In several application domains (e.g., crop conversion subsidies, forestry, natural hazard mapping, and spatial planning), the ultimate operational objective of change-detection analysis is actually limited to the identification of only one (or few) specific land-cover transition(s) of interest (i.e., a "targeted" change detection problem), disregarding all the other potential changes occurring in the area under analysis at the same time. Supervised change-detection techniques generally represent the most accurate methodological solution for mapping land-cover changes while identifying the associated land-cover transitions between two different dates. However, the application of these techniques depends on the availability of exhaustive ground-truth information for all the land-cover classes present in the area of interest at the times under investigation. Such a requirement is seldom satisfied since gathering a reliable ground truth for all the classes characterizing the considered scenes at the two dates under analysis presents several practical drawbacks and limitations (both in terms of time and economic cost) that may render this task almost impossible in most real-life cases. Nevertheless, to solve these specific types of problems, it would be highly beneficial for an operator to rely on a robust automatic technique that may allow an effective detection of the "targeted" land-cover transitions by taking into account only ground-truth information for the few classes of interest at each date (thus, avoiding the burden and cost associated to the collection of a full and exhaustive ground-truth data set at both times). In this paper, we address this challenging issue and propose a novel technique (formulated in terms of a compound decision problem) capable of identifying specific "targeted" land-cover transitions by exploiting the ground truth available only for the classes of interest at the two dates, while providing accuracies comparable to those of traditional - - fully supervised change-detection methods. The proposed technique relies on a partially supervised approach that jointly exploits the expectation-maximization algorithm and an iterative labeling strategy based on Markov random fields accounting for spatial and temporal correlation between the two images. Moreover, the proposed method is applicable to images acquired by different sensors (or to different sets of features) at the two investigated times. Experimental results on different multitemporal and multisensor data sets confirmed the effectiveness and the reliability of the proposed technique.