Proceedings of the 20th ACM international conference on Multimedia
Improving HOG with image segmentation: application to human detection
ACIVS'12 Proceedings of the 14th international conference on Advanced Concepts for Intelligent Vision Systems
TriCoS: a tri-level class-discriminative co-segmentation method for image classification
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
Object-Centric spatial pooling for image classification
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Beyond bounding-boxes: learning object shape by model-driven grouping
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Shape sharing for object segmentation
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Multi-component models for object detection
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
Salient object detection: From pixels to segments
Image and Vision Computing
Exploiting language models to recognize unseen actions
Proceedings of the 3rd ACM conference on International conference on multimedia retrieval
Local context priors for object proposal generation
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Data decomposition and spatial mixture modeling for part based model
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Learning a context aware dictionary for sparse representation
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part II
Object class detection: A survey
ACM Computing Surveys (CSUR)
Hi-index | 0.00 |
For object recognition, the current state-of-the-art is based on exhaustive search. However, to enable the use of more expensive features and classifiers and thereby progress beyond the state-of-the-art, a selective search strategy is needed. Therefore, we adapt segmentation as a selective search by reconsidering segmentation: We propose to generate many approximate locations over few and precise object delineations because (1) an object whose location is never generated can not be recognised and (2) appearance and immediate nearby context are most effective for object recognition. Our method is class-independent and is shown to cover 96.7% of all objects in the Pascal VOC 2007 test set using only 1,536 locations per image. Our selective search enables the use of the more expensive bag-of-words method which we use to substantially improve the state-of-the-art by up to 8.5% for 8 out of 20 classes on the Pascal VOC 2010 detection challenge.