[Prime Session] Generalist real-time computer vision model By 王建堯

議題

[Prime Session] Generalist real-time computer vision model

RB105 [[ new Date( '2024-08-03 01:00:00+00:00' ).toLocaleDateString('ja', {year: 'numeric', month: '2-digit', day: '2-digit'}) ]] [[ new Date( '2024-08-03 01:00:00+00:00' ).toLocaleTimeString('zh-Hant', {hour12: false, hour: '2-digit', minute:'2-digit'}) ]] ~ [[ new Date( '2024-08-03 01:45:00+00:00' ).toLocaleTimeString('zh-Hant', {hour12: false, hour: '2-digit', minute:'2-digit'}) ]] 中文 Chinese

加入行事曆加入關注加入關注已關注

通才模型能夠以一個模型處理各式各樣的任務。然而，現今的通才模型非常龐大且非常耗時，大大限縮了通才模型在現實生活中的應用層面。在這場演講中，我們將介紹我們如何將通才電腦視覺模型向即時系統推進。

搶先在 Slido 提問：https://app.sli.do/event/uR4FwktBjWUTbrpbkz8Fz4

共筆: https://hackmd.io/lKSWOVYxS26zA8jSDKva6g 下方共筆連結待更新。

講者

王建堯

Chien-Yao Wang received the Ph.D. degree in Computer Science and Information Engineering from National Central University, Zhongli, Taiwan, in 2017. He is currently an Assistant Research Fellow with the Institute of Information Science, Academia Sinica, Taiwan. His research interests include signal processing, deep learning, and machine learning. Currently, his research focuses on multi-task representation learning for multimodal signal.

Main Track 主議程軌 XWKCBM prime session