Sciweavers

75 search results - page 15 / 15
» Earth Mover Distance on superpixels
Sort
View
CVIU
2008
192views more  CVIU 2008»
13 years 5 months ago
Content based video matching using spatiotemporal volumes
This paper presents a novel framework for matching video sequences using the spatiotemporal segmentation of videos. Instead of using appearance features for region correspondence ...
Arslan Basharat, Yun Zhai, Mubarak Shah
PAMI
2008
146views more  PAMI 2008»
13 years 4 months ago
Video Event Recognition Using Kernel Methods with Multilevel Temporal Alignment
In this work, we systematically study the problem of event recognition in unconstrained news video sequences. We adopt the discriminative kernel-based method for which video clip s...
Dong Xu, Shih-Fu Chang
CVIU
2004
115views more  CVIU 2004»
13 years 4 months ago
Context-dependent segmentation and matching in image databases
The content of an image can be summarized by a set of homogeneous regions in an appropriate feature space. When exact shape is not important, the regions can be represented by sim...
Hayit Greenspan, Guy Dvir, Yossi Rubner
BMVC
2010
13 years 3 months ago
Automatic annotation of unique locations from video and text
Given a video and associated text, we propose an automatic annotation scheme in which we employ a latent topic model to generate topic distributions from weighted text and then mo...
Chris Engels, Koen Deschacht, Jan Hendrik Becker, ...
APPROX
2011
Springer
234views Algorithms» more  APPROX 2011»
12 years 5 months ago
Streaming Algorithms with One-Sided Estimation
Abstract. We study the space complexity of randomized streaming algorithms that provide one-sided approximation guarantees; e.g., the algorithm always returns an overestimate of th...
Joshua Brody, David P. Woodruff