Results 271 to 280 of about 1,029,862 (299)

Multi-view feature engineering and learning

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
We frame the problem of local representation of imaging data as the computation of minimal sufficient statistics that are invariant to nuisance variability induced by viewpoint and illumination. We show that, under very stringent conditions, these are related to “feature descriptors” commonly used in Computer Vision.
Jingming Dong, Nikolaos Karianakis, Damek Davis, Joshua Hernandez, Jonathan Balzer, Stefano Soatto   +5 more
openaire   +1 more source

Multi-view Transfer Learning with Adaboost

2011 IEEE 23rd International Conference on Tools with Artificial Intelligence, 2011
Transfer learning, serving as one of the most important research directions in machine learning, has been studied in various fields in recent years. In this paper, we integrate the theory of multi-view learning into transfer learning and propose a new algorithm named Multi-View Transfer Learning with Adaboost (MV-TL Adaboost).
Zhijie Xu, Shiliang Sun
openaire   +1 more source

Uniform Projection for Multi-View Learning

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
Multi-view learning aims to integrate multiple data information from different views to improve the learning performance. The key problem is to handle the unconformities or distortions among view-specific samples or measurements of similarity or dissimilarity.
Zhenyue Zhang, Zheng Zhai, Limin Li
openaire   +2 more sources

Multi-view dynamic texture learning

2016 IEEE Winter Conference on Applications of Computer Vision (WACV), 2016
Dynamic texture (DT) provides a flexible and suitable tool for representing phenomena over space and time. We focus here on DT learning for multi-view domains, each of which is sufficient to learn the target concept. We make several contributions in this paper. First, we derive new features and then present their use in our description of DT.
Thanh Minh Nguyen 0001, Q. M. Jonathan Wu   +1 more
openaire   +1 more source

Attentive multi-view reinforcement learning

International Journal of Machine Learning and Cybernetics, 2020
The reinforcement learning process usually takes millions of steps from scratch, due to the limited observation experience. More precisely, the representation approximated by a single deep network is usually limited for reinforcement learning agents.
Yueyue Hu, Shiliang Sun, Xin Xu 0001, Jing Zhao 0015   +3 more
openaire   +1 more source

Multi-View Learning of Network Embedding

2019
In recent years, network representation learning on complex information networks attracts more and more attention. Scholars usually use matrix factorization or deep learning methods to learn network representation automatically. However, existing methods only preserve single feature of networks. How to effectively integrate multiple features of network
Zhongming Han, Chenye Zheng, Dan Liu, Dagao Duan, Weijie Yang   +4 more
openaire   +1 more source

Incorporate Hashing with Multi-view Learning

2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW), 2016
Multi-view learning concentrates on multiple distinct feature sets mainly following either the consensus principle or the complementary principle. SVM-2K, as a typical SVM-based multi-view learning model, extends SVM for multi-view learning by combining Kernel Canonical Correlation Analysis (KCCA).
Jingjing Tang, Dewei Li 0002
openaire   +1 more source

Deep Generative Multi-view Learning

2020
Deep generative networks has attracted proliferating interests recently. In this work, the linear generative multi-view model is extended to nonlinear multi-views model where the deep neural network is leveraged to model complex latent representation underlying the multi-view observation.
openaire   +1 more source

Multi-View Learning With Incomplete Views

IEEE Transactions on Image Processing, 2015
One underlying assumption of the conventional multi-view learning algorithms is that all examples can be successfully observed on all the views. However, due to various failures or faults in collecting and pre-processing the data on different views, we are more likely to be faced with an incomplete-view setting, where an example could be missing its ...
Chang Xu 0002, Dacheng Tao, Chao Xu 0006
openaire   +2 more sources

Multi-view learning with dependent views

Proceedings of the 30th Annual ACM Symposium on Applied Computing, 2015
Multi-view algorithms, such as co-training and co-EM, utilize unlabeled data when the available attributes can be split into independent and compatible subsets. Experiments have shown that multi-view learning is sometimes beneficial for problems for which the independence assumption is not satisfied.
openaire   +1 more source