Cameras record the world using more and more pixels. Watching and processing all this data takes lots of time, which we don’t always want to spend. But do we really need all the pixels? in many cases the answer is no. When multiple cameras view the same scene often a single good view suffices to visualize what’s going on. Within a single view keeping only the “important” pixels suffices to convey the story the image or video tells. Our team develops algorithms for finding the “important”, or salient, parts of an image or video.
Presentations
Relevant papers
- O. Barzilay, L. Zelnik-Manor, Y. Gutfreund, H. Wagner, and A. Wolf, From Biokinematics to a Robotic Active Vision System, To appear in Journal of Bioinspiration & Biomimetics.
- Roey Mechrez, Eli Shechtman, Lihi Zelnik-Manor, Saliency Driven Image Manipulation, arXiv preprint arXiv:1612.02184, 7 Dec 2016. (pdf)
- D. Glasner, P. Fua, T. Zickler and L. Zelnik-Manor, Hot or Not: Exploring Correlations Between Appearance and Temperature, ICCV’2015 (pdf, Project page)
- R. Margolin, L. Zelnik-Manor, and A. Tal, How to Evaluate Foreground Maps?, CVPR’2014. (pdf, Project page)
- D. Rudoy, D.B Goldman, E. Shechtman and L. Zelnik-Manor, Learning video saliency from human gaze using candidate selection, CVPR’2013. (pdf, Project page)
- R. Margolin, A. Tal, and L. Zelnik-Manor, What Makes a Patch Distinct?, CVPR’2013. (pdf, Project page)
- R. Margolin, L. Zelnik-Manor, and A. Tal, Saliency For Image Manipulation, The Visual Computer, June 2012. (pdf, Project page)
- R. Margolin, L. Zelnik-Manor, and A. Tal, Saliency For Image Manipulation, Computer Graphics International, CGI’2012. (pdf, Project page)
- S. Goferman, L. Zelnik-Manor, and A. Tal, Context-Aware Saliency Detection , IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), 34(10): 1915–1926, Oct. 2012, PAMI’2012. (pdf, Project page)
- D. Rudoy, D.B. Goldman, E. Shechtman and L. Zelnik-Manor, Crowdsourcing Gaze Data Collection, Conference on Collective Intelligence, April 2012. (pdf, Project page)
- D. Rudoy and L. Zelnik-Manor, Viewpoint Selection for Human Actions , International Journal of Computer Vision (IJCV), Vol. 97, No.3, March 2012. (pdf)
- D. Rudoy and L. Zelnik-Manor, Posing to the camera: Automatic viewpoint selection for human actions, ACCV’2010. (pdf)
- M. Holtzman-Gazit, L. Zelnik-Manor and I. Yavne, Salient Edges: A Multi Scale Approach, ECCV 2010 Workshop on Vision for Cognitive Tasks. (pdf)
- S. Goferman, L. Zelnik-Manor, and A. Tal, Context-Aware Saliency Detection, CVPR’2010. (pdf, Project page))