Sciweavers

127 search results - page 7 / 26
» The Action Similarity Labeling Challenge
Sort
View
77
Voted
ICCV
2009
IEEE
16 years 2 months ago
Weakly supervised discriminative localization and classification: a joint learning process
Visual categorization problems, such as object classification or action recognition, are increasingly often approached using a detection strategy: a classifier function is first ...
Minh Hoai Nguyen, Lorenzo Torresani, Fernando de l...
MM
2003
ACM
165views Multimedia» more  MM 2003»
15 years 2 months ago
Video retrieval using spatio-temporal descriptors
This paper describes a novel methodology for implementing video search functions such as retrieval of near-duplicate videos and recognition of actions in surveillance video. Video...
Daniel DeMenthon, David S. Doermann
82
Voted
NIPS
2007
14 years 11 months ago
Object Recognition by Scene Alignment
Current object recognition systems can only recognize a limited number of object categories; scaling up to many categories is the next challenge. We seek to build a system to reco...
Bryan C. Russell, Antonio Torralba, Ce Liu, Robert...
FOSSACS
2008
Springer
14 years 11 months ago
Symbolic Semantics Revisited
Abstract. Symbolic bisimulations were introduced as a mean to define value-passing process calculi using smaller, possibly finite labelled transition systems, equipped with symboli...
Filippo Bonchi, Ugo Montanari
CVPR
2010
IEEE
15 years 6 months ago
Connecting Modalities: Semi-supervised Segmentation and Annotation of Images Using Unaligned Text Corpora
We propose a semi-supervised model which segments and annotates images using very few labeled images and a large unaligned text corpus to relate image regions to text labels. Give...
Richard Socher, Li Fei-Fei