应gg999策略手机白菜邀请,法国巴黎高等师范学院和法国国家信息与自动化研究院Jean Ponce教授到我校访问并作学术报告
报告题目: Unsupervised Object Discovery and Localization in Images and Videos
报告时间:10月23日(周五)下午3:00-5:00
报告地点:科学馆207
报告人简介:
Jean Ponce教授是计算机视觉领域著名专家。2005年之前先后在麻省理工学院、斯坦福大学工作,并在伊利诺伊大学香槟分校获终身教授职位。现任法国巴黎高等师范学院计算机系主任,法国国立信息与自动化研究院(INRIA)Willow项目组主任。他发表了超过120篇计算机视觉和机器人方面的论文,并编写了著名的计算机视觉教材《计算机视觉:一种现代方法》。他是IEEE Fellow, 在2003~2008年担任IJCV(International Journal of Computer Vision)主编, 并任1997年和2000年两届CVPR( IEEE Conference on Computer Vision and Pattern Recognition)大会主席,以及2008年ECCV (European Conference on Computer Vision )大会主席。
报告摘要:After a brief overview of computer vision research in my group (INRIA-willow), I will address in this presentation the unsupervised discovery and localization of dominant objects from a noisy collection of images or videos. The setting of this problem is fully unsupervised, without even class labels or any assumption of a single dominant class, and thus far more general than those of typical colocalization or weakly-supervised localization tasks. We tackle the discovery and localization problem using a part-based region matching approach. For each image/frame, a dominant object is localized by comparing the scores of candidate regions and selecting those that stand out over other regions containing them. Given a video collection, we also associate similar object regions along consecutive frames within the same video, thus achieving unsupervised tracking. Extensive experimental evaluations on standard benchmarks demonstrate that the proposed approach substantially outperforms the current state of the art in colocalization, and achieves robust object discovery in challenging mixed-class datasets.
欢迎感兴趣的师生参加!