Graduate Student, UC Berkeley
Email
Abstract
Building Systems that Talk About What They See
Powered by deep convolutional networks and large scale visual datasets, modern visual systems are capable of accurately recognizing thousands of visual categories. However, images contain so much more than categorical labels: they contain information about where objects are located (in a forest or in a kitchen?), what attributes an object has (red or blue?), and, importantly, how objects interact with other objects in a scene (is the child sitting on a sofa, or running in a field?). Natural language provides an efficient and intuitive way for visual systems to convey important information to a human about a visual scene. This poster discusses visual description systems which can not only recognize objects, but place them in the correct visual context in order to convey important information about an image.
Bio
Lisa Anne Hendricks is a fifth year Ph.D. student in the Electrical Engineering and Computer Science department at University of California at Berkeley. She is a member of the Berkeley Artificial Intelligence Research (BAIR) lab and is advised by Trevor Darrell. In 2013 she received her B.S.E.E. in Electrical and Computer Engineering from Rice University (summa cum laude).
Lisa Anne’s research interests span deep learning, computer vision, and natural language processing. Her Ph.D. work has focused on building deep learning models which can both express information about visual content using natural language and retrieve visual information given natural language queries. She has been awarded an NDSEG Fellowship, UC Berkeley Chancellor’s Fellowship, Huawei Fellowship, and Adobe Fellowship. Lisa Anne was the co-president of Women in Computer Science and Engineering (WICSE) at UC Berkeley during the 2015-2016 school year and co-organized the second Women in Computer Vision (WiCV) workshop at CVPR 2016.