Sciweavers

4366 search results - page 515 / 874
» Image Recognition with Occlusions
Sort
View
170
Voted
ECCV
2010
Springer
15 years 11 months ago
Learning to Recognize Objects from Unseen Modalities
Abstract. In this paper we investigate the problem of exploiting multiple sources of information for object recognition tasks when additional modalities that are not present in the...
MVA
1994
15 years 8 months ago
A study of Joint Set Modeling Based on Edge-Base Stereo Matching
Modeling of 3-D Joint Set Interpretation In order to estimate rock joint parameters, such as strikes and dips which geologists often inspect on site andlor calculate through 3Djoin...
Takeshi Doihara, Tatsuo Ikeda, Kazuo Oda, Masahiro...
PAMI
2002
98views more  PAMI 2002»
15 years 6 months ago
Extraction of Visual Features for Lipreading
The multimodal nature of speech is often ignored in human-computer interaction, but lip deformations and other body motion, such as those of the head, convey additional information...
Iain Matthews, Timothy F. Cootes, J. Andrew Bangha...
ICIP
2009
IEEE
15 years 4 months ago
Semantic keyword extraction via adaptive text binarization of unstructured unsourced video
We propose a fully automatic method for summarizing and indexing unstructured presentation videos based on text extracted from the projected slides. We use changes of text in the ...
Michele Merler, John R. Kender
CVPR
2011
IEEE
14 years 10 months ago
Exploiting Phonological Constraints for Handshape Inference in ASL Video
Handshape is a key linguistic component of signs, and thus, handshape recognition is essential to algorithms for sign language recognition and retrieval. In this work, linguistic ...
Ashwin Thangali, Stan Sclaroff, Carol Neidle, Joan...