Providing personalized point-of-interest (POI) recommendation has become a major issue with the rapid emergence of location-based social networks (LBSNs). Unlike traditional recommendation approaches, the LBSNs application domain comes with significant geographical and temporal dimensions, which limit performances of most of traditional recommendation algorithms. Fusing geographical and temporal influences into a single factorization model has not been much investigated yet, as far as we know. In this paper, we present GeoMF-TD, an extension of geographical matrix factorization with temporal dependencies. Our experiments on a real dataset shows up to 20% benefit on recommendation precision.