SFMVIT: Slowfast Meet VIT in Chaotic World

The task of spatiotemporal action localization in chaotic scenes is a challenging task toward advanced video under-standing. Paving the way with high-quality video feature extraction and enhancing the precision of detector-predicted anchors can effectively improve model performance. To this end, we propose a high-performance dual-stream spatiotem-poral feature extraction network SFMViT with an anchor pruning strategy. The backbone of our SFMViT is composed of ViT and SlowFast with prior knowledge of spa-tiotemporal action localization, which fully utilizes ViT's excellent global feature extraction capabilities and Slow-Fast's spatiotemporal sequence modeling capabilities. Secondly, we introduce the confidence maximum heap to prune the anchors detected in each frame of the picture to filter out the effective anchors. These designs enable our SFMViT to achieve a mAP of 26.62% in the Chaotic World dataset, far exceeding existing models. Code is available at https://github.com/jfightyr/SlowFast-Meet-ViT.