Affiliation: Computer Science and Artificial Intelligence Laboratory, Dept. of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. USA.
Place: Casa de Convalescència. Carrer de Sant Antoni Maria Claret, 171, 08041 Barcelona.
It is an exciting time for computer vision. With the success of new computational architectures for visual processing, such as deep neural networks, and the access to image databases with millions of labeled examples, such as ImageNet and Places, the state of the art in computer vision is advancing rapidly. Computer vision is now present among many commercial products, such as digital cameras, web applications, security applications, and it will be a key technology in future products such as autonomous driving and robotics.
However, the beginnings of the history of computer vision were not easy. Despite that seeing comes to us effortless, making a machine to interpret the world is still a challenging research task. Building a vision machine requires solving fundamental research problems such as reconstructing the 3D world, recognizing objects despite large variability in appearance and missing information due to occlusions, reasoning about events and understanding complex visual scenes.
While still many challenges remain in computer vision, there has been incredible amount of progress in the last years, with some tasks being close to human performance. In this talk I will give a brief perspective on why computer vision is difficult and its history. I will discuss some of the reasons why previous state of the art object detectors failed. I will then describe some of our recent work on visual scene understanding, emphasizing the power of large databases of annotated images in computer vision.
Bio: Antonio Torralba received the degree in telecommunications engineering from Telecom BCN, Spain, in 1994 and the Ph.D. degree in signal, image, and speech processing from the Institut National Polytechnique de Grenoble, France, in 2000. From 2000 to 2005, he spent postdoctoral training at the Brain and Cognitive Science Department and the Computer Science and Artificial Intelligence Laboratory, MIT. He is now a Professor of Electrical Engineering and Computer Science at the Massachusetts Institute of Technology (MIT). Prof. Torralba is an Associate Editor of the International Journal in Computer Vision, and program chair for the Computer Vision and Pattern Recognition conference in 2015. He received the 2008 National Science Foundation (NSF) Career award, the best student paper award at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) in 2009, and the 2010 J. K. Aggarwal Prize from the International Association for Pattern Recognition (IAPR).