Human-in-the-loop Computer Vision

Human-in-the-loop Computer Vision


​Exploring novel means of involving human judgment in computer vision and image processing methodology. This includes studying perceptual elements of image quality, saliency, and memorability and linking them to low-level image features, which can be used to develop more effective and perceptually-relevant recognition and compression techniques​.​​​​

Selected Publications


 Do Humans Fixate on Interest Points?

[pdf] [bibtex]​ [oral]​​


 Improving Saliency Models by Predicting Human Fixation Patches​



  1. Rachit Dubey, Akshat Dave, Bernard Ghanem, "Improving Saliency Models by Predicting Human Fixation Patches", Asian Conference on Computer Vision (ACCV 2014)
  2. Akshat Dave*, Rachit Dubey*, Bernard Ghanem, "Do Humans Fixate on Interest Points?", International Conference on Pattern Recognition (ICPR2012) 
  3. Bernard Ghanem, Esther Resendiz, and Narendra Ahuja, "Segmentation-Based Perceptual Image Quality Assessment (SPIQA)", International Conference on Image Processing (ICIP 2008)