CVAIJun 6, 2023

Learning to Ground Instructional Articles in Videos through Narrations

arXiv:2306.03802v129 citationsh-index: 57
Originality Incremental advance
AI Analysis

This addresses the challenge of automatically grounding instructional content in videos for applications like video search and education, though it is incremental in leveraging multi-modality alignment.

The paper tackles the problem of localizing steps of procedural activities in narrated how-to videos by aligning frames, narrations, and step descriptions from wikiHow without manual supervision, achieving dramatic gains over baselines on new benchmarks like HT-Step and CrossTask.

In this paper we present an approach for localizing steps of procedural activities in narrated how-to videos. To deal with the scarcity of labeled data at scale, we source the step descriptions from a language knowledge base (wikiHow) containing instructional articles for a large variety of procedural tasks. Without any form of manual supervision, our model learns to temporally ground the steps of procedural articles in how-to videos by matching three modalities: frames, narrations, and step descriptions. Specifically, our method aligns steps to video by fusing information from two distinct pathways: i) {\em direct} alignment of step descriptions to frames, ii) {\em indirect} alignment obtained by composing steps-to-narrations with narrations-to-video correspondences. Notably, our approach performs global temporal grounding of all steps in an article at once by exploiting order information, and is trained with step pseudo-labels which are iteratively refined and aggressively filtered. In order to validate our model we introduce a new evaluation benchmark -- HT-Step -- obtained by manually annotating a 124-hour subset of HowTo100M\footnote{A test server is accessible at \url{https://eval.ai/web/challenges/challenge-page/2082}.} with steps sourced from wikiHow articles. Experiments on this benchmark as well as zero-shot evaluations on CrossTask demonstrate that our multi-modality alignment yields dramatic gains over several baselines and prior works. Finally, we show that our inner module for matching narration-to-video outperforms by a large margin the state of the art on the HTM-Align narration-video alignment benchmark.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes