Lihi Zelnik-Manor

CGM lab


Starting Aug.2014 I will be visiting at CornellTech.

I am an associate professor in the Electrical Engineering department in the Technion, Israel.

My team's research is in computer vision, attempting to

- ``separate the wheat from the chaff'': We find the important pixels in an image, what interests people in a video, and which camera provides the best view of a scene. 

- Do things efficiently: We develop compact representations and efficient search methods for matching image features.

e-mail:    lihi 'at'
Phone:    +972-4-8295736
Fax:       +972-4-8295757
Office:     Meyer 959

Address:       Dept. of Electrical Engineering,
                       Technion, Haifa, 32000, Israel


Lihi's picture

ליהי צלניק-מנור


Our paper at ECCV'14:
A new descriptor for scene classification with outstanding performance
  R. Margolin, L. Zelnik-Manor, and A. Tal
"OTC: A Novel Local Descriptor for Scene Classification
 ECCV, 2014 (project page with code)

Our paper at CVPR'14:
Can we trust the common evaluation methods of foreground maps?
  R. Margolin, L. Zelnik-Manor, and A. Tal
" How to Evaluate Foreground Maps?
Spotlight video
 CVPR, 2014 (project page with code

Saliency for image retrieval:

We use image saliency, SIFT saliency and HOG saliency for image retrieval
" CBIR using SIFTpack saliency"

Our paper at ICCV'13:
An efficient alternative for storing and matching lots of SIFTs
  A. Gilinsky and L. Zelnik-Manor,
" SIFTpack: a Compact Representation for Efficient SIFT matching
 ICCV, 2013 (project page with code).

RGBD Super-resolution software:

An implementation and extension to RGBD of the paper
D. Glasner, S. Bagon, M. Irani, "Super-resultion from a single image", ICCV'09 

Depth-map Super-Resolution from a Single Image"

Our paper at VRST'13:
Extending Unwrap-mosaics to 3D inlays:
  D. Rudoy and L. Zelnik-Manor,
Video Inlays: A System for User-Friendly Matchmove",
VRST, 2013 (project page).

Our papers at CVPR'13:
Finally we have a video saliency algorithm that works well:
  D. Rudoy, D.B Goldman, E. Shechtman and L. Zelnik-Manor,
" Learning video saliency from human gaze using candidate selection ",
CVPR, 2013 (project page with code)

Our new solution to image saliency, very fast and highly accurate (code available):
R. Margolin, A. Tal, and L. Zelnik-Manor,
" What Makes a Patch Distinct? ",
 CVPR, 2013 (project page with code)