報(bào)告題目：On the Connection between Vision and Language
報(bào)告人：張含望博士
單位：美國(guó)哥倫比亞大學(xué)
報(bào)告時(shí)間：2016年12月16日（周五）下午2:00-3:00
報(bào)告地點(diǎn)：逸夫科教樓508會(huì)議室
報(bào)告人簡(jiǎn)介： 張含望博士于2009年在浙江大學(xué)獲得學(xué)士學(xué)位，于2014年在新加坡國(guó)立大學(xué)獲得博士學(xué)位，現(xiàn)為美國(guó)哥倫比亞大學(xué)計(jì)算機(jī)系DVMM實(shí)驗(yàn)室的研究員。張博士長(zhǎng)期致力于多媒體與機(jī)器視覺領(lǐng)域研究，在CVPR、ICCV、ACM Multimedia、SIGIR、AAAI、TKDE、TIST、TIP、TOMMCAP等多個(gè)頂級(jí)國(guó)際會(huì)議和期刊發(fā)表論文四十余篇（包括十次oral論文），曾獲得多媒體領(lǐng)域頂級(jí)國(guó)際會(huì)議ACM Multimedia最佳演示提名獎(jiǎng)（2012），ACM Multimedia最佳學(xué)生論文獎(jiǎng)（2013），新加坡國(guó)立大學(xué)計(jì)算機(jī)學(xué)院最佳博士論文獎(jiǎng)（2014），SIGIR最佳論文提名獎(jiǎng)(2016)。張博士擔(dān)任了Multimedia Tools and Applications、Neurocomputing等多個(gè)國(guó)際期刊副主編，亦是TIP、TMM、TCSVT、TOMMCAP等頂尖學(xué)術(shù)期刊審稿人。
報(bào)告內(nèi)容摘要：We are experiencing an unprecedented evolution of deep learning techniques. As a holy grail of Artificial Intelligence, the task of connecting vision and language perhaps gains the most appreciable benefits in recent years. For example, today’s machines are able to outperform humans in large-scale visual recognition, describe or answer questions about an image/video in natural language; and none of the above is thinkable just a decade ago. In this talk, I will first provide a brief retrospect of the progress of the connection in the pre- and current deep learning era. Then, I will introduce our recent works in addressing what is missing in the state-of-the-art paradigm, including the groundings of open-vocabulary, social networks, and deeper scene understanding. At last, several interesting future research directions are discussed.
太陽集團(tuán)tyc5997
TOP
