Cargando…
Human Action Recognition Using Improved Salient Dense Trajectories
Human action recognition in videos is a topic of active research in computer vision. Dense trajectory (DT) features were shown to be efficient for representing videos in state-of-the-art approaches. In this paper, we present a more effective approach of video representation using improved salient de...
Autores principales: | Li, Qingwu, Cheng, Haisu, Zhou, Yan, Huo, Guanying |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Hindawi Publishing Corporation
2016
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4886085/ https://www.ncbi.nlm.nih.gov/pubmed/27293425 http://dx.doi.org/10.1155/2016/6750459 |
Ejemplares similares
-
Image Classification Using Biomimetic Pattern Recognition with Convolutional Neural Networks Features
por: Zhou, Liangji, et al.
Publicado: (2017) -
Salient region detection through salient and non-salient dictionaries
por: Fareed, Mian Muhammad Sadiq, et al.
Publicado: (2019) -
Denoising Method Based on Salient Region Recognition for the Spatiotemporal Event Stream
por: Tang, Sichao, et al.
Publicado: (2023) -
Facial Expression Recognition with Fusion Features Extracted from Salient Facial Areas
por: Liu, Yanpeng, et al.
Publicado: (2017) -
NSCR-Based DenseNet for Lung Tumor Recognition Using Chest CT Image
por: Tao, Zhou, et al.
Publicado: (2020)