Valls Mascaró, Esteve und Ahn, Hyemin und Lee, Dongheui (2023) Intention-Conditioned Long-Term Human Egocentric Action Anticipation. In: 23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023, Seiten 6037-6046. IEEE. 2023 IEEE/CVF Winter Conference on Applications of Computer Vision, 2023-01-02 - 2023-01-07, Waikoloa, HI, USA. doi: 10.1109/WACV56688.2023.00599. ISBN 978-166549346-8. ISSN 2472-6737.
Dieses Archiv kann nicht den Volltext zur Verfügung stellen.
Offizielle URL: https://ieeexplore.ieee.org/document/10030492
Kurzfassung
To anticipate how a person would act in the future, it is essential to understand the human intention since it guides the subject towards a certain action. In this paper, we propose a hierarchical architecture which assumes a sequence of human action (low-level) can be driven from the human intention (high-level). Based on this, we deal with long-term action anticipation task in egocentric videos. Our framework first extracts this low- and high-level human information over the observed human actions in a video through a Hierarchical Multi-task Multi-Layer Perceptrons Mixer (H3M). Then, we constrain the uncertainty of the future through an Intention-Conditioned Variational Auto-Encoder (I-CVAE) that generates multiple stable predictions of the next actions that the observed human might perform. By leveraging human intention as high-level information, we claim that our model is able to anticipate more time-consistent actions in the long-term, thus improving the results over the baseline in Ego4D dataset. This work results in the state-of-the-art for Long-Term Anticipation (LTA) task in Ego4D by providing more plausible anticipated sequences, improving the anticipation scores of nouns and actions. Our work ranked first in both CVPR@2022 and ECCV@2022 Ego4D LTA Challenge.
elib-URL des Eintrags: | https://elib.dlr.de/197483/ | ||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dokumentart: | Konferenzbeitrag (Vortrag) | ||||||||||||||||
Titel: | Intention-Conditioned Long-Term Human Egocentric Action Anticipation | ||||||||||||||||
Autoren: |
| ||||||||||||||||
Datum: | 6 Februar 2023 | ||||||||||||||||
Erschienen in: | 23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023 | ||||||||||||||||
Referierte Publikation: | Ja | ||||||||||||||||
Open Access: | Nein | ||||||||||||||||
Gold Open Access: | Nein | ||||||||||||||||
In SCOPUS: | Ja | ||||||||||||||||
In ISI Web of Science: | Ja | ||||||||||||||||
DOI: | 10.1109/WACV56688.2023.00599 | ||||||||||||||||
Seitenbereich: | Seiten 6037-6046 | ||||||||||||||||
Verlag: | IEEE | ||||||||||||||||
ISSN: | 2472-6737 | ||||||||||||||||
ISBN: | 978-166549346-8 | ||||||||||||||||
Status: | veröffentlicht | ||||||||||||||||
Stichwörter: | Action Anticipation | ||||||||||||||||
Veranstaltungstitel: | 2023 IEEE/CVF Winter Conference on Applications of Computer Vision | ||||||||||||||||
Veranstaltungsort: | Waikoloa, HI, USA | ||||||||||||||||
Veranstaltungsart: | internationale Konferenz | ||||||||||||||||
Veranstaltungsbeginn: | 2 Januar 2023 | ||||||||||||||||
Veranstaltungsende: | 7 Januar 2023 | ||||||||||||||||
Veranstalter : | IEEE | ||||||||||||||||
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 - Basistechnologien [RO] | ||||||||||||||||
Standort: | Oberpfaffenhofen | ||||||||||||||||
Institute & Einrichtungen: | Institut für Robotik und Mechatronik (ab 2013) | ||||||||||||||||
Hinterlegt von: | Strobl, Dr. Klaus H. | ||||||||||||||||
Hinterlegt am: | 22 Sep 2023 12:56 | ||||||||||||||||
Letzte Änderung: | 24 Apr 2024 20:57 |
Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags