• Research Directions & Scope
  • An Object-based Bayesian Framework for Top-down Visual Attention. AAAI , 2012.
  • A New Synthetic Face Generation Method for Gender Discrimination. BMC Neuroscience, 2008.
  • Complementary Effects of Gaze Direction and Early Saliency in Guiding Fixations. JOV, 2014.
  • Objects do not Predict Fixations Better than Early Saliency. JOV, 2013.
  • Optimal Attentional Modulation of a Neural Population. Frontiers in comp. neuro., 2014.
  • Invariance Analysis of Modified C2 Features. MVA, 2010.
  • Online Learning of Task-driven Object-based Visual Attention control. Image and Vis. Comp., 2010.
  • Quantitative Analysis of Human-Model Agreement in Visual Saliency Modeling. IEEE TIP, 2013.
  • State-of-the-art in Visual Attention Modeling. IEEE Trans. PAMI, 2013.
  • Probabilistic Learning of Task-specific Visual Attention. CVPR, 2012.
  • Vanishing Point Attracts Eye Movements in Scene Free-viewing. CVPR Workshops, 2015.
  • What Do Eyes Reveal About the Mind? Neurocomputing, 2015.
  • Salient Object Detection: A Benchmark. IEEE TIP, 2015.
  • Bayesian Optimization Explains Human Active Search. NIPS, 2013.
  • What/where to Look Next? IEEE Trans. SMC, Part A, 2014.
  • Exploiting Local and Global Patch Rarities for Saliency Detection. CVPR, 2012.
  • Saliency Benchmark. Z. Bylinskii, T. Judd, A. Borji, L. Itti, F. Durand, A. Oliva, A. Torralba.
  • http://wowslider.com/
  • Defending Yarbus: Eye Movements Reveal Observers' Task. JOV, 2014.
Research Directions & Scope1 An Object-based Bayesian Framework for Top-down Visual Attention. AAAI , 2012.2 A New Synthetic Face Generation Method for Gender Discrimination. BMC Neuroscience, 2008. 3 Complementary Effects of Gaze Direction and Early Saliency in Guiding Fixations. JOV, 2014.4 Objects do not Predict Fixations Better than Early Saliency. JOV, 2013.5 Optimal Attentional Modulation of a Neural Population. Frontiers in comp. neuro., 2014.6 Invariance Analysis of Modified C2 Features. MVA, 2010.7 Online Learning of Task-driven Object-based Visual Attention control. Image and Vis. Comp., 2010.8 Quantitative Analysis of Human-Model Agreement in Visual Saliency Modeling. IEEE TIP, 2013.9 State-of-the-art in Visual Attention Modeling. IEEE Trans. PAMI, 2013.10 Probabilistic Learning of Task-specific Visual Attention. CVPR, 2012.11 Vanishing Point Attracts Eye Movements in Scene Free-viewing. CVPR Workshops, 2015.12 What Do Eyes Reveal About the Mind? Neurocomputing, 2015.13 Salient Object Detection: A Benchmark. IEEE TIP, 2015.14 Bayesian Optimization Explains Human Active Search. NIPS, 2013.15 What/where to Look Next? IEEE Trans. SMC, Part A, 2014.16 Exploiting Local and Global Patch Rarities for Saliency Detection. CVPR, 2012.17 Saliency Benchmark. Z. Bylinskii, T. Judd, A. Borji, L. Itti, F. Durand, A. Oliva, A. Torralba. 18 What Stands Out in a Scene? Vision research, 2013.19 Defending Yarbus: Eye Movements Reveal Observers' Task. JOV, 2014.20
wow slider by WOWSlider.com v8.6m

Welcome

Research in VLL generally focuses on computational neuroscience and artificial intelligence with emphasis on vision and learning. We are interested in both computer and human vision research. Regarding computer vision, we strive to develop purely computational or biologically-inspired algorithms for solving real-world vision tasks. With respect to human vision, we aspire to understand neural and behavioral mechanisms by which humans (as well as some animals) perceive the visual world to construct meaningful interpretations. Some topics of our interest are: Bottom-up and Top-down Visual Attention, Visual Search, Ego-centric Vision, Mind Reading (By means of eye movements), Object Recognition, Detection, and Natural Scene Understanding (e.g., Rapid Scene Categorization), ...

Learning is another research focus in VLL. Some related topics include: Active Learning, Optimal Learning, Information Foraging, Bayesian Search Theory, Function Learning, Bayesian Global Optimization, Gaussian Processes, Reinforcement Learning, Category Learning, Feature Learning, Theory of Mind, Biology-inspired Computing, ...

We conduct research studies which include both an experimental component (e.g., psychophysics, eye-tracking, EEG, fMRI, etc) and a computational component (e.g., data modeling, neural networks, neurally-inspired artificial intelligence, ...).

Computer Science Department, University of Wisconsin Milwaukee | Send Email: Ali Borji