Presentation is loading. Please wait.

Presentation is loading. Please wait.

Learning from Descriptive Text Tamara L Berg Stony Brook University.

Similar presentations


Presentation on theme: "Learning from Descriptive Text Tamara L Berg Stony Brook University."— Presentation transcript:

1 Learning from Descriptive Text Tamara L Berg Stony Brook University

2 Vision Humans Language Tags: canon, eos, macro, japan, vacation, frog, animal, toad, amphibian, pet, eye, feet, mouth, finger, hand, prince, photo, art, light, photo, flickr, blurry, favorite, nice. It's the perfect party dress. With distinctly feminine details such as a wide sash bow around an empire waist and a deep scoopneck, this linen dress will keep you comfortable and feeling elegant all evening long.

3 Visually Descriptive Text Visually descriptive language provides: information about how people construct natural language for imagery. information about the world, especially the visual world. guidance for computational visual recognition. How do people describe the world? It was an arresting face, pointed of chin, square of jaw. Her eyes were pale green without a touch of hazel, starred with bristly black lashes and slightly tilted at the ends. Above them, her thick black brows slanted upward, cutting a startling oblique line in her magnolia-white skin–that skin so prized by Southern women and so carefully guarded with bonnets, veils and mittens against hot Georgia suns – Gone with the Wind How does the world work? What should we recognize?

4 Visually Descriptive Text Visually descriptive language provides: information about how people construct natural language for imagery. information about the world, especially the visual world. guidance for computational visual recognition. How do people describe the world? It was an arresting face, pointed of chin, square of jaw. Her eyes were pale green without a touch of hazel, starred with bristly black lashes and slightly tilted at the ends. Above them, her thick black brows slanted upward, cutting a startling oblique line in her magnolia-white skin–that skin so prized by Southern women and so carefully guarded with bonnets, veils and mittens against hot Georgia suns – from Gone with the Wind by Margaret Mitchell How does the world work? What should we recognize?

5 Whats in a description? What do people describe? A bearded man is holding a child in a sling. man baby sling shirt glasses ladder fridge table watermelon chair boxes cups water bottle wall pacifier beard … A bearded man stands while holding a small child in a green sheet. A bearded man with a baby in a sling poses. Man standing in kitchen with little girl in green sack. Man with beard and baby Whats in this image?

6 Whats in a description? Predict what people will describe Given an image looking for castles in the clouds out my car window 1) 2) Given a caption two women sitting brunette blonde on bench reading magazine Predict whats in the image clouds car window castle ? women bench magazine grass skirt … e.g. Spain & Perona, 2010

7 President George W. Bush makes a statement in the Rose Garden while Secretary of Defense Donald Rumsfeld looks on, July 23, Rumsfeld said the United States would release graphic photographs of the dead sons of Saddam Hussein to prove they were killed by American troops. Photo by Larry Downing/Reuters Whos in the picture? T.L. Berg, A.C. Berg, J. Edwards, D.A. Forsyth ModelAccuracy of labeling Vision model, No Lang model67% Vision model + Lang model78%

8 Visually Descriptive Text Visually descriptive language provides: information about how people construct natural language for imagery. information about the world, especially the visual world. guidance for computational visual recognition. How do people describe the world? It was an arresting face, pointed of chin, square of jaw. Her eyes were pale green without a touch of hazel, starred with bristly black lashes and slightly tilted at the ends. Above them, her thick black brows slanted upward, cutting a startling oblique line in her magnolia-white skin–that skin so prized by Southern women and so carefully guarded with bonnets, veils and mittens against hot Georgia suns – from Gone with the Wind by Margaret Mitchell How does the world work? What should we recognize?

9 Vision is hard World knowledge (from descriptive text) can be used to smooth noisy vision predictions! Green sheep

10 Learning World Knowledge Attributes Relationships green green grass by the lake a very shiny car in the car museum in my hometown of upstate NY. Our cat Tusik sleeping on the sofa near a hot radiator. very little person in a big rocking chair BabyTalk: Understanding and Generating Simple Image Descriptions Kulkarni, Premraj, Dhar, Li, Choi, AC Berg, TL Berg, CVPR 2011

11 System Flow Input Image Extract Objects/stuff a) dog b) person c) sofa brown 0.32 striped 0.09 furry.04 wooden.2 Feathered brown 0.94 striped 0.10 furry.06 wooden.8 Feathered brown 0.01 striped 0.16 furry.26 wooden.2 feathered a) dog b) person c) sofa Predict attributes Predict prepositions a) dog b) person c) sofa near(a,b) 1 near(b,a) 1 against(a,b).11 against(b,a).04 beside(a,b).24 beside(b,a) near(a,c) 1 near(c,a) 1 against(a,c).3 against(c,a).05 beside(a,c).5 beside(c,a) near(b,c) 1 near(c,b) 1 against(b,c).67 against(c,b).33 beside(b,c).0 beside(c,b) Predict labeling – vision potentials smoothed with text potentials,against, >,near, >,beside, > Generate natural language description This is a photograph of one person and one brown sofa and one dog. The person is against the brown sofa. And the dog is near the person, and beside the brown sofa.

12 This is a picture of one sky, one road and one sheep. The gray sky is over the gray road. The gray sheep is by the gray road. Here we see one road, one sky and one bicycle. The road is near the blue sky, and near the colorful bicycle. The colorful bicycle is within the blue sky. BabyTalk results This is a picture of two dogs. The first dog is near the second furry dog. Objects, Attributes, Prepositions

13 Visually Descriptive Text Visually descriptive language provides: information about how people construct natural language for imagery. information about the world, especially the visual world. guidance for computational visual recognition. How do people describe the world? It was an arresting face, pointed of chin, square of jaw. Her eyes were pale green without a touch of hazel, starred with bristly black lashes and slightly tilted at the ends. Above them, her thick black brows slanted upward, cutting a startling oblique line in her magnolia-white skin–that skin so prized by Southern women and so carefully guarded with bonnets, veils and mittens against hot Georgia suns – from Gone with the Wind by Margaret Mitchell How does the world work? What should we recognize?

14 Recognition is beginning to work Open question – what should we recognize? Maybe objects arent (always) the right base level entities

15 Object Recognition Parts, Poselets, Attributes For example: [Fergus, Perona, Zisserman2003], [Bourdev, Malik2009], … Slide Credit: Ali Farhadi

16 Learn which terms in descriptions are depictable Fully beaded with megawatt crystals, this Christian Louboutin suede pump matches the gleam in your eye. Pump's linear heel plays up the alluring curves of its dipped sides. Round toe frames low-cut vamp. Tonally topstitched collar. 4" straight, covered heel shows off signature red sole. Creamy leather lining with padded insole. "Fifi" is made in Italy. attributes Automatically Discovering Attributes from Noisy Web Data T.L. Berg, A.C. Berg, J. Shih ECCV 2010

17 Given Web Images + Noisy Text Descriptions: 1) Discover visual attribute terms in text descriptions - likely domain dependent 2) Learn appearance models for attributes without labeled data 3) Characterize attributes by: type, localizability

18 Object Recognition For example: [Oliva, Torralba 2001], [SUN 2010], … Slide Credit: Ali Farhadi Scenes

19 What are the right quanta of Recognition? Farhadi & Sadeghi Recognition using Visual Phrases, CVPR 2011

20 Participating in Phrases Profoundly affects the appearance of objects Farhadi & Sadeghi Recognition using Visual Phrases, CVPR 2011

21 Maybe descriptive text can inform entity hypotheses! the dog is sleeping sleeping dog in delhiA dog is sleeping in a sleeping dog in NTHU What should we recognize?

22 cat in a bag cat in the bagcat in bag the cat is in the bag What should we recognize? Maybe descriptive text can inform entity hypotheses!

23 Conclusion Use large pools of descriptive text to: Learn how people describe the visual world Learn how the world works Guide future efforts in recognition Apply this knowledge to multi-modal collections & applications

24 Acknowledgements Collaborators: Alex Berg, David Forsyth, Jaety Edwards, Jonathan Shih, Girish Kulkarni, Visruth Premraj, Sagnik Dhar, Vicente Ordonez, Siming Li, Yejin Choi, Kota Yamaguchi, Vicente Ordonez Funded by NSF Faculty Early Career Development (CAREER) Program: Award # Award #


Download ppt "Learning from Descriptive Text Tamara L Berg Stony Brook University."

Similar presentations


Ads by Google