时间：9月19日（星期五）下午14：30
地点：浙江大学紫金港校区蒙民伟楼402房间
报告人: 盧策吾　博士
主持人：章国锋　副教授
报告题目：Video Abnormal Event Detection at 1000FPS
Abstract：Fast abnormal event detection meets the growing demand to process an enormous number of surveillance videos. Based on the inherent redundancy of video structures, we propose an efficient sparse combination learning framework with both batch and online solvers. It achieves decent performance in the detection phase without compromising result quality. The extremely fast execution speed is guaranteed owing to the fact that our method effectively turns the original complicated problem into a few costless smallscale least square optimizations. Our method reaches high detection rates on benchmark datasets at a speed of 1000 - 1200 frames per second on average when computing on an ordinary single core desktop PC using MATLAB.
Bio：Dr. Lu Cewu is currently a research fellow in the Department of Computer Science and Engineering at Hong Kong University of Science and Technology.  His research interests include computer vision and machine learning. He serves as an associate editor of Journal gtCVPR and reviewer of many top journals such as PAMI and TOG. He has a total of 14 (12 as first author) papers published in top-ranked refereed journals and conference proceedings including one best paper award at NPAR 2012 and one most cited paper among all papers in SIGGRAPH Asia 2011. He (as first-author) earn the 4th place in Imagenet Large Scale Visual Recognition Challenge (ILSVRC) 2014 object detection track among 38 teams from world.