Papers
arxiv:2303.13800

Aligning Step-by-Step Instructional Diagrams to Video Demonstrations

Published on Dec 2, 2024
Authors:
,
,
,
,

Abstract

A novel supervised contrastive learning method is presented for aligning assembly instruction diagrams with real-world video segments, supported by a new dataset of 183 hours of videos and 8,300 illustrations.

Multimodal alignment facilitates the retrieval of instances from one modality when queried using another. In this paper, we consider a novel setting where such an alignment is between (i) instruction steps that are depicted as assembly diagrams (commonly seen in Ikea assembly manuals) and (ii) video segments from in-the-wild videos; these videos comprising an enactment of the assembly actions in the real world. To learn this alignment, we introduce a novel supervised contrastive learning method that learns to align videos with the subtle details in the assembly diagrams, guided by a set of novel losses. To study this problem and demonstrate the effectiveness of our method, we introduce a novel dataset: IAW for Ikea assembly in the wild consisting of 183 hours of videos from diverse furniture assembly collections and nearly 8,300 illustrations from their associated instruction manuals and annotated for their ground truth alignments. We define two tasks on this dataset: First, nearest neighbor retrieval between video segments and illustrations, and, second, alignment of instruction steps and the segments for each video. Extensive experiments on IAW demonstrate superior performances of our approach against alternatives.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2303.13800
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2303.13800 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2303.13800 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2303.13800 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.