Retargeting Semantically-Rich Photos

Luming Zhang, Meng Wang, Liqiang Nie, Liang Hong, Yong Rui, Qi Tian

Abstract

Semantically-rich photos contain a rich variety of semantic objects (e.g., pedestrians and bicycles). Retargeting these photos is a challenging task since each semantic object has fixed geometric characteristics. Shrinking these objects simultaneously during retargeting is prone to distortion. In this paper, we propose to retarget semantically-rich photos by detecting photo semantics from image tags, which are predicted by a multi-label SVM. The key technique is a generative model termed latent stability discovery (LSD). It can robustly localize various semantic objects in a photo by making use of the predicted noisy image tags. Based on LSD, a feature fusion algorithm is proposed to detect salient regions at both the low-level and high-level. These salient regions are linked into a path sequentially to simulate human visual perception . Finally, we learn the prior distribution of such paths from aesthetically pleasing training photos. The prior enforces the path of a retargeted photo to be maximally similar to those from the training photos. In the experiment, we collect 217 1600 ×1200 photos, each containing over seven salient objects. Comprehensive user studies demonstrate the competitiveness of our method.
BibTeX
@article{zhang2015retargeting,
  author = {Luming Zhang and Meng Wang and Liqiang Nie and Liang Hong and Yong Rui and Qi Tian},
  title = {{Retargeting Semantically-Rich Photos}},
  journal = {IEEE Trans. Multimedia},
  year = {2015},
  doi = {10.1109/tmm.2015.2451954},
}

Loading related content...

Figure