Filters








6,518 Hits in 4.5 sec

Supervised Transfer Sparse Coding

Maruan Al-Shedivat, Jim Jing-Yan Wang, Majed Alzahrani, Jianhua Huang, Xin Gao
2014 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We further propose a unified framework named supervised transfer sparse coding (STSC) which simultaneously optimizes sparse representation, domain transfer and classification.  ...  A combination of the sparse coding and transfer learning techniques was shown to be accurate and robust in classification tasks where training and testing objects have a shared feature space but are sampled  ...  Acknowledgments The authors thank Xiangliang Zhang for a helpful discussion, and Mingsheng Long, Honglak Lee, and Boqing Gong for making their code and data available.  ... 
doi:10.1609/aaai.v28i1.8981 fatcat:4gqalw6t4vcankve3an5zum43i

Learning Category Correlations for Multi-label Image Recognition with Graph Networks [article]

Qing Li, Xiaojiang Peng, Yu Qiao, Qiang Peng
2019 arXiv   pre-print
Specifically, we introduce a plug-and-play Label Graph (LG) module to learn label correlations with word embeddings, and then utilize traditional GCN to map this graph into label-dependent object classifiers  ...  Multi-label image recognition is a task that predicts a set of object labels in an image. As the objects co-occur in the physical world, it is desirable to model label dependencies.  ...  ) that learn powerful visual representation via stacking multiple nonlinear transformations.  ... 
arXiv:1909.13005v1 fatcat:onvqczvlb5f3nmvtzdj7hyavby

Author Index

2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
via Sparse Representation for Palmprint Verification Lindstrom, Peter Triangulation Made Easy Ling, Haibin A New Texture Descriptor Using Multifractal Analysis in Multi-orientation Wavelet Pyramid  ...  Live Dense Reconstruction with a Single Moving Camera Scalable Active Matching Demo: Live Dense Reconstruction with a Single Moving Camera de Campos, Teófilo Unified Graph Matching in Euclidean Spaces  ... 
doi:10.1109/cvpr.2010.5539913 fatcat:y6m5knstrzfyfin6jzusc42p54

CogDL: A Toolkit for Deep Learning on Graphs [article]

Yukuo Cen, Zhenyu Hou, Yan Wang, Qibin Chen, Yizhen Luo, Zhongming Yu, Hengrui Zhang, Xingcheng Yao, Aohan Zeng, Shiguang Guo, Yuxiao Dong, Yang Yang (+6 others)
2022 arXiv   pre-print
In CogDL, we propose a unified design for the training loop of graph neural network (GNN) models, making it unique among existing graph learning libraries.  ...  Additionally, another important CogDL feature is its focus on ease of use with the goal of facilitating open, robust, and reproducible graph learning research.  ...  Representation learning on graphs aims to learn low-dimensional continuous vectors for graph objects, such as vertices and sub-graphs, while preserving intrinsic graph properties.  ... 
arXiv:2103.00959v3 fatcat:34lxb53rxjb2hnx5ramu5nomdq

Multi-graph Fusion for Functional Neuroimaging Biomarker Detection

Jiangzhang Gan, Xiaofeng Zhu, Rongyao Hu, Yonghua Zhu, Junbo Ma, Ziwen Peng, Guorong Wu
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
The multi-graph fusion framework automatically learns the connectivity number for every node (i.e., brain region) and integrates all subjects in a unified framework to output homogenous and discriminative  ...  In this paper, we first propose a new multi-graph fusion framework to fine-tune the original representation derived from Pearson correlation analysis, and then employ L1-SVM on fine-tuned representations  ...  Acknowledgments This work was partially supported by the Natural Science Foundation of China (Grants No: 61876046, 61836016, and 61672177); the Guangxi Collaborative Innovation Center of Multi-Source  ... 
doi:10.24963/ijcai.2020/81 dblp:conf/ijcai/Gan0HZMP020 fatcat:33bgks5gzncefcn45bjolk5mjm

Multi-attributed Dictionary Learning for Sparse Coding

Chen-Kuo Chiang, Te-Feng Su, Chih Yen, Shang-Hong Lai
2013 2013 IEEE International Conference on Computer Vision  
We present a multi-attributed dictionary learning algorithm for sparse coding.  ...  error with correct dictionary) and label-consistent (encouraging the labels of dictionary atoms to be similar).  ...  Then, the dictionaries are learned by partitioning the graph into K clusters via minimizing the objective function which enforces the dictionary to be compact, reconstructive and label-consistent.  ... 
doi:10.1109/iccv.2013.145 dblp:conf/iccv/ChiangSYL13 fatcat:i53ofar575gofloy4wdmwpno34

Detecting User Community in Sparse Domain via Cross-Graph Pairwise Learning

Zheng Gao, Hongsong Li, Zhuoren Jiang, Xiaozhong Liu
2020 Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval  
In this paper, our model, Pairwise Cross-graph Community Detection (PCCD), is proposed to cope with the sparse graph problem by involving external graph knowledge to learn user pairwise community closeness  ...  Supplementary experiments also validate its robustness on graphs with varied sparsity scales.  ...  In the main graph M ( a userobject bipartite graph), we aim to learn object representations H M = {h M 1 , ..., h M n } where h M n denotes the n t h object representation.  ... 
doi:10.1145/3397271.3401055 dblp:conf/sigir/GaoLJL20 fatcat:uh67hg5rjvbq7m6lix5lqbvgge

Multi-View Multi-Instance Learning Based on Joint Sparse Representation and Multi-View Dictionary Learning

Bing Li, Chunfeng Yuan, Weihua Xiong, Weiming Hu, Houwen Peng, Xinmiao Ding, Steve Maybank
2017 IEEE Transactions on Pattern Analysis and Machine Intelligence  
sparse representation that integrates these graphs into a unified framework for bag classification, and (iii) we propose a multi-view dictionary learning algorithm to obtain a multi-view graph dictionary  ...  Index Terms-multi-instance learning, multi-view, sparse representation, dictionary learning !  ...  These structures are represented by undirected graphs generated via the proposed sparse ε-graph model, and are integrated into a unified multi-view joint sparse representation framework for bag classification  ... 
doi:10.1109/tpami.2017.2669303 pmid:28212079 fatcat:tbrnc4zwnrexjkkfizkulf75va

Relational Similarity Machines [article]

Ryan A. Rossi, Rong Zhou, Nesreen K. Ahmed
2016 arXiv   pre-print
For instance, many existing methods perform poorly for multi-class classification problems, graphs that are sparsely labeled or network data with low relational autocorrelation.  ...  In contrast, the proposed relational learning framework is designed to be (i) fast for learning and inference at real-time interactive rates, and (ii) flexible for a variety of learning settings (multi-class  ...  We also investigated relational learning for sparsely labeled graph data.  ... 
arXiv:1608.00876v1 fatcat:eadbxyztnffcnpubj3og53rsv4

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 5817-5831 A Multi-Domain and Multi-Modal Representation Disentangler for Cross-Domain Image Manipulation and Classification.  ...  ., +, TIP 2020 199-213 A Multi-Domain and Multi-Modal Representation Disentangler for Cross-Domain Image Manipulation and Classification.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN [article]

Hang Xu, Linpu Fang, Xiaodan Liang, Wenxiong Kang, Zhenguo Li
2020 arXiv   pre-print
Then an Intra-Domain Reasoning Module learns and propagates the sparse graph representation within one dataset guided by a spatial-aware GCN.  ...  To address these drawbacks, we present a novel universal object detector called Universal-RCNN that incorporates graph transfer learning for propagating relevant semantic information across multiple datasets  ...  It should be noted that pre- 2018b) use fully connected graphs to build object-object relationships, our method instead learn a sparse spatial-aware graph structure to perform graph inference, which can  ... 
arXiv:2002.07417v1 fatcat:jju32xvo5zbe3ma3bzpzz6r2ku

Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN

Hang Xu, Linpu Fang, Xiaodan Liang, Wenxiong Kang, Zhenguo Li
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Then an Intra-Domain Reasoning Module learns and propagates the sparse graph representation within one dataset guided by a spatial-aware GCN.  ...  To address these drawbacks, we present a novel universal object detector called Universal-RCNN that incorporates graph transfer learning for propagating relevant semantic information across multiple datasets  ...  .; Liu et al. 2018a; use fully connected graphs to build object-object relationships, our method instead learn a sparse spatial-aware graph structure to perform graph inference, which can reduce lots  ... 
doi:10.1609/aaai.v34i07.6937 fatcat:vlulmyim2bgxjekytexsmviube

VCIP 2020 Index

2020 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)  
A Unified Single Image De-raining Model via Region Adaptive Coupled Network Meng, Fanman Mining Larger Class Activation Map with Common Attribute Labels Meng, Fanman A New Bounding Box based  ...  Mining Larger Class Activation Map with Common Attribute Labels Ngan, King Ngi A Unified Single Image De-raining Model via Region Adaptive Coupled Network Ngan, King Ngi A New Bounding Box based  ... 
doi:10.1109/vcip49819.2020.9301896 fatcat:bdh7cuvstzgrbaztnahjdp5s5y

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.  ...  It is always demanding to learn robust visual representation for various learning problems; however, this learning and maintenance process usually suffers from noise, incompleteness or knowledge domain  ...  This fusion strategy jointly explores the representation learning and multi-view fusion in a unified framework.  ... 
arXiv:1909.13123v2 fatcat:wll23rkrznejvhzsihc6rwcwve

Special issue on "visual semantic analysis with weak supervision"

Luming Zhang, Yang Yang, Rongrong Ji, Roger Zimmermann
2017 Multimedia Systems  
Thanks to all the people who help us to make this special issue a successful one.  ...  These local sparse codes are then aggregated for object representation, and a classifier is learned to discriminate the target from the background.  ...  In "Semi-supervised Tensor Learning for Image Classification", Zhang et al. proposed a new tensor-based representation algorithm for image classification.  ... 
doi:10.1007/s00530-016-0527-4 fatcat:72hcjiiwfzbk7mdrsumuia7rzy
« Previous Showing results 1 — 15 out of 6,518 results