Instructions

You can use this demo to predict situations for images of your choice. Start by clicking on the example images. The demo provides the nearest neighbors in the imSitu training set and a list of predicted situations and associated probability. The demo has a 2 second time limit, so please do not try to very large images because they will take the server too long to download. The demo is an implemenation of the Compositional Conditional Random Field, pre-trained using semantic data augmention on 5 million web images, found here.

Click on images to try these examples

Recognize Situations

Paste a url

Upload a file

Results


Query

Similar in imSitu train set

Predicted situations

flapping
agent bodypart place
bird wing outdoors
0.18638
feeding
agent food source eater place
bird beak bird outside
0.12719
catching
agent caughtitem tool place
bird fish beak body of water
0.09332
plunging
agent plunged destination place
bird head water
0.06815
clinging
agent clungto place
bird stalk outdoors
0.06577
foraging
agent item place
bird bug outdoors
0.05206
splashing
agent destination substance tool place
bird bird water bird outside
0.04514
emerging
agent source destination place
bird cocoon outdoors outdoors
0.02507
swooping
agent place
bird outdoors
0.02453
waddling
agent place
bird outdoors
0.02172