Results 51 to 60 of about 76,480 (326)

Hybrid weakly supervised learning with deep learning technique for detection of fake news from cyber propaganda

Array, 2023
Due to the emergence of social networking sites and social media platforms, there is faster information dissemination to the public. Unverified information is widely disseminated across social media platforms without any apprehension about the accuracy ...
Liyakathunisa Syed, Abdullah Alsaeedi, Lina A. Alhuri, Hutaf R. Aljohani   +3 more
doaj   +1 more source

Hand pose estimation through semi-supervised and weakly-supervised learning [PDF]

Computer Vision and Image Understanding, 2017
13 pages, 10 figures, 4 ...
Neverova, Natalia, Wolf, Christian, Nebout, Florian, Taylor, Graham   +3 more
openaire   +2 more sources

Reducing Label Dependency in Human Activity Recognition with Wearables: From Supervised Learning to Novel Weakly Self-Supervised Approaches

Sensors
Human activity recognition (HAR) using wearable sensors has advanced through various machine learning paradigms, each with inherent trade-offs between performance and labeling requirements.
Taoran Sheng, Manfred Huber
doaj   +1 more source

Instance-Aware Plant Disease Detection by Utilizing Saliency Map and Self-Supervised Pre-Training

Agriculture, 2022
Plant disease detection is essential for optimizing agricultural productivity and crop quality. With the recent advent of deep learning and large-scale plant disease datasets, many studies have shown high performance of supervised learning-based plant ...
Taejoo Kim, Hyeongjun Kim, Kyeonghoon Baik, Yukyung Choi   +3 more
doaj   +1 more source

Weakly supervised label learning flows

Neural Networks
Accepted as a full length research article by Neural ...
You Lu, Wenzhuo Song, Chidubem Arachie, Bert Huang   +3 more
openaire   +3 more sources

Weakly Supervised Learning of Objects, Attributes and Their Associations [PDF]

, 2014
The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-10605-2_31]”
Hospedales, TM, Shi, Z, Xiang, T, Yang, Y   +3 more
core   +3 more sources

WeText: Scene Text Detection under Weak Supervision

, 2017
The requiring of large amounts of annotated training data has become a common constraint on various deep learning systems. In this paper, we propose a weakly supervised scene text detection method (WeText) that trains robust and accurate scene text ...
Li, Chongshou, Lu, Shijian, Tian, Shangxuan   +2 more
core   +1 more source

Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning [PDF]

, 2016
Object category localization is a challenging problem in computer vision. Standard supervised training requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised learning.
Cordelia Schmid, Cordelia Schmid, Cordelia Schmid, Hal Id Hal, Jakob Verbeek, Jakob Verbeek, Jakob Verbeek, Object Local, Ramazan Gokberk Cinbis, Ramazan Gokberk Cinbis, Ramazan Gokberk Cinbis, Weakly Supervised   +11 more
core   +6 more sources

Weakly supervised learning of semantic colour terms

IET Computer Vision, 2014
Recognition of visual attributes in images allows an image's information content to be expressed textually. This has benefits for web search and image archiving, especially since visual attributes transcend language barriers.
David Hanwell, Majid Mirmehdi
doaj   +1 more source

Point-Based Weakly Supervised Learning for Object Detection in High Spatial Resolution Remote Sensing Images

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021
Object detection is challenging in high spatial resolution (HSR) remote sensing images that have a complex background and irregular object locations.
Youyou Li, Binbin He, Farid Melgani, Teng Long   +3 more
doaj   +1 more source