Skip to main content
EURASIP Journal on Image and Video Processing

Table 7 Lemmas co-occurrence with visually discriminative words

From: Semantic embeddings of generic objects for zero-shot learning

 

Car

Truck

Bird

Cassowary

Wheel

1.3×10−4

1.6×10−4

2.0×10−6

0.0

Drive

1.0×10−3

1.0×10−3

2.2×10−5

2.4×10−3

Wings

4.0×10−6

0.0

1.6×10−4

0.0

Beak

0.0

0.0

5.2×10−5

0.0

Occ.

4.7×105

7.8×104

1.4×105

7.9×102

  1. Statistics presented in this table were gathered from the English Wikipedia corpus with a context window size of five words. The columns correspond to visual class lemmas, and rows correspond to visually discriminative words. The last row shows the number of occurrence of the visual class lemmas in the corpus. Upper rows show the frequency of occurrence of visually discriminative words within the context of visual class lemmas. For example, the upper left value denotes p(wheel|car)
Back to article page