Sciweavers

12441 search results - page 150 / 2489
» Frame Based Features
Sort
View
CVPR
2011
IEEE
13 years 4 months ago
action recognition by dense trajectories
Feature trajectories have shown to be efficient for representing videos. Typically, they are extracted using the KLT tracker or matching SIFT descriptors between frames. However,...
Heng Wang, Alexander Kläser, Cordelia Schmid, Che...
AMS
2005
Springer
182views Robotics» more  AMS 2005»
14 years 2 months ago
Visual Odometry Using Sparse Bundle Adjustment on an Autonomous Outdoor Vehicle
Visual Odometry is the process of estimating the movement of a (stereo) camera through its environment by matching point features between pairs of consecutive image frames. No prio...
Niko Sünderhauf, Kurt Konolige, Simon Lacroix...
SIP
2001
13 years 10 months ago
Multiresolutional descriptions of digital video in terms of "relevance"
This paper introduces algorithms for determining the "relevance" of each frame (and objects within the frame) to the scenes present in a given video sequence. Specifical...
Onur G. Guleryuz, V. Ratnakar
FLAIRS
2003
13 years 10 months ago
Open Domain Information Extraction via Automatic Semantic Labeling
This paper presents a semantic labeling technique based on information encoded in FrameNet. Sentences labeled for frames relevant to any new Information Extraction domain enable t...
Alessandro Moschitti, Paul Morarescu, Sanda M. Har...
NAACL
2003
13 years 10 months ago
Semantic Extraction with Wide-Coverage Lexical Resources
We report on results of combining graphical modeling techniques with Information Extraction resources (Pattern Dictionary and Lexicon) for both frame and semantic role assignment....
Behrang Mohit, Srini Narayanan