Cross-task weakly supervised learning from instructional videos
This addresses the problem of reducing annotation costs for video understanding in instructional contexts, though it is incremental by building on existing weak supervision methods.
The paper tackles learning visual models for task steps using weak supervision from narrations and step lists, showing that cross-task sharing at the component level improves performance and enables parsing of unseen tasks through compositionality.
In this paper we investigate learning visual models for the steps of ordinary tasks using weak supervision via instructional narrations and an ordered list of steps instead of strong supervision via temporal annotations. At the heart of our approach is the observation that weakly supervised learning may be easier if a model shares components while learning different steps: `pour egg' should be trained jointly with other tasks involving `pour' and `egg'. We formalize this in a component model for recognizing steps and a weakly supervised learning framework that can learn this model under temporal constraints from narration and the list of steps. Past data does not permit systematic studying of sharing and so we also gather a new dataset, CrossTask, aimed at assessing cross-task sharing. Our experiments demonstrate that sharing across tasks improves performance, especially when done at the component level and that our component model can parse previously unseen tasks by virtue of its compositionality.