Action representation of manipulable objects has been found to be involved in object recognition. Recently, studies have indicated the existence of two distinct action systems: functional action specifying how to use an object and structural action concerning how to grasp an object. Despite evidence revealing the systems' anatomical and functional differences, few preceding studies have dissociated their respective roles in object recognition. The present study aimed to tease apart their roles in the recognition of manipulable objects with a priming paradigm. Specifically, we used static stimuli (photos, Experiments 1 and 2) and dynamic stimuli (video clips, Experiments 3 and 4) depicting functional and structural action hand gestures as primes and measured the magnitude of functional and structural action priming effect in object recognition. We found that static and dynamic priming stimuli induced a robust action priming effect only for functional action prime-target pairs. Naming latencies of the target objects were shorter when functional action representations of the prime and target were congruent than when they were incongruent. Moreover, as compared to static priming photos, dynamic priming stimuli induced a larger functional action priming effect. By contrast, neither static nor dynamic priming stimuli elicited a structural action priming effect. Behavioral data from our four experiments provide consistent evidence of the dominant role of functional action representation in the recognition of manipulable objects, suggesting that action knowledge regarding how to use rather than grasp an object is more likely an intrinsic component of objects' conceptual representation.