Towards deeper understanding of Video and Language
主講人:蔣路,Google
時(shí)間:12月21日上午10:00~11:30
地點(diǎn):計(jì)算所421會(huì)議室
報(bào)告摘要:
In this talk, we first briefly discuss an efficient and scalable retrieval method for Internet video content that we developed at Carnegie Mellon University. We implemented E-Lamp Lite, the first of its kind content-based search engine for Internet videos. After that, we will discuss our recent research on vision+language and weakly-supervised deep learning at Google AI. A few interesting problems such as video question answering and video understanding will be discussed to showcase our deep learning research.
報(bào)告人簡介:
蔣路,谷歌科學(xué)家,谷歌云人工智能(李飛飛)團(tuán)隊(duì)創(chuàng)始成員。曾于2017年獲得卡內(nèi)基梅隆大學(xué)人工智能(語言技術(shù))博士學(xué)位。曾于2008年2011年獲得西安交通大學(xué)工學(xué)學(xué)士與碩士學(xué)位。長期致力于計(jì)算機(jī)視覺,機(jī)器學(xué)習(xí)和多媒體的交叉領(lǐng)域研究。他是Yahoo Fellowship和歐盟的Erasmus Mundus Scholarship的獲得者。作為核心成員獲得美國國家標(biāo)準(zhǔn)總局(NIST)舉辦的多項(xiàng)大賽中獲得冠軍。近年來在包括 NIPS, ICML, CVPR, ECCV, MM, AAAI, IJCAI 等發(fā)表論文20余篇。他是ACM Multimedia, AAAI, IJCAI, CVPR 等會(huì)議的技術(shù)程序委員,JMLR, TPAMI, TMM, CVIU等期刊的審稿人。工作曾經(jīng)獲得IEEE SLT的最佳論文(best poster)和ACM ICMR的最佳論文提名(best paper candidate)。