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 photos, each containing over seven salient objects. Comprehensive user studies demonstrate the competitiveness of our method.