Recognition (2016)
辯認 (2016)
Fabrica (Italy)
Fabrica 意大利傳播硏究中心 (意大利)
Can a machine make us look afresh at great art through the lens of today’s world?
Recognition, winner of IK Prize 2016 for digital innovation, is an artificial intelligence program that compares up-to-the-minute photojournalism with British art from the Tate collection.
Over three months, Recognition will create an ever-expanding virtual gallery by searching through Tate’s collection of British art and archive material online, comparing artworks with news images from Reuters based on visual and thematic similarities twenty-four hours a day. The result will be a time capsule of the world represented in diverse types of images, past and present.
Recognition incorporates multiple artificial intelligence technologies, including computer vision capabilities such as object recognition, facial recognition, colour and composition analysis; and natural language processing of text associated with images, allowing it to analyse context and subject matter and produce written descriptions of image comparisons.
A display at Tate Britain accompanies the online project offering visitors the chance to interrupt the machine’s selection process. The results of this experiment – to see if an artificial intelligence can learn from the many personal responses humans have when looking at images – will be presented on the virtual gallery site at the end of the project.
機器能讓我們通過當今世界的鏡頭重新審視偉大的藝術嗎?
《Recognition 辯認》,是英國泰特美術館2016年IK奬數碼創新得奬作品。作品通過人工智能(AI)辯識圖像技術,結合泰特美術館館藏,將當今的新聞攝影圖片,利用作品比對泰特類似的館藏畫作,體驗古今交錯的奇妙感受。
三個月以來,作品通過在線搜索泰特美術館的英國藝術館藏及檔案資料,將館藏作品與路透社的新聞圖像根據每天廿四小時的視覺和主題相似性進行比較,以創建一個不斷擴展的虛擬畫廊。作品的結果將是代表著過去與現在各類圖像的時間膠囊。
作品併合了多種人工智能技術,包含著計算機視覺功能,如物體識別、面部識別、頻色和成份分析等,同時也包括與圖像相關的文本自然語言處理,允許它分析上下文和主題,並產生圖像比較的書面論述。
英國泰特美術館的展示結合在線功能,為參觀者提供了中斷機器選擇過程的機會。這個實驗的結果是要看看人工智能能否在觀察人們在查看圖像時的多種個人反應的過程中學習,並在項目結束時同時於虛擬畫廊中呈現。
Fabrica (Italy)
Fabrica 意大利傳播硏究中心 (意大利)
Fabrica is a communication research centre based in Treviso, Italy, part of the Benetton Group. Established in 1994, Fabrica offers to young researchers from around the world a one-year scholarship within disciplines such as design, visual communication, photography, interaction, video, music and journalism. The Fabrica team are Coralie Gourguechon, Monica Lanaro, Angelo Semeraro and Isaac Vallentin.
Jolibrain are artificial intelligence specialists based in Toulouse, France. Jolibrain is the editor of the DeepDetect deep learning API and server used in a variety of industries. Jolibrain are experts across the field of A.I. and its applications in a range of industries, from image recognition to NLP applications and cyber security.
Fabrica是一家位於意大利特雷維索的傳播硏究中心,隸屬於貝納通集團,於1994年成立。中心旨於為來自世界各地的年輕硏究人員提供為期一年的奬學金,包括設計、視覺傳訊、攝影、互動設計、錄像、音樂及新聞傳播等。是次項目團隊包括:Coralie Gourguechon、Monica Lanaro、Angelo Semeraro 以及 Isaac Vallentin。
Jolibrain是位於法國圖盧茲的人工智能專家組織,是用於各種行業的DeepDetect深度學習API和服務器的編輯。Jolibrain是人工智能領域以及其於各行業應用的專家,技術層面由圖像識別至NLP應用及網絡安全不等。