Zero-Shot Video Grounding for Automatic Video Understanding in Sustainable Smart Cities

Ping Wang, Li Sun, Liuan Wang and Jun Sun ()
Additional contact information
Ping Wang: Fujitsu Research & Development Center Co., Ltd., Beijing 100022, China
Li Sun: Fujitsu Research & Development Center Co., Ltd., Beijing 100022, China
Liuan Wang: Fujitsu Research & Development Center Co., Ltd., Beijing 100022, China
Jun Sun: Fujitsu Research & Development Center Co., Ltd., Beijing 100022, China

Sustainability, 2022, vol. 15, issue 1, 1-22

Abstract: Automatic video understanding is a crucial piece of technology which promotes urban sustainability. Video grounding is a fundamental component of video understanding that has been evolving quickly in recent years, but its use is restricted due to the high labeling costs and typical performance limitations imposed by the pre-defined training dataset. In this paper, a novel atom-based zero-shot video grounding (AZVG) method is proposed to retrieve the segments in the video that correspond to a given input sentence. Although it is training-free, the performance of AZVG is competitive to the weakly supervised methods and better than unsupervised SOTA methods on the Charades-STA dataset. The method can support flexible queries as well as different video content. It can play an important role in a wider range of urban living applications.

Keywords: video grounding; video understanding; zero-shot; multi-modality; CLIP (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/15/1/153/pdf (application/pdf)
https://www.mdpi.com/2071-1050/15/1/153/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:15:y:2022:i:1:p:153-:d:1011338

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().