The class activation maps are generated from the final convolutional layer of CNN. They can
highlight discriminative object regions for the class of interest. These discovered object …

Fine-grained bird image classification (FBIC) is not only meaningful for endangered bird
observation and protection but also a prevalent task for image classification in multimedia …

Weakly supervised semantic segmentation with image-level labels has attracted a lot of
attention recently because these labels are already available in most datasets. To obtain …

We introduce a new loss function for the weakly-supervised training of semantic image
segmentation models based on three guiding principles: to seed with weak localization …

We present an approach to learn a dense pixel-wise labeling from image-level tags. Each
image-level tag imposes constraints on the output labeling of a Convolutional Neural …

We are interested in inferring object segmentation by leveraging only object class
information, and by considering only minimal priors on the object segmentation task. This …

As compared to actions, activities are much more complex, but semantically they are more
representative of a human׳ s real life. Techniques for action recognition from sensor …

The technology of image segmentation is widely used in medical image processing, face
recognition pedestrian detection, etc. The current image segmentation techniques include …

The development of smartphones equipped with accelerometers gives a promising way for
researchers to accurately recognize an individual's physical activity in order to better …

In digital pathology, tissue slides are scanned into Whole Slide Images (WSI) and
pathologists first screen for diagnostically-relevant Regions of Interest (ROIs) before …