10,957 Hits in 7.9 sec

Projective Feature Learning for 3D Shapes with Multi-View Depth Images

Zhige Xie, Kai Xu, Wen Shan, Ligang Liu, Yueshan Xiong, Hui Huang
2015 Computer graphics forum (Print)  
(a) (b) (c) Figure 1: We propose an projective feature learning method, called MVD-ELM, for learning 3D shape features from multi-view depth images.  ...  We adopt the multi-view depth image representation and propose Multi-View Deep Extreme Learning Machine (MVD-ELM) to achieve fast and quality projective feature learning for 3D shapes.  ...  Machine (ELM) AutoEncoder [CZH13], to learn data-driven features.  ... 
doi:10.1111/cgf.12740 fatcat:hzqcevtckbdzjfuxpf2qwo4dle

MedMNIST v2: A Large-Scale Lightweight Benchmark for 2D and 3D Biomedical Image Classification [article]

Jiancheng Yang, Rui Shi, Donglai Wei, Zequan Liu, Lin Zhao, Bilian Ke, Hanspeter Pfister, Bingbing Ni
2021 arXiv   pre-print
All images are pre-processed into a small size of 28x28 (2D) or 28x28x28 (3D) with the corresponding classification labels so that no background knowledge is required for users.  ...  (binary/multi-class, ordinal regression, and multi-label).  ...  could be formulized as a multi-label binary-class classification task.  ... 
arXiv:2110.14795v1 fatcat:bxqp5dnmhjerzpwsugufuownim

Towards Robust Pattern Recognition: A Review [article]

Xu-Yao Zhang, Cheng-Lin Liu, Ching Y. Suen
2020 arXiv   pre-print
Actually, our brain is robust at learning concepts continually and incrementally, in complex, open and changing environments, with different contexts, modalities and tasks, by showing only a few examples  ...  and identically distributed assumption, and clean and big data assumption, which form the foundation of most pattern recognition models.  ...  Semi-supervised Learning Semi-supervised learning (SSL) deals with a small number of labeled data and a large amount of unlabeled data simultaneously, and therefore, can be viewed as a combination of supervised  ... 
arXiv:2006.06976v1 fatcat:mn35i7bmhngl5hxr3vukdcmmde

Joint auto-encoders: a flexible multi-task learning framework [article]

Baruch Epstein. Ron Meir, Tomer Michaeli
2017 arXiv   pre-print
are learned in a data-driven fashion.  ...  The method deals with domain adaptation and multi-task learning in a unified fashion, and can easily deal with data arising from different types of sources.  ...  on minimizing a loss function that balances between the classification loss of the (labeled) source data and the reconstruction cost of the target data.  ... 
arXiv:1705.10494v1 fatcat:4qz5bhtibja3tfrfequwfe6udi

Uncertain Label Correction via Auxiliary Action Unit Graphs for Facial Expression Recognition [article]

Yang Liu, Xingming Zhang, Janne Kauttonen, Guoying Zhao
2022 arXiv   pre-print
Finally, a re-labeling strategy corrects the ambiguous annotations by comparing their feature similarities with semantic templates.  ...  Specifically, a weighted regularization module is introduced to highlight valid samples and suppress category imbalance in every batch.  ...  In addition, automatically labeled samples in AffectNet are used as a set of real noisy data, denoted as AffectNet Auto, to verify the ability of ULC-AG in handling uncertain expressions.  ... 
arXiv:2204.11053v1 fatcat:mpkxwvvyrbclrnfxj2ud7cqomm

Boosting web video categorization with contextual information from social web

Xiao Wu, Chong-Wah Ngo, Yi-Ming Zhu, Qiang Peng
2011 World wide web (Bussum)  
In this paper, we explore web video categorization from a new perspective, by integrating the model-based and data-driven approaches to boost the performance.  ...  The other improvement is derived from the integration of model-based classification and data-driven majority voting from related videos and user videos.  ...  A Social Web Data-driven Approaches Model-based Classification Majority Voting Semantics Interest Relevance Figure 2 The framework of web video categorization. list of expanded terms, with a weight  ... 
doi:10.1007/s11280-011-0129-1 fatcat:b754uyfdkrezvmjtnjo2uextra

Learning Robust Data Representation: A Knowledge Flow Perspective [article]

Zhengming Ding and Ming Shao and Handong Zhao and Sheng Li
2020 arXiv   pre-print
First of all, we deliver a unified formulation for robust knowledge discovery given single dataset.  ...  Second, we discuss robust knowledge transfer and fusion given multiple datasets with different knowledge flows, followed by practical challenges, model variations, and remarks.  ...  While Liu et al. directly explored a multi-view regression model to recover the consistent knowledge for multi-view multi-label image classification .  ... 
arXiv:1909.13123v2 fatcat:wll23rkrznejvhzsihc6rwcwve

A Brief Survey on Text Classification Using Various Machine Learning Techniques

Padmavathi .S, M. Chidambaram
2018 International Journal of Advanced Research in Computer Science and Software Engineering  
Text classification has grown into more significant in managing and organizing the text data due to tremendous growth of online information.  ...  It does classification of documents in to fixed number of predefined categories. Rule based approach and Machine learning approach are the two ways of text classification.  ...  Therefore, Boost.SH uses a same weight distribution among the views and helps to improve performance of multi-view learning. VI.  ... 
doi:10.23956/ijarcsse.v8i1.521 fatcat:hhwvjsyl3jecxonmu6hwr7ybz4

OpTopNET: A Learning Optimal Topology Synthesizer for Ad-hoc Robot Networks [article]

Matin Macktoobian, Zhan Shu, Qing Zhao
2022 arXiv   pre-print
This problem is technically a multi-task classification problem. However, we divide it into a class of multi-class classification problems that can be more efficiently solved.  ...  Then, we propose a stacked ensemble model whose output is the topology prediction for the particular robot associated with it.  ...  Related Work Various data-driven strategies have been employed to learn topological information of ad-hoc networks.  ... 
arXiv:2201.12900v1 fatcat:2wrhyobygvh6fbus5ec3lvnhku

2020 Index IEEE Transactions on Knowledge and Data Engineering Vol. 32

2021 IEEE Transactions on Knowledge and Data Engineering  
., +, TKDE April 2020 728-738 Parameter-Free Weighted Multi-View Projected Clustering with Structured Graph Learning.  ...  ., +, TKDE April 2020 815-820 Parameter-Free Weighted Multi-View Projected Clustering with Structured Graph Learning.  ... 
doi:10.1109/tkde.2020.3038549 fatcat:75f5fmdrpjcwrasjylewyivtmu

Multi-omics Data and Analytics Integration in Ovarian Cancer [chapter]

Archana Bhardwaj, Kristel Van Steen
2020 IFIP Advances in Information and Communication Technology  
Cancer, which involves the dysregulation of genes via multiple mechanisms, is unlikely to be fully explained by a single data type.  ...  The analysis workflows were applied to real-life data for ovarian cancer and underlined the benefits of joint data and analytic integration.  ...  We thank So Yeon Kim for sharing extended code of iDRW that allows the integration of 3 omics data types.  ... 
doi:10.1007/978-3-030-49186-4_29 fatcat:oy3joxmxsvarvjwio7hhqmapni

Reinforced Co-Training

Jiawei Wu, Lei Li, William Yang Wang
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)  
More specifically, our approach uses Q-learning to learn a data selection policy with a small labeled dataset, and then exploits this policy to train the co-training classifiers automatically.  ...  Co-training is a popular semi-supervised learning framework to utilize a large amount of unlabeled data in addition to a small labeled set.  ...  data and additional auto-labeled set.  ... 
doi:10.18653/v1/n18-1113 dblp:conf/naacl/WuLW18 fatcat:72iawhfbd5evvju2c4kp6xtiny

Reinforced Co-Training [article]

Jiawei Wu, Lei Li, William Yang Wang
2018 arXiv   pre-print
More specifically, our approach uses Q-learning to learn a data selection policy with a small labeled dataset, and then exploits this policy to train the co-training classifiers automatically.  ...  Co-training is a popular semi-supervised learning framework to utilize a large amount of unlabeled data in addition to a small labeled set.  ...  data and additional auto-labeled set.  ... 
arXiv:1804.06035v1 fatcat:w6kzq6wxo5fu5kvkgs423jlpnm

TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-Rays

Xiaosong Wang, Yifan Peng, Le Lu, Zhiyong Lu, Ronald M. Summers
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
The proposed auto-annotation framework achieves high accuracy (over 0.9 on average in AUCs) in assigning disease labels for our hand-label evaluation dataset.  ...  Furthermore, we transform the TieNet into a chest X-ray reporting system. It simulates the reporting process and can output disease classification and a preliminary report together.  ...  Medical Image Auto-Annotation One straightforward application of the TieNet is the auto-annotation task to mine image classification labels.  ... 
doi:10.1109/cvpr.2018.00943 dblp:conf/cvpr/WangPLLS18 fatcat:a24rm6k3tvf7fkyfm6obygpe4i

Detecting 3D Points of Interest Using Multiple Features and Stacked Auto-encoder

Zhenyu Shu, Shiqing Xin, Xin Xu, Ligang Liu, Ladislav Kavan
2018 IEEE Transactions on Visualization and Computer Graphics  
Our algorithm requires two separate deep neural networks (stacked auto-encoders) to accomplish the task.  ...  to what degree p is a point of interest, especially for a specific class of 3D shapes.  ...  Schelling Point method is also data-driven but different from the strategy adopted in this paper -they use a decision tree based regression model (M5P regression trees as provided by Weka) to detect POIs  ... 
doi:10.1109/tvcg.2018.2848628 pmid:29994118 fatcat:pkejfi5wiffifcmzfalu6cifme
« Previous Showing results 1 — 15 out of 10,957 results