Ahn, Hyemin und Lee, Dongheui (2021) Refining action segmentation with hierarchical video representations. In: 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021, Seiten 16302-16310. IEEE. international Conference on Computer Vision, 2021-10-11 - 2021-10-17, Virtual. doi: 10.1109/ICCV48922.2021.01599. ISBN 978-166542812-5. ISSN 1550-5499.
PDF
2MB |
Kurzfassung
In this paper, we propose Hierarchical Action Segmentation Refiner (HASR), which can refine temporal action segmentation results from various models by understanding the overall context of a given video in a hierarchical way. When a backbone model for action segmentation estimates how the given video can be segmented, our model extracts segment-level representations based on frame-level features, and extracts a video-level representation based on the segment-level representations. Based on these hierarchical representations, our model can refer to the overall context of the entire video, and predict how the segment labels that are out of context should be corrected. Our HASR can be plugged into various action segmentation models (MS-TCN, SSTDA, ASRF), and improve the performance of state-of-the-art models based on three challenging datasets (GTEA, 50Salads, and Breakfast). For example, in 50Salads dataset, the segmental edit score improves from 67.9% to 77.4% (MS-TCN), from 75.8% to 77.3% (SSTDA), from 79.3% to 81.0% (ASRF). In addition, our model can refine the segmentation result from the unseen backbone model, which was not referred to when training HASR. This generalization performance would make HASR be an effective tool for boosting up the existing approaches for temporal action segmentation. Our code is available at https://github.com/cotton-ahn/HASR_iccv2021.
elib-URL des Eintrags: | https://elib.dlr.de/147186/ | ||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dokumentart: | Konferenzbeitrag (Poster) | ||||||||||||
Zusätzliche Informationen: | This work has been partially supported by the Helmholtz Association. | ||||||||||||
Titel: | Refining action segmentation with hierarchical video representations | ||||||||||||
Autoren: |
| ||||||||||||
Datum: | Oktober 2021 | ||||||||||||
Erschienen in: | 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021 | ||||||||||||
Referierte Publikation: | Ja | ||||||||||||
Open Access: | Ja | ||||||||||||
Gold Open Access: | Nein | ||||||||||||
In SCOPUS: | Ja | ||||||||||||
In ISI Web of Science: | Ja | ||||||||||||
DOI: | 10.1109/ICCV48922.2021.01599 | ||||||||||||
Seitenbereich: | Seiten 16302-16310 | ||||||||||||
Verlag: | IEEE | ||||||||||||
ISSN: | 1550-5499 | ||||||||||||
ISBN: | 978-166542812-5 | ||||||||||||
Status: | veröffentlicht | ||||||||||||
Stichwörter: | Video Action Segmentation; Computer Vision; Deep Learning | ||||||||||||
Veranstaltungstitel: | international Conference on Computer Vision | ||||||||||||
Veranstaltungsort: | Virtual | ||||||||||||
Veranstaltungsart: | internationale Konferenz | ||||||||||||
Veranstaltungsbeginn: | 11 Oktober 2021 | ||||||||||||
Veranstaltungsende: | 17 Oktober 2021 | ||||||||||||
Veranstalter : | IEEE Computer Society | ||||||||||||
HGF - Forschungsbereich: | Luftfahrt, Raumfahrt und Verkehr | ||||||||||||
HGF - Programm: | Raumfahrt | ||||||||||||
HGF - Programmthema: | Robotik | ||||||||||||
DLR - Schwerpunkt: | Raumfahrt | ||||||||||||
DLR - Forschungsgebiet: | R RO - Robotik | ||||||||||||
DLR - Teilgebiet (Projekt, Vorhaben): | R - Autonome, lernende Roboter [RO], R - Intuitive Mensch-Roboter Schnittstelle [RO] | ||||||||||||
Standort: | Oberpfaffenhofen | ||||||||||||
Institute & Einrichtungen: | Institut für Robotik und Mechatronik (ab 2013) | ||||||||||||
Hinterlegt von: | Ahn, Hyemin | ||||||||||||
Hinterlegt am: | 10 Dez 2021 09:22 | ||||||||||||
Letzte Änderung: | 24 Apr 2024 20:45 |
Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags