Xiaoyu Fang

Learn More
Content-based video copy detection over large corpus with complex transformations is important but challenging. It is not surprising that most existing methods fall short of either sufficient robustness to detect severely deformed copies or high accuracy to localize copy segments. In this paper, we propose a video copy detection approach which exploits(More)
Event detection in crowded surveillance videos is a challenging yet important problem. In this paper, we present our eSur (Event detection system on SURveillance video) system , which is derived from TRECVid'12 surveillance tasks. Currently, eSur attempts to detect two categories of events: 1) pair-wise events (e.g., PeopleMeet, PeopleSplitUp and Embrace);(More)
Objectives: To identify current practices and care gaps for elderly patients admitted following a hip fracture, and to characterize patients' patterns of functional recovery over 1-year. Relevance Increased awareness of existing gaps and improving our understanding of patients' recovery can help optimize patients' outcomes. Methods: Forty community-dwelling(More)
In this paper, we describe our system for the surveillance events detection task in TRECVid 2010. We focused on pair-wise events (e.g., PeopleMeet, PeopleSplitUp, Embrace) that need to explore the relationship between two active persons. For our team had participated in the TRECVid SED task in 2009, we developed the system based on the old one. The(More)
  • 1