報(bào)告題目:Vision and Language: Bridging Vision and Language with Deep Learning
報(bào)告人:梅濤 研究員
單位:微軟亞洲研究院
時(shí)間: 2016年12月13日 (星期二) 上午9:30
地點(diǎn):學(xué)術(shù)活動(dòng)中心二樓小報(bào)告廳
Abstract: Visual recognition has been a fundamental challenge in computer vision for decades. Thanks to the recent development of deep learning techniques, researchers are striving to bridge vision (image and video) and natural language, which has become an emerging research area. We will present a few recent advances bridging vision and language with deep learning techniques, including image and video captioning, image and video chatting, storytelling, vision and language grounding, datasets, grand challenges, and open issues. In particular, we will introduce our recently developed approaches which investigate semantic attributes for image and video captioning.
報(bào)告人簡(jiǎn)介:
梅濤博士,微軟亞洲研究院資深研究員,國(guó)際模式識(shí)別學(xué)會(huì)會(huì)士,國(guó)際計(jì)算機(jī)協(xié)會(huì)杰出科學(xué)家,中國(guó)科技大學(xué)和中山大學(xué)兼職教授博導(dǎo)。他分別于2001年和2006年在中國(guó)科技大學(xué)獲學(xué)士和博士學(xué)位。主要研究興趣為多媒體分析和計(jì)算機(jī)視覺(jué),在國(guó)際頂級(jí)學(xué)術(shù)期刊和會(huì)議上發(fā)表論文100余篇,先后10次榮獲最佳論文獎(jiǎng),擁有17項(xiàng)美國(guó)專利,其研究成果多次被轉(zhuǎn)化到微軟的產(chǎn)品和服務(wù)中。在微軟亞洲研究院期間,先后指導(dǎo)了來(lái)自全球的80多名實(shí)習(xí)生,并培養(yǎng)了四位微軟學(xué)者。他目前同時(shí)擔(dān)任IEEE和ACM多媒體匯刊的編委(IEEE TMM和ACM TOMM),并且是多個(gè)國(guó)際多媒體會(huì)議的大會(huì)主席和程序委員會(huì)主席。
太陽(yáng)集團(tuán)tyc5997