Razstava: duckrabbit.tv | 12. maj, 19:00 | Aksioma Projektni prostor
+ Predavanje: Baloni itd. | 13. maj, 15:00–16:00 | ALUO, Erjavčeva

—

[ENG]

𝗦𝗶𝗺𝗼𝗻𝗲 𝗖 𝗡𝗶𝗾𝘂𝗶𝗹𝗹𝗲
𝑊𝐴𝑊𝐿𝐴 (𝑊ℎ𝑎𝑡 𝐴𝑟𝑒 𝑊𝑒 𝐿𝑜𝑜𝑘𝑖𝑛𝑔 𝐴𝑡)
WORKSHOP | 13 May, 5–8 PM | ALUO, Tobačna
✦ aksioma.org/becomingimage/workshops/wawla/

🔵 𝗙𝗿𝗲𝗲 𝗮𝗱𝗺𝗶𝘀𝘀𝗶𝗼𝗻, 𝗼𝗻𝗹𝘆 𝗿𝗲𝗴𝗶𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻 𝗿𝗲𝗾𝘂𝗶𝗿𝗲𝗱! > pretix.eu/aksioma/becomingimage/

𝑊𝐴𝑊𝐿𝐴 (𝑊ℎ𝑎𝑡 𝐴𝑟𝑒 𝑊𝑒 𝐿𝑜𝑜𝑘𝑖𝑛𝑔 𝐴𝑡) is a workshop that dives into the world of computer vision, image training datasets and the invisible human labour that makes machines see. We will get familiar with the workflow of creating a computer vision model and the steps behind assembling and preparing an image training dataset while specifically focusing on image segmentation. Segmentation is crucial for computer vision as it “points out” the parts of an image that are of value to the system. At this stage of image processing, an image is visually separated into areas of information. By outlining an object of interest (a road sign, a deer, a face) or filling in a region of particular focus (the road, the tree, shadows), these marked segments ultimately inform the computer vision model’s way of perceiving the world. What is and isn’t segmented depends on various factors, from the technology’s future application to cultural context, image resolution, operation language, subjective perception, and might differ from our own way of reading an image.

🔹 RELATED EVENTS with Simone C Niquille:
+ Exhibition: duckrabbit.tv | 12 May, 7 PM | Aksioma Project Space
+ Artist talk: Balloons etc. | 13 May, 3–4 PM | ALUO, Erjavčeva

–
In the framework of tactics&practice #17: Becoming Image curated by Marco De Mutiis.
aksioma.org/becomingimage/