Spatio-Temporal Graph for Video Captioning with Knowledge Distillation

CVPR(2020)

引用 286|浏览390
暂无评分
摘要
Video captioning is a challenging task that requires a deep understanding of visual scenes. State-of-the-art methods generate captions using either scene-level or object-level information but without explicitly modeling object interactions. Thus, they often fail to make visually grounded predictions, and are sensitive to spurious correlations. In this paper, we propose a novel spatio-temporal graph model for video captioning that exploits object interactions in space and time. Our model builds interpretable links and is able to provide explicit visual grounding. To avoid unstable performance caused by the variable number of objects, we further propose an object-aware knowledge distillation mechanism, in which local object information is used to regularize global scene features. We demonstrate the efficacy of our approach through extensive experiments on two benchmarks, showing our approach yields competitive performance with interpretable predictions.
更多
查看译文
关键词
visual scenes,global scene features,local object information,object-aware knowledge distillation mechanism,video captioning,spatio-temporal graph model,visually grounded predictions,object interactions,object-level information,scene-level information
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要