Within the last year
Within the past 3 years
1 - 8 of 8 articles
Highlights ► Periodic motions can be reconstructed in 3D based only on their apparent trajectories viewed from a single camera. ► Focus is on real human motions. ► The degree of periodicity is examined. ► We demonstrate applicability to clinical gait analysis, in the form of a diagnostic...
Highlights ► We separate reflection components based on the surface chromaticity invariant. ► We estimate surface normal for non-Lambertian surfaces. ► We derive a linear relationship between the image color and the surface normal. ► We demonstrate accurate surface reconstruction of...
Highlights ► The shape based view space models pose more accurately. ► The pose recovery in Kalman filter encourages better AAM fitting for face tracking. ► The adaptive incorporation of the local appearance constraint improves robustness. ► Random forest based shape initialization to use...
Highlights ► Extract discriminative parts of an object from any part of the object. ► An extracted discriminative part is not confined to any specified shape. ► Our method can incrementally learn discriminative parts. ► The decision tree technique is used to accelerate recognition...
Highlights ► We learn to recognize exemplars from unstructured collections of captioned images. ► Using language, we perceptually group local features into meaningful parts. ► We further group discovered parts into flexible hierarchical configurations. ► Learned visual structures are...
Highlights ► Each fragment describing a different object part has a reliability value. ► Current visual context dynamically adjusts fragment reliabilities for adaptive cue integration. ► Each fragment contributes to the joint tracking result relative to its reliability. ► Fragments-based...
Highlights ► We study the maximum weight region problem. ► Decomposing for basic shapes has already been studied. ► We consider target shape as a union of basic shapes. ► If regions cannot overlap the problem is in P . ► If regions may overlap it is NP-hard.
Read and print from thousands of top scholarly journals.
Sign up with Facebook
Sign up with Google
Already have an account? Log in
Save this article to read later. You can see your Read Later on your DeepDyve homepage.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Sign Up Log In
To subscribe to email alerts, please log in first, or sign up for a DeepDyve account if you don’t already have one.
To get new article updates from a journal on your personalized homepage, please log in first, or sign up for a DeepDyve account if you don’t already have one.