• Publications
  • Influence
Summarizing visual data using bidirectional similarity
TLDR
We propose a principled approach to summarization of visual data (images or video) based on optimization of a well-defined similarity measure. Expand
Spatio-Temporal Alignment of Sequences
  • Y. Caspi, M. Irani
  • Computer Science
  • IEEE Trans. Pattern Anal. Mach. Intell.
  • 1 November 2002
TLDR
We show that, by folding spatial and temporal cues into a single alignment framework, situations which are inherently ambiguous for traditional image-to-image alignment methods, are often uniquely resolved by sequence- to-sequence alignment. Expand
Feature-Based Sequence-to-Sequence Matching
TLDR
This paper studies the problem of matching two unsynchronized video sequences of the same dynamic scene, recorded by different stationary video cameras. Expand
Space-time super-resolution
TLDR
We propose a method for constructing a video sequence of high space-time resolution by combining information from multiple low-resolution video sequences of the same dynamic scene. Expand
Alignment of non-overlapping sequences
  • Y. Caspi, M. Irani
  • Computer Science
  • Proceedings Eighth IEEE International Conference…
  • 7 July 2001
TLDR
This paper shows how two image sequences that have no spatial overlap between their fields of view can be aligned both in time and in space. Expand
Action synopsis: pose selection and illustration
TLDR
We introduce a method that produces an action synopsis for presenting motion in still images. Expand
A step towards sequence-to-sequence alignment
  • Y. Caspi, M. Irani
  • Computer Science
  • Proceedings IEEE Conference on Computer Vision…
  • 13 June 2000
TLDR
We present an approach for establishing correspondences in time and in space between two different video sequences of the same dynamic scene, recorded by stationary uncalibrated video cameras. Expand
Inducing Semantic Segmentation from an Example
TLDR
In this paper, we present a novel labeling method, which computes a semantically meaningful partitioning of an input image, as induced from one (or more) correctly segmented training image. Expand
Dividing the Archaeal Way: The Ancient Cdv Cell-Division Machinery
Cell division in most prokaryotes is mediated by the well-studied fts genes, with FtsZ as the principal player. In many archaeal species, however, division is orchestrated differently. TheExpand
Increasing Space-Time Resolution in Video
TLDR
We propose a method for constructing a video sequence of high space-time resolution by combining information from multiple low-resolution video sequences of the same dynamic scene. Expand
...
1
2
3
4
...