Motion estimation and segmentation using a recurrent mixture of experts architecture

Yair Weiss; Edward H. Adelson

Motion estimation and segmentation using a recurrent mixture of experts architecture

Yair Weiss^*
, Edward H. Adelson

^*Corresponding author for this work

Research output: Contribution to conference › Paper › peer-review

6 Scopus citations

Abstract

Estimating motion in scenes containing multiple motions remains a difficult problem for computer vision. Here we describe a novel recurrent network architecture which solves this problem by simultaneously estimating motion and segmenting the scene. The network is comprised of locally connected units which carry out simple calculations in parallel. We present simulation results illustrating the successful motion estimation and rapid convergence of the network on real image sequences.

Original language	English
Pages	293-302
Number of pages	10
State	Published - 1995
Externally published	Yes
Event	Proceedings of the 5th IEEE Workshop on Neural Networks for Signal Processing (NNSP'95) - Cambridge, MA, USA Duration: 31 Aug 1995 → 2 Sep 1995

Conference

Conference	Proceedings of the 5th IEEE Workshop on Neural Networks for Signal Processing (NNSP'95)
City	Cambridge, MA, USA
Period	31/08/95 → 2/09/95

Cite this

@conference{bb873f3180fc43e3a1176e12ca461477,

title = "Motion estimation and segmentation using a recurrent mixture of experts architecture",

abstract = "Estimating motion in scenes containing multiple motions remains a difficult problem for computer vision. Here we describe a novel recurrent network architecture which solves this problem by simultaneously estimating motion and segmenting the scene. The network is comprised of locally connected units which carry out simple calculations in parallel. We present simulation results illustrating the successful motion estimation and rapid convergence of the network on real image sequences.",

author = "Yair Weiss and Adelson, \{Edward H.\}",

year = "1995",

language = "אנגלית",

pages = "293--302",

note = "Proceedings of the 5th IEEE Workshop on Neural Networks for Signal Processing (NNSP'95) ; Conference date: 31-08-1995 Through 02-09-1995",

}

TY - CONF

T1 - Motion estimation and segmentation using a recurrent mixture of experts architecture

AU - Weiss, Yair

AU - Adelson, Edward H.

PY - 1995

Y1 - 1995

N2 - Estimating motion in scenes containing multiple motions remains a difficult problem for computer vision. Here we describe a novel recurrent network architecture which solves this problem by simultaneously estimating motion and segmenting the scene. The network is comprised of locally connected units which carry out simple calculations in parallel. We present simulation results illustrating the successful motion estimation and rapid convergence of the network on real image sequences.

AB - Estimating motion in scenes containing multiple motions remains a difficult problem for computer vision. Here we describe a novel recurrent network architecture which solves this problem by simultaneously estimating motion and segmenting the scene. The network is comprised of locally connected units which carry out simple calculations in parallel. We present simulation results illustrating the successful motion estimation and rapid convergence of the network on real image sequences.

UR - https://www.scopus.com/pages/publications/0029227887

M3 - ???researchoutput.researchoutputtypes.contributiontoconference.paper???

AN - SCOPUS:0029227887

SP - 293

EP - 302

T2 - Proceedings of the 5th IEEE Workshop on Neural Networks for Signal Processing (NNSP'95)

Y2 - 31 August 1995 through 2 September 1995

ER -

Motion estimation and segmentation using a recurrent mixture of experts architecture

Abstract

Conference

Other files and links

Fingerprint

Cite this