Transformers in computational visual media: A survey
Transformers, the dominant architecture for natural language processing, have also recently
attracted much attention from computational visual media researchers due to their capacity …
attracted much attention from computational visual media researchers due to their capacity …
A comprehensive survey of convolutions in deep learning: Applications, challenges, and future trends
In today's digital age, Convolutional Neural Networks (CNNs), a subset of Deep Learning
(DL), are widely used for various computer vision tasks such as image classification, object …
(DL), are widely used for various computer vision tasks such as image classification, object …
Cream: Weakly supervised object localization via class re-activation map**
Abstract Weakly Supervised Object Localization (WSOL) aims to localize objects with image-
level supervision. Existing works mainly rely on Class Activation Map** (CAM) derived …
level supervision. Existing works mainly rely on Class Activation Map** (CAM) derived …
Background activation suppression for weakly supervised object localization and semantic segmentation
Weakly supervised object localization and semantic segmentation aim to localize objects
using only image-level labels. Recently, a new paradigm has emerged by generating a …
using only image-level labels. Recently, a new paradigm has emerged by generating a …