Will You Ever Become Popular? Learning to Predict Virality of Dance Clips
This work addresses virality prediction for dance challenges, which has commercial value for applications like smart recommendation and popularity promotion in video communities, but is incremental as it builds on existing multi-modal and graph-based methods.
The paper tackles the problem of predicting virality for dance clips in short-form video platforms, proposing a multi-modal framework that integrates skeletal, appearance, facial, and scenic cues, and achieves effective results validated on a dataset of over 4,000 clips from eight viral dance challenges.
Dance challenges are going viral in video communities like TikTok nowadays. Once a challenge becomes popular, thousands of short-form videos will be uploaded in merely a couple of days. Therefore, virality prediction from dance challenges is of great commercial value and has a wide range of applications, such as smart recommendation and popularity promotion. In this paper, a novel multi-modal framework which integrates skeletal, holistic appearance, facial and scenic cues is proposed for comprehensive dance virality prediction. To model body movements, we propose a pyramidal skeleton graph convolutional network (PSGCN) which hierarchically refines spatio-temporal skeleton graphs. Meanwhile, we introduce a relational temporal convolutional network (RTCN) to exploit appearance dynamics with non-local temporal relations. An attentive fusion approach is finally proposed to adaptively aggregate predictions from different modalities. To validate our method, we introduce a large-scale viral dance video (VDV) dataset, which contains over 4,000 dance clips of eight viral dance challenges. Extensive experiments on the VDV dataset demonstrate the efficacy of our model. Extensive experiments on the VDV dataset well demonstrate the effectiveness of our approach. Furthermore, we show that short video applications like multi-dimensional recommendation and action feedback can be derived from our model.