Skip to Content

Will Artificial Intelligence Win the Caption Contest?

Neural networks have mastered the ability to label things in images, and now they’re learning to tell stories from a set of photos.

When social-media users upload photographs and caption them, they don’t just label their contents. They tell a story, which gives the photos context and additional emotional meaning.

A paper published by Microsoft Research describes an image captioning system that mimics humans’ unique style of visual storytelling. Companies like Microsoft, Google, and Facebook have spent years teaching computers to label the contents of images, but this new research takes it a step further by teaching a neural-network-based system to infer a story from several images. Someday it could be used to automatically generate descriptions for sets of images, or to bring humanlike language to other applications for artificial intelligence.

“Rather than giving bland or vanilla descriptions of what’s happening in the images, we put those into a larger narrative context,” says Frank Ferraro, a Johns Hopkins University PhD student who coauthored the paper. “You can start making likely inferences of what might be happening.”

Consider an album of pictures depicting a group of friends celebrating a birthday at a bar. Some of the early pictures show people ordering beer and drinking it, while a later photo shows someone asleep on a couch.

“A captioning system might just say, ‘A person lying on a couch,’” Ferraro says. “But a storytelling system might be able to say, ‘Well, given that I think these people were out partying or out eating and drinking, then this person may be drunk.’”

One example listed in the paper includes a series of five images. They show a family gathered around a table, a plate of shellfish, a dog, and images from the beach. The neural network described them with a story reading, “The family got together for a cookout. They had a lot of delicious food. The dog was happy to be there. They had a great time on the beach. They even had a swim in the water.”

The team, which was led by Microsoft researcher Margaret Mitchell and included Microsoft interns like Ferraro and a researcher from Facebook AI, turned what’s called a sequence-to-sequence recurrent neural network into a storyteller by training it with images sourced from Flickr. They had helpers write captions for individual images and for series of images in specific sequences.

An approach similar to those used to label the contents of single photos produced stories that were too generic. To counter this, the team developed a way for the network to choose words that were likely to be visually salient. They also required that the system not repeat words.

Storytelling is an important part of being human, says Stanford Vision Lab director Fei-Fei Li, who did not contribute to the research. Technology that can imitate humans’ techniques for documenting stories needs to be able to cross-reference objects and characters seen in multiple pictures and infer relationships between people, objects, and places.

“The published paper is just the beginning toward this kind of technology,” Li says. “But it is a good step forward to start tackling such an ambitious project. I look forward to more follow-up work from these authors and others.”

Keep Reading

Most Popular

wet market selling fish
wet market selling fish

This scientist now believes covid started in Wuhan’s wet market. Here’s why.

How a veteran virologist found fresh evidence to back up the theory that covid jumped from animals to humans in a notorious Chinese market—rather than emerged from a lab leak.

light and shadow on floor
light and shadow on floor

How Facebook and Google fund global misinformation

The tech giants are paying millions of dollars to the operators of clickbait pages, bankrolling the deterioration of information ecosystems around the world.

masked travellers at Heathrow airport
masked travellers at Heathrow airport

We still don’t know enough about the omicron variant to panic

The variant has caused alarm and immediate border shutdowns—but we still don't know how it will respond to vaccines.

egasus' fortune after macron hack
egasus' fortune after macron hack

NSO was about to sell hacking tools to France. Now it’s in crisis.

French officials were close to buying controversial surveillance tool Pegasus from NSO earlier this year. Now the US has sanctioned the Israeli company, and insiders say it’s on the ropes.

Stay connected

Illustration by Rose WongIllustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.