Searching for objects driven by context

Bogdan Alexe, Nicolas Heess, Yee Whye Teh, Vittorio Ferrari

Research output: Chapter in Book/Report/Conference proceedingConference contribution


The dominant visual search paradigm for object class detection is sliding windows. Although simple and effective, it is also wasteful, unnatural and rigidly hardwired.We propose strategies to search for objects which intelligently explore the space of windows by making sequential observations at locations decided based on previous observations. Our strategies adapt to the class being searched and to the content of a particular test image, exploiting context as the statistical relation between the appearance of a window and its location relative to the object, as observed in the training set. In addition to being more elegant than sliding windows, we demonstrate experimentally on the PASCAL VOC 2010 dataset that our strategies evaluate two orders of magnitude fewer windows while achieving higher object detection performance.
Original languageEnglish
Title of host publicationNIPS 2012
Number of pages9
Publication statusPublished - 1 Dec 2012


  • object detection, object recognition


Dive into the research topics of 'Searching for objects driven by context'. Together they form a unique fingerprint.

Cite this