Paper Info
Title
From Where and How to What We See
Abstract
Eye movement studies have confirmed that overt attention is highly biased towards faces and text regions in images. In this paper we explore a novel problem of predicting face and text regions in images using eye tracking data from multiple subjects. The problem is challenging as we aim to predict the semantics (face/text/background) only from eye tracking data without utilizing any image information. The proposed algorithm spatially clusters eye tracking data obtained in an image into different coherent groups and subsequently models the likelihood of the clusters containing faces and text using a fully connected Markov Random Field (MRF). Given the eye tracking data from a test image, it predicts potential face/head (humans, dogs and cats) and text locations reliably. Furthermore, the approach can be used to select regions of interest for further analysis by object detectors for faces and text. The hybrid eye position/object detector approach achieves better detection performance and reduced computation time compared to using only the object detection algorithm. We also present a new eye tracking dataset on 300 images selected from ICDAR, Street-view, Flickr and Oxford-IIIT Pet Dataset from 15 subjects.
Year
DOI
Venue
2013
10.1109/ICCV.2013.83
ICCV
Keywords
Field
DocType
potential face,eye movement study,text location,text region,object detector,image information,object detection algorithm,object detector approach,hybrid eye position,new eye tracking dataset,markov processes,face recognition
Computer vision,Object detection,Facial recognition system,Markov process,Pattern recognition,Markov random field,Computer science,Eye tracking,Eye movement,Artificial intelligence,Standard test image,Computation
Conference
Citations 
PageRank 
References 
9
0.49
30
Authors
5
Name
Order
Citations
PageRank
S. Karthikeyan114815.16
Vignesh Jagadeesh221712.74
Renuka Shenoy3100.85
Miguel Ecksteinz490.49
B. S. Manjunath57561783.37