Timezone: »

Im2Text: Describing Images Using 1 Million Captioned Photographs
Vicente Ordonez · Girish Kulkarni · Tamara L Berg

Wed Dec 14 02:04 AM -- 02:08 AM (PST) @

We develop and demonstrate automatic image description methods using a large captioned photo collection. One contribution is our technique for the automatic collection of this new dataset -- performing a huge number of Flickr queries and then filtering the noisy results down to 1 million images with associated visually relevant captions. Such a collection allows us to approach the extremely challenging problem of description generation using relatively simple non-parametric methods and produces surprisingly effective results. We also develop methods incorporating many state of the art, but fairly noisy, estimates of image content to produce even more pleasing results. Finally we introduce a new objective performance measure for image captioning.

Author Information

Vicente Ordonez (University of North Carolina at Chapel Hill)
Girish Kulkarni (Stony Brook University)
Tamara L Berg (Stony Brook University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors