Image (mathematics)

Machine learning

Graph

Artificial intelligence

Closed captioning

Economics

Exploit

Organic chemistry

Scene graph

Chemistry

Management

Distillation

Rendering (computer graphics)

Task (project management)

Object (grammar)

Computer vision

Computer security

Computer science

Theoretical computer science

Spurious relationship

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.

Spatio-Temporal Graph for Video Captioning With Knowledge Distillation