Our society may enhance and create new services in a people-centric IoT context through the exchange of information with sensor devices. Unfortunately, communication and services may be compromised due to a number of factors including unreliable communication, complexity, and security threats like spoofing. Within the technologies involved in the IoT paradigm, passive RFID allows the inventorying of simple objects toward wireless communication with a low-cost investment. We present a solution to increase the personalization of IoT applications and services (e.g., accessing a restricted area with a contact- less card) by detecting people-object gestures with an accelerometer-enabled passive RFID tag. We demonstrate the feasibility of our proposal by achieving a precision of 85 percent in people-object gestures classification. As a future task, we aim to implement it in a real scenario.