Although deep learning has achieved satisfactory performance in computer vision, a large
volume of images is required. However, collecting images is often expensive and …

As an emerging and challenging problem in the computer vision community, weakly
supervised object localization and detection plays an important role for developing new …

This paper proposes a new transformer-based framework to learn class-specific object
localization maps as pseudo labels for weakly supervised semantic segmentation (WSSS) …

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 …

Learning semantic segmentation from weakly-labeled (eg, image tags only) data is
challenging since it is hard to infer dense object regions from sparse semantic tags. Despite …

Abstract Convolutional Neural Networks (CNN) conduct image classification by activating
dominant features that correlated with labels. When the training and testing data are under …

An integral part of video analysis and surveillance is temporal activity detection, which
means to simultaneously recognize and localize activities in long untrimmed videos …

Prior work for articulated 3D shape reconstruction often relies on specialized multi-view and
depth sensors or pre-built deformable 3D models. Such methods do not scale to diverse sets …

In this paper, we present a novel cross-consistency based semi-supervised approach for
semantic segmentation. Consistency training has proven to be a powerful semi-supervised …

Masked autoencoding has achieved great success for self-supervised learning in the image
and language domains. However, mask based pretraining has yet to show benefits for point …