Sciweavers

116 search results - page 5 / 24
» Towards using multiple cues for robust object recognition
Sort
View
ICCV
2009
IEEE
1335views Computer Vision» more  ICCV 2009»
15 years 14 days ago
Top-Down Color Attention for Object Recognition
Generally the bag-of-words based image representation follows a bottom-up paradigm. The subsequent stages of the process: feature detection, feature description, vocabulary cons...
Fahad Shahbaz Khan, Joost van de Weijer, Maria Van...
ICRA
2000
IEEE
192views Robotics» more  ICRA 2000»
13 years 12 months ago
Robust Localization for 3D Object Recognition Using Local EGI and 3D Template Matching with M-Estimators
A tele-operated system in a robot greatly reduces the demands on the human operator, although some human intervention is still required to perform such tasks as insulator recognit...
Kentaro Kawamura, Kiminori Hasegawa, Yasuyuki Some...
CIVR
2008
Springer
279views Image Analysis» more  CIVR 2008»
13 years 9 months ago
Semi-supervised learning of object categories from paired local features
This paper presents a semi-supervised learning (SSL) approach to find similarities of images using statistics of local matches. SSL algorithms are well known for leveraging a larg...
Wen Wu, Jie Yang
AIPR
2001
IEEE
13 years 11 months ago
Towards Robust Face Recognition from Video
A novel, template-based method for face recognition is presented. The goals of the proposed method are to integrate multiple observations for improved robustness and to provide au...
Jeffery R. Price, Timothy F. Gee
CVPR
2004
IEEE
13 years 11 months ago
A Probabilistic Approach to Image Orientation Detection via Confidence-Based Integration of Low-Level and Semantic Cues
Automatic image orientation detection for natural images is a useful, yet challenging research area. Humans use scene context and semantic object recognition to identify the corre...
Jiebo Luo, Matthew R. Boutell