Results 31 to 40 of about 1,256,985 (257)
Metric Learning-Based Multi-Instance Multi-Label Classification With Label Correlation
IEEE Access, 2019 In multi-instance multi-label learning (MIML) problems, predicting the labels of unseen bags becomes difficult when the labels of their instances are not provided directly.
Haifeng Hu +3 more
doaj +1 more source
Multi-Graph Multi-Label Learning Based on Entropy
Entropy, 2018 Recently, Multi-Graph Learning was proposed as the extension of Multi-Instance Learning and has achieved some successes. However, to the best of our knowledge, currently, there is no study working on Multi-Graph Multi-Label Learning, where each object is
Zixuan Zhu, Yuhai Zhao
doaj +1 more source
Robust Multi-Instance Learning with Stable Instances
, 2020 In Proceedings of the Twenty-Fourth European Conference on Artificial Intelligence (ECAI'20)
Zhang, Weijia, Li, Jiuyong, Liu, Lin
openaire +3 more sources
Multi-instance multi-label active learning [PDF]
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017 Multi-instance multi-label learning(MIML) has been successfully applied into many real-world applications. Along with the enhancing of the expressive power, the cost of labelling a MIML example increases significantly. And thus it becomes an important task to train an effective MIML model with as few labelled examples as possible.
Sheng-Jun Huang +2 more
openaire +1 more source
Combine Supervised Edge and Semantic Supplement for Instance Segmentation
IEEE Access, 2022 Two-stage instance segmentation method outperforms the one-stage counterpart on complex occasions. However, we found that the RoIAlign operation identifies the feature map to smaller size, and the convolution or up-sampling causes the loss of detailed ...
Yakun Yang, Wenjie Luo, Xuedong Tian
doaj +1 more source
Stock Market Prediction via Multi-Source Multiple Instance Learning
IEEE Access, 2018 Forecasting the stock market movements is an important and challenging task. As the Web information grows, researchers begin to extract effective indicators (e.g., the events and sentiments) from the Web to facilitate the prediction.
Xi Zhang +4 more
doaj +1 more source
Human activity recognition based on multi‐instance learning
Expert Systems, 2023 AbstractHuman activity recognition (HAR) is the process of classifying a person's actions, and it is an essential task for many human‐centered applications. Multi‐instance learning (MIL) is a special case of machine learning where the training examples are bags containing many instances, and a single class label is assigned for an entire bag of ...
Duygu Bagci Das, Derya Birant
openaire +4 more sources
Multi-Label Learning with Label Enhancement
, 2019 The task of multi-label learning is to predict a set of relevant labels for the unseen instance. Traditional multi-label learning algorithms treat each class label as a logical indicator of whether the corresponding label is relevant or irrelevant to the
Geng, Xin, Shao, Ruifeng, Xu, Ning
core +1 more source
Multi-Task Multi-View Learning Based on Cooperative Multi-Objective Optimization
IEEE Access, 2018 Traditional multi-task multi-view (MTMV) models work under the single-objective learning framework and cannot incorporate too many regularization terms, which are primarily attributed to the utilization of the conventional numerical optimization methods.
Di Zhou +4 more
doaj +1 more source
Groupwise Ranking Loss for Multi-Label Learning
IEEE Access, 2020 This work studies multi-label learning (MLL), where each instance is associated with a subset of positive labels. For each instance, a good multi-label predictor should encourage the predicted positive labels to be close to its ground-truth positive ones.
Yanbo Fan +5 more
doaj +1 more source