Adapting Object Detectors from Images to Weakly Labeled Videos.

Omit Chanda Eu Wern Teh Mrigank Rochan Zhenyu Guo Yang Wang

Published in: BMVC (2017)

Keyphrases

weakly labeled
object detectors
weakly supervised
bounding box
image data
image database
object detection
three dimensional
object recognition
input image
image retrieval
ground truth
small number
test images
image classification
image regions
region of interest
multiple images
image features
training data
segmentation algorithm
segmentation method
active learning
image annotation
object categories
target object
co occurrence
image segmentation