Atmospheric turbulence distorts visual imagery and is always problematic for information interpretation by both human and machine. Most well-developed approaches to remove atmospheric turbulence distortion are model-based. However, these methods require high computation and large memory preventing their feasibility of real-time operation. Deep learning-based approaches have hence gained more attention but currently work efficiently only on static scenes. This paper presents a novel learning-based framework offering short temporal spanning to support dynamic scenes. We exploit complex-valued convolutions as phase information, altered by atmospheric turbulence, is captured better than using ordinary real-valued convolutions. Two concatenated modules are proposed. The first module aims to remove geometric distortions and, if enough memory, the second module is applied to refine micro details of the videos. Experimental results show that our proposed framework efficiently mitigate the atmospheric turbulence distortion and significantly outperforms the existing methods.