Saved in:
Bibliographic Details
Main Authors: Chen, Brian, Shvetsova, Nina, Rouditchenko, Andrew, Kondermann, Daniel, Thomas, Samuel, Chang, Shih-Fu, Feris, Rogerio, Glass, James, Kuehne, Hilde
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2303.16990
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916264122777600
author Chen, Brian
Shvetsova, Nina
Rouditchenko, Andrew
Kondermann, Daniel
Thomas, Samuel
Chang, Shih-Fu
Feris, Rogerio
Glass, James
Kuehne, Hilde
author_facet Chen, Brian
Shvetsova, Nina
Rouditchenko, Andrew
Kondermann, Daniel
Thomas, Samuel
Chang, Shih-Fu
Feris, Rogerio
Glass, James
Kuehne, Hilde
contents Spatio-temporal grounding describes the task of localizing events in space and time, e.g., in video data, based on verbal descriptions only. Models for this task are usually trained with human-annotated sentences and bounding box supervision. This work addresses this task from a multimodal supervision perspective, proposing a framework for spatio-temporal action grounding trained on loose video and subtitle supervision only, without human annotation. To this end, we combine local representation learning, which focuses on leveraging fine-grained spatial information, with a global representation encoding that captures higher-level representations and incorporates both in a joint approach. To evaluate this challenging task in a real-life setting, a new benchmark dataset is proposed providing dense spatio-temporal grounding annotations in long, untrimmed, multi-action instructional videos for over 5K events. We evaluate the proposed approach and other methods on the proposed and standard downstream tasks showing that our method improves over current baselines in various settings, including spatial, temporal, and untrimmed multi-action spatio-temporal grounding.
format Preprint
id arxiv_https___arxiv_org_abs_2303_16990
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle What, when, and where? -- Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions
Chen, Brian
Shvetsova, Nina
Rouditchenko, Andrew
Kondermann, Daniel
Thomas, Samuel
Chang, Shih-Fu
Feris, Rogerio
Glass, James
Kuehne, Hilde
Computer Vision and Pattern Recognition
Spatio-temporal grounding describes the task of localizing events in space and time, e.g., in video data, based on verbal descriptions only. Models for this task are usually trained with human-annotated sentences and bounding box supervision. This work addresses this task from a multimodal supervision perspective, proposing a framework for spatio-temporal action grounding trained on loose video and subtitle supervision only, without human annotation. To this end, we combine local representation learning, which focuses on leveraging fine-grained spatial information, with a global representation encoding that captures higher-level representations and incorporates both in a joint approach. To evaluate this challenging task in a real-life setting, a new benchmark dataset is proposed providing dense spatio-temporal grounding annotations in long, untrimmed, multi-action instructional videos for over 5K events. We evaluate the proposed approach and other methods on the proposed and standard downstream tasks showing that our method improves over current baselines in various settings, including spatial, temporal, and untrimmed multi-action spatio-temporal grounding.
title What, when, and where? -- Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2303.16990