活動介紹：

題目: Bigger data and bigger models for visual recognition and social media 

主講人: Dr. Liangliang Cao

時間：5月19日下午14：00

地點：軟件所5號樓4層第一會議室

自由研討和座談

時間：5月19日下午15：00

地點：軟件所5號樓4層第一會議室

內容介紹：

In the past decade, the field of visual recognition has experienced a number of significant changes. The size of the datasets collected by vision researchers has grown substantially. For example, the ImageNet LSVRC dataset in 2010 is 150 times bigger than the Caltech101 dataset in 2003. On the other hand, the visual recognition models also become dramatically bigger. The-state-of-the-art deep CNN models have 1000 times more parameters than the tradition bag of words model in the early 2000s. In this talk, I plan to give a personal overview of these evolvements in visual recognition, and show how modelsdata reinforce each other’s growth. I would like to share our experiences of winning the First Place in ImageNet Large Scale Visual Recognition Challenge 2010 as well as the First Place in ImageCLEF medical image recognition 2012&2013 and examine the influence of scalable techniques in these visual recognition problems. A few our recent demos of visual recognition, text recognition and social media mining will be shown during the talk together with discussions of future research.

主講人介紹：

Dr. Liangliang Cao is a research staff member in IBM T.J. Waston Research Center. He also holds an adjunct faculty position at the Columbia University in the City of New York. His work has received three times the IBM Research Division Award (individual award) as well as one Outstanding Technical Accomplishment (group award). He is now leading the efforts of building big data learning toolkit for IBM Multimedia group. Before joining IBM, he did summer interns at Kodak, Microsoft, and NEC Research Labs and received his Ph.D. from University of Illinois at Urbana-Champaign. He received the best paper award from  the International Workshop on Big Data Mining, 2012 He was listed as an IBM Emerging Leader in Multimedia and Signal Processing in 2010 and Facebook Fellowship Finalist in 2010. He was a general chair of Greater New York Area Multimedia and Vision Meeting from 2012 to 2013. He was also a founding chair of ACM workshop on Geo-Multimedia. He was an area chair of ACM Multimedia 2012 and WACV 2014

活動宣傳：軟件所青聯舉辦計算機視覺與新媒體技術交流研討會