scholarly journals Large-Scale Video Hashing via Structure Learning

2013 ◽  
Author(s):  
Guangnan Ye ◽  
Dong Liu ◽  
Jun Wang ◽  
Shih-Fu Chang
Keyword(s):  
Large Scale ◽  
Structure Learning ◽  
Video Hashing

scholarly journals Unsupervised Segmentation of Bibliographic Elements with Latent Permutations

2011 ◽  
Vol 2 (2) ◽  
pp. 49-62 ◽  
Author(s):  
Tomonari Masada
Keyword(s):  
Large Scale ◽  
Structure Learning ◽  
Unsupervised Segmentation ◽  
New Approach ◽  
Document Structure ◽  
Word Token ◽  
Token Sequence

This paper introduces a new approach for large-scale unsupervised segmentation of bibliographic elements. The problem is segmenting a citation given as an untagged word token sequence into subsequences so that each subsequence corresponds to a different bibliographic element (e.g., authors, paper title, journal name, publication year, etc.). The same bibliographic element should be referred to by contiguous word tokens. This constraint is called contiguity constraint. The authors meet this constraint by using generalized Mallows models, effectively applied to document structure learning by Chen, Branavan, Barzilay, and Karger (2009). However, the method works for this problem only after modification. Therefore, the author proposes strategies to make the method applicable to this problem.

scholarly journals Dynamic Programming Structure Learning Algorithm of Bayesian Network Integrating MWST and Improved MMPC

2021 ◽  
Vol 2021 ◽  
pp. 1-17
Author(s):  
Ruo-Hai Di ◽  
Ye Li ◽  
Ting-Peng Li ◽  
Lian-Dong Wang ◽  
Peng Wang
Keyword(s):  
Dynamic Programming ◽  
Bayesian Network ◽  
Spanning Tree ◽  
Large Scale ◽  
Structure Learning ◽  
Learning Algorithm ◽  
Maximum Weight ◽  
Significance Level ◽  
Bayesian Network Structure ◽  
Parents And Children

Dynamic programming is difficult to apply to large-scale Bayesian network structure learning. In view of this, this article proposes a BN structure learning algorithm based on dynamic programming, which integrates improved MMPC (maximum-minimum parents and children) and MWST (maximum weight spanning tree). First, we use the maximum weight spanning tree to obtain the maximum number of parent nodes of the network node. Second, the MMPC algorithm is improved by the symmetric relationship to reduce false-positive nodes and obtain the set of candidate parent-child nodes. Finally, with the maximum number of parent nodes and the set of candidate parent nodes as constraints, we prune the parent graph of dynamic programming to reduce the number of scoring calculations and the complexity of the algorithm. Experiments have proved that when an appropriate significance level α is selected, the MMPCDP algorithm can greatly reduce the number of scoring calculations and running time while ensuring its accuracy.

scholarly journals Joint Hierarchical Category Structure Learning and Large-Scale Image Classification

2017 ◽  
Vol 26 (9) ◽  
pp. 4331-4346 ◽  
Author(s):  
Yanyun Qu ◽  
Li Lin ◽  
Fumin Shen ◽  
Chang Lu ◽  
Yang Wu ◽  
...  
Keyword(s):  
Image Classification ◽  
Large Scale ◽  
Structure Learning ◽  
Category Structure

scholarly journals Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval

2019 ◽  
Vol 28 (4) ◽  
pp. 1993-2007 ◽  
Author(s):  
Gengshen Wu ◽  
Jungong Han ◽  
Yuchen Guo ◽  
Li Liu ◽  
Guiguang Ding ◽  
...  
Keyword(s):  
Large Scale ◽  
Video Retrieval ◽  
Video Hashing ◽  
Balanced Code

Large-Scale Unsupervised Hashing with Shared Structure Learning

2015 ◽  
Vol 45 (9) ◽  
pp. 1811-1822 ◽  
Author(s):  
Xianglong Liu ◽  
Yadong Mu ◽  
Danchen Zhang ◽  
Bo Lang ◽  
Xuelong Li
Keyword(s):  
Large Scale ◽  
Structure Learning ◽  
Shared Structure

Attention-based Video Hashing for Large-Scale Video Retrieval

2020 ◽  
pp. 1-1
Author(s):  
Yingxin Wang ◽  
Xiushan Nie ◽  
Yang Shi ◽  
Xin Zhou ◽  
Yilong Yin
Keyword(s):  
Large Scale ◽  
Video Retrieval ◽  
Video Hashing
Sign in / Sign up

Export Citation Format

Share Document