Attentive Object Detection Using an Information Theoretic Saliency Measure

Gerald Fritz, Christin Seifert, Lucas Paletta, Horst Bischof

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

18 Citations (Scopus)


A major goal of selective attention is to focus processing on relevant information to enable rapid and robust task performance. For the example of attentive visual object recognition, we investigate here the impact of top-down information on multi-stage processing, instead of integrating generic visual feature extraction into object specific interpretation. We discriminate between generic and specific task based filters that select task relevant information of different scope and specificity within a processing chain. Attention is applied by tuned early features to selectively respond to generic task related visual features, i.e., to information that is in general locally relevant for any kind of object search. The mapping from appearances to discriminative regions is then modeled using decision trees to accelerate processing. The focus of attention on discriminative patterns enables efficient recognition of specific objects, by means of a sparse object representation that enables selective, task relevant, and rapid object specific responses. In the experiments, the performance in object recognition from single appearance patterns dramatically increased considering only discriminative patterns, and evaluation of complete image analysis under various degrees of partial occlusion and image noise resulted in highly robust recognition, even in the presence of severe occlusion and noise effects. Finally, preliminary results on attention for both generic and specific object detection demonstrated successful indexing to relevant object locations within a cluttered environment.
Original languageEnglish
Title of host publicationAttention and Performance in Computational Vision
Subtitle of host publicationSecond International Workshop, WAPCV 2004, Prague, Czech Republic, May 15, 2004, Revised Selected Papers
EditorsLucas Paletta, John K. Tsotsos, Erich Rome, Glyn Humphreys
Place of PublicationBerlin, Heidelberg
ISBN (Electronic)978-3-540-30572-9
ISBN (Print)978-3-540-24421-9
Publication statusPublished - 1 May 2004
Externally publishedYes
Event2nd International Workshop on Attention and Performance in Computational Vision, WAPCV 2004 - Czech Technical University, Prague, Czech Republic
Duration: 15 May 200415 May 2004
Conference number: 2

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Conference2nd International Workshop on Attention and Performance in Computational Vision, WAPCV 2004
Abbreviated titleWAPCV
Country/TerritoryCzech Republic


  • Object Recognition
  • Recognition Rate
  • Majority Vote
  • Partial Occlusion
  • Interest Operator
  • n/a OA procedure


Dive into the research topics of 'Attentive Object Detection Using an Information Theoretic Saliency Measure'. Together they form a unique fingerprint.

Cite this