• Publications
  • Influence
Image retrieval: Ideas, influences, and trends of the new age
TLDR
We have witnessed great interest and a wealth of promise in content-based image retrieval as an emerging technology. Expand
  • 3,493
  • 197
  • PDF
Studying Aesthetics in Photographic Images Using a Computational Approach
TLDR
Aesthetics, in the world of art and photography, refers to the principles of the nature and appreciation of beauty. Expand
  • 556
  • 58
  • PDF
Content-based image retrieval: approaches and trends of the new age
TLDR
In this paper, we discuss some of the key contributions in the current decade related to image retrieval and automated image annotation, spanning 120 references. Expand
  • 519
  • 33
  • PDF
Aesthetics and Emotions in Images
TLDR
In this tutorial, we define and discuss key aspects of the problem of computational inference of aesthetics and emotion from images. Expand
  • 280
  • 15
  • PDF
IMAGINATION: a robust image-based CAPTCHA generation system
TLDR
We propose IMAGINATION (IMAge Generation for INternet AuthenticaTION), a system for the generation of attack-resistant, user-friendly, image-based CAPTCHAs. Expand
  • 149
  • 10
  • PDF
ACQUINE: aesthetic quality inference engine - real-time automatic rating of photo aesthetics
TLDR
We present ACQUINE - Aesthetic Quality Inference Engine, a publicly accessible system which allows users to upload their photographs and have them rated automatically for aesthetic quality. Expand
  • 77
  • 10
  • PDF
Algorithmic inferencing of aesthetics and emotion in natural images: An exposition
TLDR
We define the aesthetics gap and discuss key aspects of the problem of aesthetics and emotion inference in natural images, presenting statistical analysis of and insights into them. Expand
  • 131
  • 8
  • PDF
Toward bridging the annotation-retrieval gap in image search by a generative modeling approach
TLDR
We propose an annotation-driven image retrieval approach and argue that under a number of different scenarios, this is very effective for semantically meaningful image search. Expand
  • 59
  • 4
Spectrum Fusion: Using Multiple Mass Spectra for De Novo Peptide Sequencing
TLDR
We report on a new algorithm for combining the information from several mass spectra of the same peptide. Expand
  • 17
  • 4
Exploiting the Human–Machine Gap in Image Recognition for Designing CAPTCHAs
TLDR
We study the effect of controlled distortions of varying nature and strength on human and machine recognizability, and show that they can be exploited to prevent automated network attacks. Expand
  • 46
  • 3
  • PDF