Sciweavers

155 search results - page 9 / 31
» Matching Local Self-Similarities across Images and Videos
Sort
View
ICDAR
2011
IEEE
12 years 7 months ago
Symbol Recognition by Multiresolution Shape Context Matching
—We present a multiresolution scheme for symbol representation and recognition based on statistical shape features. We define a symbol as a set of shape points, each of which is...
Feng Su, Tong Lu, Ruoyu Yang
ICIP
2001
IEEE
14 years 9 months ago
Application of the motion vector constraint to the regularized enhancement of compressed video
In this paper, we present a novel fidelity constraint for the image enhancement problem by exploiting the motion vectors of a compressed video bit-stream. These vectors establish ...
C. Andrew Segall, Aggelos K. Katsaggelos
ACCV
2010
Springer
13 years 2 months ago
Finding Human Poses in Videos Using Concurrent Matching and Segmentation
Abstract. We propose a novel method to detect human poses in videos by concurrently optimizing body part matching and object segmentation. With a single exemplar image, the propose...
Hao Jiang
ICMCS
2006
IEEE
237views Multimedia» more  ICMCS 2006»
14 years 1 months ago
Matching Faces with Textual Cues in Soccer Videos
In soccer videos, most significant actions are usually followed by close–up shots of players that take part in the action itself. Automatically annotating the identity of the p...
Marco Bertini, Alberto Del Bimbo, Walter Nunziati
CIVR
2009
Springer
212views Image Analysis» more  CIVR 2009»
14 years 2 months ago
Video copy detection by fast sequence matching
Sequence matching techniques are effective for comparing two videos. However, existing approaches suffer from demanding computational costs and thus are not scalable for large-sca...
Mei-Chen Yeh, Kwang-Ting Cheng