Discovering thematic objects in image collections and videos

Junsong Yuan*, Gangqiang Zhao, Yun Fu, Zhu Li, Aggelos K. Katsaggelos, Ying Wu

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

32 Scopus citations


Given a collection of images or a short video sequence, we define a thematic object as the key object that frequently appears and is the representative of the visual contents. Successful discovery of the thematic object is helpful for object search and tagging, video summarization and understanding, etc. However, this task is challenging because 1) there lacks a priori knowledge of the thematic objects, such as their shapes, scales, locations, and times of re-occurrences, and 2) the thematic object of interest can be under severe variations in appearances due to viewpoint and lighting condition changes, scale variations, etc. Instead of using a top-down generative model to discover thematic visual patterns, we propose a novel bottom-up approach to gradually prune uncommon local visual primitives and recover the thematic objects. A multilayer candidate pruning procedure is designed to accelerate the image data mining process. Our solution can efficiently locate thematic objects of various sizes and can tolerate large appearance variations of the same thematic object. Experiments on challenging image and video data sets and comparisons with existing methods validate the effectiveness of our method.

Original languageEnglish (US)
Article number6112717
Pages (from-to)2207-2219
Number of pages13
JournalIEEE Transactions on Image Processing
Issue number4
StatePublished - Apr 2012


  • Image data mining
  • thematic object discovery

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Discovering thematic objects in image collections and videos'. Together they form a unique fingerprint.

Cite this