# Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videos

Source: [Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videos](<https://www.sota2.com/research/paper/68fa6af61e209131cea2b609>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:37:16.577Z

Authors: Reza Ghoddoosian, Saif Sayed, Vassilis Athitsos

Published: 2021-10-12T02:32:15.000Z

## Abstract

This paper focuses on task recognition and action segmentation in weakly-labeled instructional videos, where only the ordered sequence of video-level actions is available during training. We propose a two-stream framework, which exploits semantic and temporal hierarchies to recognize top-level tasks in instructional videos. Further, we present a novel top-down weakly-supervised action segmentation approach, where the predicted task is used to constrain the inference of fine-grained action sequences. Experimental results on the popular Breakfast and Cooking 2 datasets show that our two-stream hierarchical task modeling significantly outperforms existing methods in top-level task recognition for all datasets and metrics. Additionally, using our task recognition framework in the proposed top-down action segmentation approach consistently improves the state of the art, while also reducing segmentation inference time by 80-90 percent.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2110.05697>)

[PDF](<https://arxiv.org/pdf/2110.05697.pdf>)
