154
Voted
CVPR
2009
IEEE
16 years 10 months ago
2009
IEEE
We present a novel framework for recognizing repetitive
sequential events performed by human actors with strong
temporal dependencies and potential parallel overlap. Our
solutio...
148
click to vote
CVPR
2009
IEEE
16 years 10 months ago
2009
IEEE
We address the problem of label assignment in computer
vision: given a novel 3-D or 2-D scene, we wish to assign a
unique label to every site (voxel, pixel, superpixel, etc.). To...
134
Voted
CVPR
2009
IEEE
16 years 10 months ago
2009
IEEE
Many problems in computer vision can be modeled using
conditional Markov random fields (CRF). Since finding
the maximum a posteriori (MAP) solution in such models
is NP-hard, mu...
141
click to vote
CVPR
2009
IEEE
16 years 10 months ago
2009
IEEE
Multiple-instance Learning (MIL) is a new paradigm
of supervised learning that deals with the classification of
bags. Each bag is presented as a collection of instances
from whi...
157
click to vote
CVPR
2009
IEEE
16 years 10 months ago
2009
IEEE
In many image and video collections, we have access
only to partially labeled data. For example, personal photo
collections often contain several faces per image and a caption
t...