93 search results - page 9 / 19 » Learning to Detect Objects of Many Classes Using Binary Clas... |
EMNLP
2010
13 years 7 months ago
2010
This paper studies the effects of training data on binary text classification and postulates that negative training data is not needed and may even be harmful for the task. Tradit...
CVPR
2011
IEEE
13 years 6 months ago
2011
IEEE
The bounding box representation employed by many popular object detection models [3, 6] implicitly assumes all pixels inside the box belong to the object. This assumption makes th...
ICML
2007
IEEE
14 years 10 months ago
2007
IEEE
We present a comprehensive suite of experimentation on the subject of learning from imbalanced data. When classes are imbalanced, many learning algorithms can suffer from the pers...
CVPR
2008
IEEE
14 years 11 months ago
2008
IEEE
The required amount of labeled training data for object detection and classification is a major drawback of current methods. Combining labeled and unlabeled data via semisupervise...
CVPR
2008
IEEE
2008
IEEE
Discovering class specific composite features through discriminative sampling with Swendsen-Wang Cut
14 years 11 months ago
This paper proposes a novel approach to discover a set of class specific "composite features" as the feature pool for the detection and classification of complex objects...