Key point detection by max pooling for tracking

Xiaoyuan Yu, Jianchao Yang, Tianjiang Wang, Thomas Huang

Research output: Contribution to journalArticlepeer-review


Inspired by the recent image feature learning work, we propose a novel key point detection approach for object tracking. Our approach can select mid-level interest key points by max pooling over the local descriptor responses from a set of filters. Linear filters are first learned from targets in first frames. Then max pooling is performed over data driven spatial supporting field to detect discriminant key points, and thus the detected key points bear higher level semantic meanings, which we apply in tracking by structured key point matching. We show that our tracking system is robust to occlusions and cluttered background. Testing on several challenging tracking sequences, we demonstrate that our proposed tracking system can achieve competitive or better performances than the state-of-the-art trackers.

Original languageEnglish (US)
Article number6840351
Pages (from-to)430-438
Number of pages9
JournalIEEE Transactions on Cybernetics
Issue number3
StatePublished - Mar 1 2015


  • Data driven max pooling
  • Object tracking
  • key point detection
  • mid-level feature learning

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Information Systems
  • Human-Computer Interaction
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Key point detection by max pooling for tracking'. Together they form a unique fingerprint.

Cite this