Title:Towards deeper understanding of Video and Language
Time:09:30 ~10:45on December 21
Venue:Room 446 in ICT
Summary:
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.
Brief
introduction of the speaker: Jiang Lu, a Google scientist, is a founding member of the Google Cloud artificial Intelligence (Li Feifei) team. He received his Ph.D. degree in artificial Intelligence (language Technology) from Carnegie Mellon University in 2017. He received his Bachelor of Engineering and Master\'s degree from Xi\'an Jiaotong University in 2008 and 2011. For a long time, he has devoted himself to the cross-field research of computer vision, machine learning and multimedia. He is the winner of Yahoo Fellowship and Erasmus Mundus Scholarship of the European Union. As a core member, he won the championship in many competitions organized by (NIST) of the National Standards Administration of the United States. In recent years, he has published more than 20 papers, including NIPS, ICML, CVPR, ECCV, MM, AAAI, IJCAI and so on. He is a reviewer of journals such as, JMLR, TPAMI, TMM, CVIU. He was in the technical procedure committee of the ACM Multimedia, AAAI, IJCAI, CVPR and other meetings. He won IEEE SLT\'s best paper (best poster) and ACM ICMR\'s best paper nomination (best paper candidate).
Download: