My research program is in the field of Computational Visual Cognition, a framework that strives to identify the substrates of complex visual recognition tasks and to develop models inspired by human perception and cognition. The natural visual environment is composed of three-dimensional objects, with textures, colors, and materials, embedded in an explicit spatial layout. Yet, the human brain understands scenes, places and events quickly and effortlessly, outperforming the most advanced artificial vision system. In the lab, we use multi-disciplinary techniques from behavioral sciences, cognitive neuroscience and computational vision, to identify key principles of human object, scene and space understanding and evaluate the capacity and fidelity of human memory systems for guiding the development of computational and theoretical frameworks in computational cognition. Ultimately, the results of characterizing human perceptual and cognitive abilities and limitations in a natural setting holds promise for inspiring the next generation of artificial vision systems but also gives insights for the understanding of visual and cognitive disorders. Our research programs bring together disciplines such as perceptual science, cognitive science and neuroscience, neuropsychology, photography, architecture, image processing, computer vision and computer graphics.
Alvarez, G.A., & Oliva, A. (2009). Spatial Ensemble Statistics:
Efficient Codes that can be Represented with Reduced Attention.
Proceedings of the National Academy of Sciences, 106, 7345-7350.
Greene, M.R., & Oliva, A. (2009). Recognition of natural scenes from global properties: Seeing the forest without representing the trees. Cognitive Psychology, 58(2), 137-179.
Brady, T.F., Konkle, T., Alvarez, G.A., & Oliva, A. (2008). Remembering Thousands of Objects with High Fidelity. Proceedings of the National Academy of Sciences, 105 (38), 14325-14329.
Brady, T. F., & Oliva, A. (2008). Statistical Learning using Real World Scenes: Extracting Categorical Regularities without Conscious Intent. Psychological Science, 19(7), 678-685.
Oliva, A., & Torralba, A. (2007). The role of context in object recognition. Trends in Cognitive Science. 11(12), 520-527.
Serre, T., Oliva, A., & Poggio, T. (2007). A feed forward architecture accounts for rapid categorization. Proceedings of the National Academy of Sciences, 104 (15), 6424-6429.
Oliva, A., Torralba, A., & Schyns, P.G. (2006). Hybrid Images. ACM Transactions on Graphics (Siggraph), 25, 3, 527-532.
Torralba, A., Oliva, A., Castelhano, M., & Henderson, J.M. (2006). Contextual guidance of eye movements and attention in real-world scenes: the role of global features in object search. Psychological Review, 113, 766-786.