Learning To Recognize Procedural Activities with Distant Supervision
Authors:
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 13843-13853
Abstract
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.Keywords
All Related Versions
This publication has 35 references indexed in Scilit:
- Rethinking the Inception Architecture for Computer Vision2016
- Recognizing Fine-Grained and Composite Activities Using Hand-Centric Features and Script DataInternational Journal of Computer Vision, 2015
- A discriminative CNN video representation for event detection2015
- Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks2015
- The Language of Actions: Recovering the Syntax and Semantics of Goal-Directed Human Activities2014
- A database for fine grained activity detection of cooking activities2012
- Modeling Relations and Their Mentions without Labeled Text2010
- Distant supervision for relation extraction without labeled data2009
- Freebase2008
- Acquisition of cognitive skill.Psychological Review, 1982