Cargando…
Spatio-Temporal Action Detection in Untrimmed Videos by Using Multimodal Features and Region Proposals
This paper proposes a novel deep neural network model for solving the spatio-temporal-action-detection problem, by localizing all multiple-action regions and classifying the corresponding actions in an untrimmed video. The proposed model uses a spatio-temporal region proposal method to effectively d...
Autores principales: | Song, Yeongtaek, Kim, Incheol |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6427216/ https://www.ncbi.nlm.nih.gov/pubmed/30832433 http://dx.doi.org/10.3390/s19051085 |
Ejemplares similares
-
Segment-Tube: Spatio-Temporal Action Localization in Untrimmed Videos with Per-Frame Segmentation
por: Wang, Le, et al.
Publicado: (2018) -
Joint Multi-object Detection and Segmentation from an Untrimmed Video
por: Liu, Xinling, et al.
Publicado: (2020) -
Spatio-temporal prediction and reconstruction network for video anomaly detection
por: Liu, Ting, et al.
Publicado: (2022) -
A Robotic Context Query-Processing Framework Based on Spatio-Temporal Context Ontology
por: Lee, Seokjun, et al.
Publicado: (2018) -
Spatio-Temporal Features in Action Recognition Using 3D Skeletal Joints
por: Trăscău, Mihai, et al.
Publicado: (2019)