Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Action tube extraction based 3D-CNN for RGB-D action recognition

Autor
Xu, Z.; Vilaplana, V.; Morros, J.R.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
16th International Conference on Content-Based Multimedia Indexing
Any de l'edició
2018
Data de presentació
2018-11-04
Llibre d'actes
16th International Conference on Content-Based Multimedia Indexing: 4-6 September, 2018 La Rochelle, France
Pàgina inicial
1
Pàgina final
6
DOI
https://doi.org/10.1109/CBMI.2018.8516450 Obrir en finestra nova
Repositori
http://hdl.handle.net/2117/128191 Obrir en finestra nova
Resum
In this paper we propose a novel action tube extractor for RGB-D action recognition in trimmed videos. The action tube extractor takes as input a video and outputs an action tube. The method consists of two parts: spatial tube extraction and temporal sampling. The first part is built upon MobileNet-SSD and its role is to define the spatial region where the action takes place. The second part is based on the structural similarity index (SSIM) and is designed to remove frames without obvious motio...
Paraules clau
3D-CNN, CNN models, action recognition, action tube extraction extraction, indexing (of information), spatial regions, state-of-the-art methods, structural similarity indices (SSIM), temporal sampling, tubes (components), two-stream
Grup de recerca
GPI - Grup de Processament d'Imatge i Vídeo
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants