Learning To Recognize Procedural Activities with Distant Supervision
This work addresses the challenge of recognizing complex procedural activities in videos for applications like cooking or home improvement, but it is incremental as it builds on existing methods for distant supervision.
The paper tackles the problem of classifying fine-grained, multi-step activities from long videos by addressing the lack of step annotations due to high annotation costs. It proposes using distant supervision from a textual knowledge base (wikiHow) to automatically label steps, resulting in video models that achieve superior generalization on four downstream tasks, such as recognition of procedural activities and step classification.
In this paper we consider the problem of classifying fine-grained, multi-step activities (e.g., cooking different recipes, making disparate home improvements, creating various forms of arts and crafts) from long videos spanning up to several minutes. Accurately categorizing these activities requires not only recognizing the individual steps that compose the task but also capturing their temporal dependencies. This problem is dramatically different from traditional action classification, where models are typically optimized on videos that span only a few seconds and that are manually trimmed to contain simple atomic actions. While step annotations could enable the training of models to recognize the individual steps of procedural activities, existing large-scale datasets in this area do not include such segment labels due to the prohibitive cost of manually annotating temporal boundaries in long videos. To address this issue, we propose to automatically identify steps in instructional videos by leveraging the distant supervision of a textual knowledge base (wikiHow) that includes detailed descriptions of the steps needed for the execution of a wide variety of complex activities. Our method uses a language model to match noisy, automatically-transcribed speech from the video to step descriptions in the knowledge base. We demonstrate that video models trained to recognize these automatically-labeled steps (without manual supervision) yield a representation that achieves superior generalization performance on four downstream tasks: recognition of procedural activities, step classification, step forecasting and egocentric video classification.