Human Character-oriented Animated GIF Generation Framework

Click-through rate (CTR) is a critical metric to boost the popularity of newly published videos on streaming platforms. Humans and human-like characters play a significant role in GIF selection and improving the CTR of the video. This paper proposes a new lightweight method to generate human character-oriented animated GIFs using the end-user device's computational capabilities. Instead of analyzing full video, the proposed method analyzes the lightweight thumbnail containers to decrease computational complexity in the GIF generation process. Moreover, it uses the segment to generate the GIF and reduced valuable network bandwidth and storage demands in the user end. A feed-forward 2D deep neural network trained on the CelebA dataset is designed to detect humans or humanlike characters and their gender. Experimental evaluations and results performed in 10 full videos showed that the proposed method is 2.34 times more computationally efficient than the SoA approach. The proposed method is designed to support end-user devices with different computational capabilities.