主 题: Multi-component models for object detection
报告人: Dr. Chunhui Gu (Google Inc.)
时 间: 2012-10-18 14:00-15:00
地 点: 理科一号楼1114
In this talk, I will present a multi-component approach for object detection. Rather than attempting to represent an object category with a monolithic model, or pre-defining a reduced set of aspects, we form visual clusters from the data that are tight in appearance and configuration spaces. We train individual classifiers for each component, and then learn a second classifier that operates at the category level by aggregating responses from multiple components. In order to reduce computation cost during detection, we adopt the idea of object window selection, and our segmentation-based selection mechanism produces fewer than 500 windows per image while preserving high object recall. When compared to the leading methods in the challenging VOC PASCAL 2010 dataset, our multi-component approach obtains highly competitive results. Furthermore, unlike monolithic detection methods, our approach allows the transfer of finer-grained semantic information from the components, such as keypoint location and segmentation masks.
Bio: Chunhui Gu\'s research focuses on computer vision and machine learning, specifically in object detection and segmentation. He joined Google in January 2012 and works on applying computer vision techniques to various Google products. Before that, he received his PhD in Electrical Engineering and Computer Sciences from UC Berkeley in 2012, and bachelor\'s degree in Electrical Engineering from California Institute of Technology in 2006.