Top-down and bottom-up attentional multiple instance learning for still image action recognition.

Cagdas Bas Nazli Ikizler-Cinbis

Published in: Signal Process. Image Commun. (2022)

Keyphrases

action recognition
multiple instance learning
static images
image data
image content
image features
image representation
image segmentation
multiple instance
bag of words
image classification
input image
multiscale
computer vision
image analysis
human actions
class specific
image collections
image retrieval
image database
image matching
low level
visual words
image annotation
image regions
semi supervised learning
high level
supervised learning