-
Deep Compositional Captioning: Describing Novel Object Categories Without Paired Training Data
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
-
[
pdf]
[ bibtex]
Generation and Comprehension of Unambiguous Object Descriptions
Stacked Attention Networks for Image Question Answering
Image Question Answering Using Convolutional Neural Network With Dynamic Parameter Prediction
Neural Module Networks
Learning Deep Representations of Fine-Grained Visual Descriptions
Multi-Cue Zero-Shot Learning With Strong Supervision
Latent Embeddings for Zero-Shot Classification
One-Shot Learning of Scene Locations via Feature Trajectory Transfer
Learning Attributes Equals Multi-Source Domain Generalization
Anticipating Visual Representations From Unlabeled Video
Learning to Assign Orientations to Feature Points
Learning Dense Correspondence via 3D-Guided Cycle Consistency
The Global Patch Collider
Joint Probabilistic Matching Using m-Best Solutions
Face Alignment Across Large Poses: A 3D Solution
Interactive Segmentation on RGBD Images via Cue Selection
Layered Scene Decomposition via the Occlusion-CRF
Affinity CNN: Learning Pixel-Centric Pairwise Relations for Figure/Ground Embedding
Weakly Supervised Object Boundaries
Object Contour Detection With a Fully Convolutional Encoder-Decoder Network
What Value Do Explicit High Level Concepts Have in Vision to Language Problems?
Fast Detection of Curved Edges at Low SNR
Object Skeleton Extraction in Natural Images by Fusing Scale-Associated Deep Side Outputs
Learning Relaxed Deep Supervision for Better Edge Detection
Occlusion Boundary Detection via Deep Exploration of Context
SemiContour: A Semi-Supervised Learning Approach for Contour Detection
Learning to Localize Little Landmarks
InterActive: Inter-Layer Activeness Propagation
Exploit Bounding Box Annotations for Multi-Label Object Recognition
TI-Pooling: Transformation-Invariant Pooling for Feature Learning in Convolutional Neural Networks
Fashion Style in 128 Floats: Joint Ranking and Classification Using Weak Data for Feature Extraction
Equiangular Kernel Dictionary Learning With Applications to Dynamic Texture Analysis
Compact Bilinear Pooling
Accumulated Stability Voting: A Robust Descriptor From Descriptors of Multiple Scales
CoMaL: Good Features to Match on Object Boundaries
Progressive Feature Matching With Alternate Descriptor Selection and Correspondence Enrichment
A New Finsler Minimal Path Model With Curvature Penalization for Image Segmentation and Closed Contour Detection
Scale-Aware Alignment of Hierarchical Image Segmentation
Deep Interactive Object Selection
Pull the Plug? Predicting If Computers or Humans Should Segment Images
In the Shadows, Shape Priors Shine: Using Occlusion to Improve Multi-Region Segmentation
Convexity Shape Constraints for Image Segmentation
MCMC Shape Sampling for Image Segmentation With Nonparametric Shape Priors
From Noise Modeling to Blind Image Denoising
Efficient and Robust Color Consistency for Community Photo Collections
Needle-Match: Reliable Patch Matching Under High Uncertainty
ReconNet: Non-Iterative Reconstruction of Images From Compressively Sensed Measurements
Soft-Segmentation Guided Object Motion Deblurring
Two Illuminant Estimation and User Correction Preference
Deep Contrast Learning for Salient Object Detection
Multiview Image Completion With Space Structure Propagation
Composition-Preserving Deep Photo Aesthetics Assessment
Automatic Image Cropping : A Computational Complexity Study
A Deeper Look at Saliency: Feature Contrast, Semantics, and Beyond
Spatially Binned ROC: A Comprehensive Saliency Metric
GraB: Visual Saliency via Novel Graph Model and Background Priors
Predicting When Saliency Maps Are Accurate and Eye Fixations Consistent
Split and Match: Example-Based Adaptive Patch Sampling for Unsupervised Style Transfer
Detection and Accurate Localization of Circular Fiducials Under Highly Challenging Conditions
Scene Recognition With CNNs: Objects, Scales and Dataset Bias
Learning Action Maps of Large Environments via First-Person Vision
Single-Image Crowd Counting via Multi-Column Convolutional Neural Network
Shallow and Deep Convolutional Networks for Saliency Prediction
Sample and Filter: Nonparametric Scene Parsing via Efficient Filtering
DeLay: Robust Spatial Layout Estimation for Cluttered Indoor Scenes
A Text Detection System for Natural Scenes With Convolutional Feature Learning and Cascaded Classification
Reversible Recursive Instance-Level Object Segmentation
Coherent Parametric Contours for Interactive Video Object Segmentation
Manifold SLIC: A Fast Method to Compute Content-Sensitive Superpixels
Deep Saliency With Encoded Low Level Distance Map and High Level Features
Instance-Level Segmentation for Autonomous Driving With Deep Densely Connected MRFs
DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection
Object Co-Segmentation via Graph Optimized-Flexible Manifold Ranking
Primary Object Segmentation in Videos via Alternate Convex Optimization of Foreground and Background Distributions
Automatic Fence Segmentation in Videos of Dynamic Scenes
Discovering the Physical Parts of an Articulated Object Class From Multiple Videos
A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation
Learning Temporal Regularity in Video Sequences
Bilateral Space Video Segmentation
ReD-SFA: Relation Discovery Based Slow Feature Analysis for Trajectory Clustering
Training Region-Based Object Detectors With Online Hard Example Mining
Deep Residual Learning for Image Recognition
You Only Look Once: Unified, Real-Time Object Detection
LocNet: Improving Localization Accuracy for Object Detection
Sketch Me That Shoe
Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images
Object Detection From Video Tubelets With Convolutional Neural Networks
Learning With Side Information Through Modality Hallucination
Object-Proposal Evaluation Protocol is 'Gameable'
HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
We Don't Need No Bounding-Boxes: Training Object Class Detectors Using Only Human Verification
Factors in Finetuning Deep Model for Object Detection With Long-Tail Distribution
Information-Driven Adaptive Structured-Light Scanners
Simultaneous Optical Flow and Intensity Estimation From an Event Camera
Macroscopic Interferometry: Rethinking Depth Estimation With Frequency-Domain Time-Of-Flight
ASP Vision: Optically Computing the First Layer of Convolutional Neural Networks Using Angle Sensitive Pixels
Computational Imaging for VLBI Image Reconstruction
You Lead, We Exceed: Labor-Free Video Concept Learning by Jointly Exploiting Web Videos and Images
Track and Segment: An Iterative Unsupervised Approach for Video Object Proposals
Beyond Local Search: Tracking Objects Everywhere With Instance-Specific Proposals
Groupwise Tracking of Crowded Similar-Appearance Targets From Low-Continuity Image Sequences
Social LSTM: Human Trajectory Prediction in Crowded Spaces
What Players Do With the Ball: A Physically Constrained Interaction Modeling
Highlight Detection With Pairwise Deep Ranking for First-Person Video Summarization
Direct Prediction of 3D Body Poses From Motion Compensated Sequences
Video2GIF: Automatic Generation of Animated GIFs From Video
NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis
Progressively Parsing Interactional Objects for Fine Grained Action Detection
Hierarchical Recurrent Neural Encoder for Video Representation With Application to Captioning
From Keyframes to Key Objects: Video Summarization by Representative Object Proposal Selection
Temporal Action Localization in Untrimmed Videos via Multi-Stage CNNs
Summary Transfer: Exemplar-Based Subset Selection for Video Summarization
POD: Discovering Primary Objects in Videos Based on Evolutionary Refinement of Object Recurrence, Background, and Primary Object Models
What If We Do Not Have Multiple Videos of the Same Action? -- Video Action Localization Using Web Images
Beyond F-Formations: Determining Social Involvement in Free Standing Conversing Groups From Static Images
DeepFashion: Powering Robust Clothes Recognition and Retrieval With Rich Annotations
SketchNet: Sketch Classification With Web Images
Embedding Label Structures for Fine-Grained Feature Representation
Fine-Grained Image Classification by Exploring Bipartite-Graph Labels
Picking Deep Filter Responses for Fine-Grained Image Recognition
SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-Grained Recognition
Fine-Grained Categorization and Dataset Bootstrapping Using Deep Metric Learning With Humans in the Loop
Mining Discriminative Triplets of Patches for Fine-Grained Classification
Part-Stacked CNN for Fine-Grained Visual Categorization
Learning Compact Binary Descriptors With Unsupervised Deep Neural Networks
Solving Small-Piece Jigsaw Puzzles by Growing Consensus
Pairwise Matching Through Max-Weight Bipartite Belief Propagation
Structured Feature Similarity With Explicit Feature Map
Temporal Epipolar Regions
Recurrent Attention Models for Depth-Based Person Identification
Learning a Discriminative Null Space for Person Re-Identification
Learning Deep Feature Representations With Domain Guided Dropout for Person Re-Identification
How Far Are We From Solving Pedestrian Detection?
Similarity Learning With Spatial Constraints for Person Re-Identification
Sample-Specific SVM Learning for Person Re-Identification
Joint Learning of Single-Image and Cross-Image Representations for Person Re-Identification
A Multi-Level Contextual Model For Person Recognition in Photo Albums
Unsupervised Cross-Dataset Transfer Learning for Person Re-Identification
Pedestrian Detection Inspired by Appearance Constancy and Shape Symmetry
Recurrent Convolutional Network for Video-Based Person Re-Identification
Person Re-Identification by Multi-Channel Parts-Based CNN With Improved Triplet Loss Function
Top-Push Video-Based Person Re-Identification
Improving Person Re-Identification via Pose-Aware Multi-Shot Matching
Hierarchical Gaussian Descriptor for Person Re-Identification
STCT: Sequentially Training Convolutional Networks for Visual Tracking
Determining Occlusions From Space and Time Image Reconstructions
Online Multi-Object Tracking via Structural Constraint Event Aggregation
Staple: Complementary Learners for Real-Time Tracking
Robust Optical Flow Estimation of Double-Layer Images Under Transparency or Reflection
Siamese Instance Search for Tracking
Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking
3D Part-Based Sparse Tracker With Automatic Synchronization and Registration
Recurrently Target-Attending Tracking
Structured Regression Gradient Boosting
Loss Functions for Top-k Error: Analysis and Insights
Metric Learning as Convex Combinations of Local Models With Generalization Guarantees
Efficient Training of Very Deep Neural Networks for Supervised Hashing
Information Bottleneck Learning Using Privileged Information for Visual Recognition
3D Action Recognition From Novel Viewpoints
3D Shape Attributes
Three-Dimensional Object Detection and Layout Prediction Using Clouds of Oriented Gradients
3D Semantic Parsing of Large-Scale Indoor Spaces
Dense Human Body Correspondences Using Convolutional Networks
Geometry-Informed Material Recognition
Towards Open Set Deep Networks
What's Wrong With That Object? Identifying Images of Unusual Objects by Modelling the Detection Score Distribution
Large-Scale Location Recognition and the Geometric Burstiness Problem
Regularity-Driven Facade Matching Between Aerial and Street Views
Do Computational Models Differ Systematically From Human Object Perception?
Contour Detection in Unstructured 3D Point Clouds
Unsupervised Learning of Edges
Blind Image Deblurring Using Dark Channel Prior
Deeply-Recursive Convolutional Network for Image Super-Resolution
Accurate Image Super-Resolution Using Very Deep Convolutional Networks
RAW Image Reconstruction Using a Self-Contained sRGB-JPEG Image With Only 64 KB Overhead
Group MAD Competition - A New Methodology to Compare Objective Image Quality Models
Non-Local Image Dehazing
A Holistic Approach to Cross-Channel Image Noise Modeling and Its Application to Image Denoising
Multispectral Images Denoising by Intrinsic Tensor Sparsity Regularization
A Comparative Study for Single Image Blind Deblurring
Spatiotemporal Bundle Adjustment for Dynamic 3D Reconstruction
Inextensible Non-Rigid Shape-From-Motion by Second-Order Cone Programming
Optimal Relative Pose With Unknown Correspondences
Homography Estimation From the Common Self-Polar Triangle of Separate Ellipses
Heterogeneous Light Fields
A Consensus-Based Framework for Distributed Bundle Adjustment
Globally Optimal Manhattan Frame Estimation in Real-Time
Mirror Surface Reconstruction Under an Uncalibrated Camera
A Hole Filling Approach Based on Background Reconstruction for View Synthesis in 3D Video
A Direct Least-Squares Solution to the PnP Problem With Unknown Focal Length
Efficient Intersection of Three Quadrics and Applications in Computer Vision
Using Spatial Order to Boost the Elimination of Incorrect Feature Matches
A Probabilistic Framework for Color-Based Point Set Registration
Blind Image Deconvolution by Automatic Gradient Activation
PSyCo: Manifold Span Reduction for Super Resolution
Parametric Object Motion From Blur
Image Deblurring Using Smartphone Inertial Sensors
Seven Ways to Improve Example-Based Single Image Super Resolution
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
They Are Not Equally Reliable: Semantic Event Search Using Differentiated Concept Classifiers
Going Deeper into First-Person Activity Recognition
Cascaded Interactional Targeting Network for Egocentric Video Analysis
Fast Temporal Activity Proposals for Efficient Detection of Human Actions in Untrimmed Videos
Discriminative Hierarchical Rank Pooling for Activity Recognition
Convolutional Two-Stream Network Fusion for Video Action Recognition
Learning Activity Progression in LSTMs for Activity Detection and Early Detection
VLAD3: Encoding Dynamics of Deep Features for Action Recognition
A Multi-Stream Bi-Directional Recurrent Neural Network for Fine-Grained Action Detection
A Hierarchical Deep Temporal Model for Group Activity Recognition
A Hierarchical Pose-Based Approach to Complex Action Understanding Using Dictionaries of Actionlets and Motion Poselets
A Key Volume Mining Deep Framework for Action Recognition
Improved Hamming Distance Search Using Variable Length Substrings
Shortlist Selection With Residual-Aware Distance Estimator for K-Nearest Neighbor Search
Supervised Quantization for Similarity Search
Efficient Large-Scale Approximate Nearest Neighbor Search on the GPU
Collaborative Quantization for Cross-Modal Similarity Search
Aggregating Image and Text Quantized Correlated Components
Efficient Indexing of Billion-Scale Datasets of Deep Descriptors
Deep Supervised Hashing for Fast Image Retrieval
Efficient Large-Scale Similarity Search Using Matrix Factorization
Incremental Object Discovery in Time-Varying Image Collections
Detecting Migrating Birds at Night
When Naive Bayes Nearest Neighbors Meet Convolutional Neural Networks
Traffic-Sign Detection and Classification in the Wild
Large Scale Semi-Supervised Object Detection Using Visual and Semantic Knowledge Transfer
Exploit All the Layers: Fast and Accurate CNN Object Detector With Scale Dependent Pooling and Cascaded Rejection Classifiers
Dictionary Pair Classifier Driven Convolutional Neural Networks for Object Detection
Monocular 3D Object Detection for Autonomous Driving
How Hard Can It Be? Estimating the Difficulty of Visual Search in an Image
Deep Relative Distance Learning: Tell the Difference Between Similar Vehicles
Eye Tracking for Everyone
Efficient Globally Optimal 2D-To-3D Deformable Shape Matching
Ambiguity Helps: Classification With Disagreements in Crowdsourced Annotations
A Task-Oriented Approach for Cost-Sensitive Recognition
Refining Architectures of Deep Convolutional Neural Networks
iLab-20M: A Large-Scale Controlled Object Dataset to Investigate Deep Learning
Recursive Recurrent Nets With Attention Modeling for OCR in the Wild
Deep Decision Network for Multi-Class Image Classification
Less Is More: Zero-Shot Learning From Online Textual Documents With Noise Suppression
Fast Algorithms for Linear and Kernel SVM+
Hierarchically Gated Deep Networks for Semantic Segmentation
Deep Structured Scene Parsing by Learning With Image Descriptions
CNN-RNN: A Unified Framework for Multi-Label Image Classification
Walk and Learn: Facial Attribute Representation Learning From Egocentric Video and Contextual Data
CNN-N-Gram for Handwriting Word Recognition
Synthetic Data for Text Localisation in Natural Images
End-To-End People Detection in Crowded Scenes
Real-Time Salient Object Detection With a Minimum Spanning Tree
Local Background Enclosure for RGB-D Salient Object Detection
Adaptive Object Detection Using Adjacency and Zoom Prediction
Semantic Channels for Fast Pedestrian Detection
G-CNN: An Iterative Grid Based Object Detector
Recurrent Face Aging
Face2Face: Real-Time Face Capture and Reenactment of RGB Videos
Self-Adaptive Matrix Completion for Heart Rate Estimation From Face Videos Under Realistic Conditions
Visually Indicated Sounds
Image Style Transfer Using Convolutional Neural Networks
Patch-Based Convolutional Neural Network for Whole Slide Tissue Image Classification
Hedgehog Shape Priors for Multi-Object Segmentation
Latent Variable Graphical Model Selection Using Harmonic Analysis: Applications to the Human Connectome Project (HCP)
Simultaneous Estimation of Near IR BRDF and Fine-Scale Surface Geometry
Do It Yourself Hyperspectral Imaging With Everyday Digital Cameras
Automatic Content-Aware Color and Tone Stylization
Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis
DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentation
Learning to Read Chest X-Rays: Recurrent Neural Cascade Model for Automated Image Annotation
Conformal Surface Alignment With Optimal Mobius Search
Coupled Harmonic Bases for Longitudinal Characterization of Brain Networks
Automating Carotid Intima-Media Thickness Video Interpretation With Convolutional Neural Networks
Context Encoders: Feature Learning by Inpainting
Comparative Deep Learning of Hybrid Representations for Image Recommendations
Fast ConvNets Using Group-Wise Brain Damage
Learning to Co-Generate Object Proposals With a Deep Structured Network
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks
Blockout: Dynamic Model Selection for Hierarchical Deep Networks
FireCaffe: Near-Linear Acceleration of Deep Neural Network Training on Compute Clusters
MDL-CW: A Multimodal Deep Learning Framework With Cross Weights
Structured Receptive Fields in CNNs
First Person Action Recognition Using Deep Learned Descriptors
Recognizing Micro-Actions and Reactions From Paired Egocentric Videos
Mining 3D Key-Pose-Motifs for Action Recognition
Predicting the Where and What of Actors and Actions Through Online Action Localization
Actions ~ Transformations
Visual Path Prediction in Complex Scenes With Crowded Moving Objects
End-To-End Learning of Action Detection From Frame Glimpses in Videos
Action Recognition in Video Using Sparse Coding and Relative Features
Improving Human Action Recognition by Non-Action Classification
Actionness Estimation Using Hybrid Fully Convolutional Networks
Real-Time Action Recognition With Enhanced Motion Vector CNNs
Laplacian Patch-Based Image Synthesis
Rain Streak Removal Using Layer Priors
Gradient-Domain Image Reconstruction Framework With Intensity-Range and Base-Structure Constraints
Removing Clouds and Recovering Ground Observations in Satellite Image Sequences via Temporally Contiguous Robust Matrix Completion
D3: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Images
From Bows to Arrows: Rolling Shutter Rectification of Urban Scenes
A Weighted Variational Model for Simultaneous Reflectance and Illumination Estimation
Visualizing and Understanding Deep Texture Representations
Robust Kernel Estimation With Outliers Handling for Image Deblurring
Online Collaborative Learning for Open-Vocabulary Visual Classifiers
Rethinking the Inception Architecture for Computer Vision
Cross Modal Distillation for Supervision Transfer
Efficient Point Process Inference for Large-Scale Object Detection
Weakly Supervised Deep Detection Networks
BORDER: An Oriented Rectangles Approach to Texture-Less Object Recognition
Active Image Segmentation Propagation
Inside-Outside Net: Detecting Objects in Context With Skip Pooling and Recurrent Neural Networks
RIFD-CNN: Rotation-Invariant and Fisher Discriminative Convolutional Neural Networks for Object Detection
Reinforcement Learning for Visual Object Detection
Detecting Repeating Objects Using Patch Correlation Analysis
Analyzing Classifiers: Fisher Vectors and Deep Neural Networks
Learning Deep Features for Discriminative Localization
Seeing Through the Human Reporting Bias: Visual Classifiers From Noisy Human-Centric Labels
Learning Aligned Cross-Modal Representations From Weakly Aligned Data
A Probabilistic Collaborative Representation Based Approach for Pattern Classification
Learning Structured Inference Neural Networks With Label Relations
Discriminative Multi-Modal Feature Fusion for RGBD Indoor Scene Recognition
Conditional Graphical Lasso for Multi-Label Image Classification
Region Ranking SVM for Image Classification
Predicting Motivations of Actions by Leveraging Text
BoxCars: 3D Boxes as CNN Input for Improved Fine-Grained Vehicle Recognition
Highway Vehicle Counting in Compressed Domain
Camera Calibration From Periodic Motion of a Pedestrian
Dynamic Image Networks for Action Recognition
Detecting Events and Key Actors in Multi-Person Videos
Regularizing Long Short Term Memory With 3D Human-Skeleton Sequences for Action Recognition
Personalizing Human Video Pose Estimation
End-To-End Learning of Deformable Mixture of Parts and Deep Convolutional Neural Networks for Human Pose Estimation
Actor-Action Semantic Segmentation With Grouping Process Models
Temporal Action Localization With Pyramid of Score Distribution Features
Recognizing Activities of Daily Living With a Wrist-Mounted Camera
Harnessing Object and Scene Semantics for Large-Scale Video Understanding
Video-Story Composition via Plot Analysis
Temporal Action Detection Using a Statistical Language Model
Multi-Scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation
Instance-Aware Semantic Segmentation via Multi-Task Network Cascades
ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation
Feature Space Optimization for Semantic Video Segmentation
Large-Scale Semantic 3D Reconstruction: An Adaptive Multi-Resolution Model for Multi-Class Volumetric Labeling
Semantic Object Parsing With Local-Global Long Short-Term Memory
Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation
Learning Transferrable Knowledge for Semantic Segmentation With Deep Convolutional Neural Network
The Cityscapes Dataset for Semantic Urban Scene Understanding
Gaussian Conditional Random Field Network for Semantic Segmentation
The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes
Progressive Prioritized Multi-View Stereo
WarpNet: Weakly Supervised Matching for Single-View Reconstruction
What Sparse Light Field Coding Reveals About Scene Structure
Online Reconstruction of Indoor Scenes From RGB-D Streams
Patches, Planes and Probabilities: A Non-Local Prior for Volumetric 3D Reconstruction
Single Image Camera Calibration With Lenticular Arrays for Augmented Reality
Augmented Blendshapes for Real-Time Simultaneous 3D Head Modeling and Facial Motion Capture
Learned Binary Spectral Shape Descriptor for 3D Shape Correspondence
Multiple Model Fitting as a Set Coverage Problem
Piecewise-Planar 3D Approximation From Wide-Baseline Stereo
Sparse to Dense 3D Reconstruction From Rolling Shutter Images
Consistency of Silhouettes and Their Duals
Rolling Shutter Absolute Pose Problem With Known Vertical Direction
Uncertainty-Driven 6D Pose Estimation of Objects and Scenes From a Single RGB Image
Multicamera Calibration From Visible and Mirrored Epipoles
Joint Unsupervised Deformable Spatio-Temporal Alignment of Sequences
Deep Region and Multi-Label Learning for Facial Action Unit Detection
Constrained Joint Cascade Regression Framework for Simultaneous Facial Action Unit Recognition and Facial Landmark Detection
Unconstrained Face Alignment via Cascaded Compositional Learning
Automated 3D Face Reconstruction From Multiple Images Using Quality Measures
Occlusion-Free Face Alignment: Deep Regression Networks Coupled With De-Corrupt AutoEncoders
Multimodal Spontaneous Emotion Corpus for Human Behavior Analysis
Learning Reconstruction-Based Remote Gaze Estimation
Joint Training of Cascaded CNN for Face Detection
Facial Expression Intensity Estimation Using Ordinal Information
Proposal Flow
ProNet: Learning to Propose Object-Specific Boxes for Cascaded Neural Networks
Seeing Behind the Camera: Identifying the Authorship of a Photograph
Material Classification Using Raw Time-Of-Flight Measurements
Weakly Supervised Object Localization With Progressive Domain Adaptation
Newtonian Scene Understanding: Unfolding the Dynamics of Objects in Static Images
Identifying Good Training Data for Self-Supervised Free Space Estimation
Learning to Match Aerial Images With Deep Attentive Architectures
Track and Transfer: Watching Videos to Simulate Strong Human Supervision for Weakly-Supervised Object Detection
DeepCAMP: Deep Convolutional Action & Attribute Mid-Level Patterns
Canny Text Detector: Fast and Robust Scene Text Localization Algorithm
Temporal Multimodal Learning in Audiovisual Speech Recognition
Recovering 6D Object Pose and Predicting Next-Best-View in the Crowd
Robust 3D Hand Pose Estimation in Single Depth Images: From Single-View CNN to Multi-View CNNs
Semantic Segmentation With Boundary Neural Fields
HD Maps: Fine-Grained Road Segmentation by Parsing Ground and Aerial Images
DAG-Recurrent Neural Networks For Scene Labeling
Saliency Guided Dictionary Learning for Weakly-Supervised Image Parsing
Attention to Scale: Scale-Aware Semantic Image Segmentation
Scene Labeling Using Sparse Precision Matrix
Iterative Instance Segmentation
Recurrent Attentional Networks for Saliency Detection
Instance-Level Video Segmentation From Object Tracks
Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer
Amplitude Modulated Video Camera - Light Separation in Dynamic Scenes
A Benchmark Dataset and Evaluation for Non-Lambertian and Uncalibrated Photometric Stereo
Depth From Semi-Calibrated Stereo and Defocus
Exploiting Spectral-Spatial Correlation for Coded Hyperspectral Image Restoration
Variable Aperture Light Field Photography: Overcoming the Diffraction-Limited Spatio-Angular Resolution Tradeoff
Convolutional Networks for Shape From Light Field
Panoramic Stereo Videos With a Single Camera
The Next Best Underwater View
Reconstructing Shapes and Appearances of Thin Film Objects Using RGB Images
Noisy Label Recovery for Shadow Detection in Unfamiliar Domains
Deep Hand: How to Train a CNN on 1 Million Hand Images When Your Data Is Continuous and Weakly Labelled
Recognizing Car Fluents From Video
Pairwise Decomposition of Image Sequences for Active Multi-View Recognition
Inferring Forces and Learning Human Utilities From Videos
Force From Motion: Decoding Physical Sensation in a First Person Video
Robust Multi-Body Feature Tracker: A Segmentation-Free Approach
Slow and Steady Feature Analysis: Higher Order Temporal Coherence in Video
Volumetric 3D Tracking by Detection
The Solution Path Algorithm for Identity-Aware Multi-Object Tracking
In Defense of Sparse Tracking: Circulant Sparse Tracker
Optical Flow With Semantic Segmentation and Localized Layers
Video Segmentation via Object Flow
Closed-Form Training of Mahalanobis Distance for Supervised Clustering
Scalable Sparse Subspace Clustering by Orthogonal Matching Pursuit
Oracle Based Active Set Algorithm for Scalable Elastic Net Subspace Clustering
Sparse Coding and Dictionary Learning With Linear Dynamical Systems
Sublabel-Accurate Relaxation of Nonconvex Energies
The Multiverse Loss for Robust Transfer Learning
Learning From the Mistakes of Others: Matching Errors in Cross-Dataset Learning
An Efficient Exact-PGA Algorithm for Constant Curvature Manifolds
Online Learning With Bayesian Classification Trees
Cross-Stitch Networks for Multi-Task Learning
Deep Metric Learning via Lifted Structured Feature Embedding
Fast Algorithms for Convolutional Neural Networks
Coordinating Multiple Disparity Proposals for Stereo Computation
Joint Multiview Segmentation and Localization of RGB-D Images Using Depth-Induced Silhouette Consistency
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
6D Dynamic Camera Relocalization From Single Reference Image
Dense Monocular Depth Estimation in Complex Dynamic Scenes
Using Self-Contradiction to Learn Confidence Measures in Stereo Vision
Understanding Real World Indoor Scenes With Synthetic Data
Stereo Matching With Color and Monochrome Cameras in Low-Light Conditions
Camera Calibration From Dynamic Silhouettes Using Motion Barcodes
Structure-From-Motion Revisited
Constructing Canonical Regions for Fast and Effective View Selection
Prior-Less Compressible Structure From Motion
Rolling Shutter Camera Relative Pose: Generalized Epipolar Geometry
Structure From Motion With Objects
DeepHand: Robust Hand Pose Estimation by Completing a Matrix Imputed With Deep Features
Multi-Oriented Text Detection With Fully Convolutional Networks
Robust Scene Text Recognition With Automatic Rectification
Mnemonic Descent Method: A Recurrent Process Applied for End-To-End Face Alignment
Large-Pose Face Alignment via CNN-Based Dense 3D Model Fitting
Adaptive 3D Face Reconstruction From Unconstrained Photo Collections
Online Detection and Classification of Dynamic Hand Gestures With Recurrent 3D Convolutional Neural Network
Kinematic Structure Correspondences via Hypergraph Matching
CP-mtML: Coupled Projection Multi-Task Metric Learning for Large Scale Face Retrieval
PatchBatch: A Batch Augmented Loss for Optical Flow
Joint Recovery of Dense Correspondence and Cosegmentation in Two Images
Multi-View People Tracking via Hierarchical Trajectory Composition
Object Tracking via Dual Linear Structured SVM and Explicit Feature Map
Robust, Real-Time 3D Tracking of Multiple Objects With Similar Appearances
An Egocentric Look at Video Photographer Identity
Learning Multi-Domain Convolutional Neural Networks for Visual Tracking
Hedged Deep Tracking
Structural Correlation Filter for Robust Visual Tracking
Visual Tracking Using Attention-Modulated Disintegration and Integration
A Continuous Occlusion Model for Road Scene Understanding
Virtual Worlds as Proxy for Multi-Object Tracking Analysis
Uncalibrated Photometric Stereo by Stepwise Optimization Using Principal Components of Isotropic BRDFs
Unbiased Photometric Stereo for Colored Surfaces: A Variational Approach
3D Reconstruction of Transparent Objects With Position-Normal Consistency
Real-Time Depth Refinement for Specular Objects
Recovering Transparent Shape From Time-Of-Flight Distortion
Robust Light Field Depth Estimation for Noisy Scene With Occlusion
Rotational Crossed-Slit Light Field
Single Image Object Modeling Based on BRDF and R-Surfaces Learning
A Nonlinear Regression Technique for Manifold Valued Data With Applications to Medical Image Analysis
RAID-G: Robust Estimation of Approximate Infinite Dimensional Gaussian With Application to Material Recognition
An Empirical Evaluation of Current Convolutional Architectures' Ability to Manage Nuisance Location and Scale Variability
Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks
Mixture of Bilateral-Projection Two-Dimensional Probabilistic Principal Component Analysis
Rolling Rotations for Recognizing Human Actions From 3D Skeletal Data
Improving the Robustness of Deep Neural Networks via Stability Training
Logistic Boosting Regression for Label Distribution Learning
Efficient Temporal Sequence Comparison and Classification Using Gram Matrix Embeddings on a Riemannian Manifold
Deep Reflectance Maps
Semantic Filtering
UAV Sensor Fusion With Latent-Dynamic Conditional Random Fields in Coronal Plane Estimation
Robust Visual Place Recognition With Graph Kernels
Semantic Image Segmentation With Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform
Natural Language Object Retrieval
DenseCap: Fully Convolutional Localization Networks for Dense Captioning
Unsupervised Learning From Narrated Instruction Videos
Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks
Jointly Modeling Embedding and Translation to Bridge Video and Language
We Are Humor Beings: Understanding and Predicting Visual Humor
Where to Look: Focus Regions for Visual Question Answering
Ask Me Anything: Free-Form Visual Question Answering Based on Knowledge From External Sources
MovieQA: Understanding Stories in Movies Through Question-Answering
TGIF: A New Dataset and Benchmark on Animated GIF Description
Image Captioning With Semantic Attention
Temporally Coherent 4D Reconstruction of Complex Dynamic Scenes
Consensus of Non-Rigid Reconstructions
Isometric Non-Rigid Shape-From-Motion in Linear Time
Learning Online Smooth Predictors for Realtime Camera Planning Using Recurrent Decision Trees
Egocentric Future Localization
Full Flow: Optical Flow Estimation By Global Optimization Over Regular Grids
Structured Feature Learning for Pose Estimation
Convolutional Pose Machines
Human Pose Estimation With Iterative Error Feedback
WELDON: Weakly Supervised Learning of Deep Convolutional Neural Networks
DisturbLabel: Regularizing CNN on the Loss Layer
Gradual DropIn of Layers to Train Very Deep Neural Networks
Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition
Deep SimNets
Studying Very Low Resolution Recognition Using Deep Networks
Deep Gaussian Conditional Random Field Network: A Model-Based Deep Network for Discriminative Denoising
Event-Specific Image Importance
Quantized Convolutional Neural Networks for Mobile Devices
Inverting Visual Representations With Convolutional Networks
Pose-Aware Face Recognition in the Wild
Multi-View Deep Network for Cross-View Classification
Sparsifying Neural Network Connections for Face Recognition
Pairwise Linear Regression Classification for Image Set Retrieval
The MegaFace Benchmark: 1 Million Faces for Recognition at Scale
Learnt Quasi-Transitive Similarity for Retrieval From Large Collections of Faces
Latent Factor Guided Convolutional Neural Networks for Age-Invariant Face Recognition
Copula Ordinal Regression for Joint Estimation of Facial Action Unit Intensity
A Robust Multilinear Model Learning Framework for 3D Faces
Ordinal Regression With Multiple Output CNN for Age Estimation
DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation
Thin-Slicing for Pose: Learning to Understand Pose Without Explicit Pose Estimation
A Dual-Source Approach for 3D Pose Estimation From a Single Image
Efficiently Creating 3D Training Data for Fine Hand Pose Estimation
Sparseness Meets Deepness: 3D Human Pose Estimation From Monocular Video
Answer-Type Prediction for Visual Question Answering
Visual Word2Vec (vis-w2v): Learning Visually Grounded Word Embeddings Using Abstract Scenes
Visual7W: Grounded Question Answering in Images
Learning Deep Structure-Preserving Image-Text Embeddings
Yin and Yang: Balancing and Answering Binary Visual Questions
GIFT: A Real-Time and Scalable 3D Shape Search Engine
Functional Faces: Groupwise Dense Correspondence Using Functional Maps
Similarity Metric For Curved Shapes In Euclidean Space
Shape Analysis With Hyperbolic Wasserstein Distance
Tensor Power Iteration for Multi-Graph Matching
Multivariate Regression on the Grassmannian for Predicting Novel Domains
Learning Cross-Domain Landmarks for Heterogeneous Domain Adaptation
Geospatial Correspondences for Multimodal Registration
Constrained Deep Transfer Feature Learning and Its Applications
Deep Canonical Time Warping
Multilinear Hyperplane Hashing
Large Scale Hard Sample Mining With Monte Carlo Tree Search
Multi-Label Ranking From Positive and Unlabeled Data
Joint Unsupervised Learning of Deep Representations and Image Clusters
Kernel Sparse Subspace Clustering on Symmetric Positive Definite Manifolds
Symmetry reCAPTCHA
Unsupervised Learning of Discriminative Attributes and Visual Representations
When VLAD Met Hilbert
Approximate Log-Hilbert-Schmidt Distances Between Covariance Operators for Image Classification
Subspace Clustering With Priors via Sparse Quadratically Constrained Quadratic Programming
Robust Tensor Factorization With Unknown Noise
Kernel Approximation via Empirical Orthogonal Decomposition for Unsupervised Feature Learning
Active Learning for Delineation of Curvilinear Structures
Recognizing Emotions From Abstract Paintings Using Non-Linear Matrix Completion
Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization
Sliced Wasserstein Kernels for Probability Distributions
Trace Quotient Meets Sparsity: A Method for Learning Low Dimensional Image Representations
Backtracking ScSPM Image Classifier for Weakly Supervised Top-Down Saliency
MSR-VTT: A Large Video Description Dataset for Bridging Video and Language
NetVLAD: CNN Architecture for Weakly Supervised Place Recognition
Structural-RNN: Deep Learning on Spatio-Temporal Graphs
Learning to Select Pre-Trained Deep Representations With Bayesian Evidence Framework
Synthesized Classifiers for Zero-Shot Learning
Semi-Supervised Vocabulary-Informed Learning
Simultaneous Clustering and Model Selection for Tensor Affinities
Discriminatively Embedded K-Means for Multi-View Clustering
Min Norm Point Algorithm for Higher Order MRF-MAP Inference
Learning Deep Representation for Imbalanced Classification
Learning Local Image Descriptors With Deep Siamese and Triplet Convolutional Networks by Minimising Global Loss Functions
Sparse Coding for Third-Order Super-Symmetric Tensor Descriptors With Application to Texture Recognition
Random Features for Sparse Signal Classification
High-Quality Depth From Uncalibrated Small Motion Clip
Efficient 3D Room Shape Recovery From a Single Panorama
Structured Prediction of Unobserved Voxels From a Single Depth Image
HyperDepth: Learning Depth From Structured Light Without Matching
SVBRDF-Invariant Shape and Reflectance Estimation From Light-Field Cameras
Semantic 3D Reconstruction With Continuous Regularization and Ray Potentials Using a Visibility Consistency Constraint
Theory and Practice of Structure-From-Motion Using Affine Correspondences
Just Look at the Image: Viewpoint-Specific Surface Normal Prediction for Improved Multi-View Reconstruction
From Dusk Till Dawn: Modeling in the Dark
Accelerated Generative Models for 3D Point Cloud Data
Monocular Depth Estimation Using Neural Regression Forest
DeepStereo: Learning to Predict New Views From the World's Imagery
WIDER FACE: A Face Detection Benchmark
Situation Recognition: Visual Semantic Role Labeling for Image Understanding
A 3D Morphable Model Learnt From 10,000 Faces
Some Like It Hot - Visual Guidance for Preference Prediction
EmotioNet: An Accurate, Real-Time Algorithm for the Automatic Annotation of a Million Facial Expressions in the Wild
ForgetMeNot: Memory-Aware Forensic Facial Sketch Matching
LOMo: Latent Ordinal Model for Facial Analysis in Videos
Discriminative Invariant Kernel Features: A Bells-and-Whistles-Free Approach to Unsupervised Face Recognition and Pose Estimation
Bottom-Up and Top-Down Reasoning With Hierarchical Rectified Gaussians
Fits Like a Glove: Rapid and Reliable Hand Shape Personalization
Slicing Convolutional Neural Network for Crowd Video Understanding
Linear Shape Deformation Models With Local Support Using Graph-Based Structured Matrix Factorisation
Motion From Structure (MfS): Searching for 3D Objects in Cluttered Point Trajectories
Volumetric and Multi-View CNNs for Object Classification on 3D Data
Detecting Vanishing Points Using Global Image Context in a Non-Manhattan World
Learning Weight Uncertainty With Stochastic Gradient MCMC for Shape Classification
A Field Model for Repairing 3D Shapes
GOGMA: Globally-Optimal Gaussian Mixture Alignment
Efficient Deep Learning for Stereo Matching
Efficient Coarse-To-Fine PatchMatch for Large Displacement Optical Flow
FANNG: Fast Approximate Nearest Neighbour Graphs
Exemplar-Driven Top-Down Saliency Detection via Deep Association
Unconstrained Salient Object Detection via Proposal Subset Optimization
Recombinator Networks: Learning Coarse-To-Fine Feature Aggregation
End-To-End Saliency Mapping via Probability Distribution Prediction
A Paradigm for Building Generalized Models of Human Image Perception Through Data Fusion
Longitudinal Face Modeling via Temporal Deep Restricted Boltzmann Machines
Saliency Unified: A Deep Architecture for Simultaneous Eye Fixation Prediction and Salient Object Segmentation
Estimating Correspondences of Deformable Objects "In-The-Wild"
Gravitational Approach for Point Set Registration
Context-Aware Gaussian Fields for Non-Rigid Point Set Registration
Trust No One: Low Rank Matrix Factorization Using Hierarchical RANSAC
Relaxation-Based Preprocessing Techniques for Markov Random Field Inference
Sparse Coding for Classification via Discrimination Ensemble
Principled Parallel Mean-Field Inference for Discrete Random Fields
Guaranteed Outlier Removal With Mixed Integer Linear Programs
Memory Efficient Max Flow for Multi-Label Submodular MRFs
Proximal Riemannian Pursuit for Large-Scale Trace-Norm Minimization
Minimizing the Maximal Rank
Solving Temporal Puzzles
Estimating Sparse Signals With Smooth Support via Convex Programming and Block Sparsity
TenSR: Multi-Dimensional Tensor Sparse Representation
Moral Lineage Tracing
Globally Optimal Rigid Intensity Based Registration: A Fast Fourier Domain Approach
On Benefits of Selection Diversity via Bilevel Exclusive Sparsity
Fast Training of Triplet-Based Deep Binary Embedding Networks
Marr Revisited: 2D-3D Alignment via Surface Normal Prediction
Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning
Fast Zero-Shot Image Tagging
Modality and Component Aware Feature Fusion For RGB-D Scene Classification
PPP: Joint Pointwise and Pairwise Image Label Prediction
Cataloging Public Objects Using Aerial and Street-Level Images - Urban Trees
Deep Exemplar 2D-3D Detection by Adapting From Real to Rendered Views
Zero-Shot Learning via Joint Latent Similarity Embedding
CRAFT Objects From Images