23,249 Hits in 7.9 sec

Learning and using taxonomies for fast visual categorization

Gregory Griffin, Pietro Perona
2008 2008 IEEE Conference on Computer Vision and Pattern Recognition  
We explore algorithms for automatically building classification trees which have, in principle, log N cat complexity.  ...  The computational complexity of current visual categorization algorithms scales linearly at best with the number of categories.  ...  Acknowledgments Research funded by National Science Foundation grant NSF IIS-0535292 and by ONR MURI grant N00014-06-0734.  ... 
doi:10.1109/cvpr.2008.4587410 dblp:conf/cvpr/GriffinP08 fatcat:aliaue2755g3dbvu4sidiy6kku

Fast Density Clustering Algorithm for Numerical Data and Categorical Data

Chen Jinyin, He Huihao, Chen Jungan, Yu Shanqing, Shi Zhaoxia
2017 Mathematical Problems in Engineering  
Data objects with mixed numerical and categorical attributes are often dealt with in the real world.  ...  A novel data similarity metric is designed for clustering data including numerical attributes and categorical attributes.  ...  Acknowledgments This work was supported by a grant from the National Natural Science Foundation of China (no. 61502423), Zhejiang Provincial Natural Science Foundation (Y14F020092), and Zhejiang Natural  ... 
doi:10.1155/2017/6393652 fatcat:rnco66f7vzg7nohlxtjnwqjlbm


Tien-Dung Mai
2016 Journal of Computer Science and Cybernetics  
Furthermore, we proposed an algorithm for learning a balanced tree which gains the computational efficiency in classification.  ...  A challenging issue is how to learn a tree structure which achieves both classification accuracy and computational efficiency.  ...  CONCLUSION AND FUTURE WORK In this paper, we proposed a method for learning an effective and balanced label tree for efficient multi-class classification.  ... 
doi:10.15625/1813-9663/32/2/7574 fatcat:cjlioemftvba5lug2i2x5ddumm

Fast image search for learned metrics

Prateek Jain, Brian Kulis, Kristen Grauman
2008 2008 IEEE Conference on Computer Vision and Pattern Recognition  
Our learned metrics improve accuracy relative to commonly-used metric baselines, while our hashing construction enables efficient indexing with learned distances and very large databases. 978-1-4244-2243  ...  We further formulate an indirect solution that enables metric learning and hashing for vector spaces whose high dimensionality make it infeasible to learn an explicit weighting over the feature dimensions  ...  Acknowledgements: We thank Greg Shakhnarovich for sharing the Poser data. This research was supported in part by grants from ORAU and Microsoft Research.  ... 
doi:10.1109/cvpr.2008.4587841 dblp:conf/cvpr/JainKG08 fatcat:qf7rlbtyxff4fkvltt33cnz46i

Espresso: A Fast End-to-end Neural Speech Recognition Toolkit [article]

Yiming Wang and Tongfei Chen and Hainan Xu and Shuoyang Ding and Hang Lv and Yiwen Shao and Nanyun Peng and Lei Xie and Shinji Watanabe and Sanjeev Khudanpur
2019 arXiv   pre-print
We present Espresso, an open-source, modular, extensible end-to-end neural automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch and the popular neural machine translation  ...  a fast, parallelized decoder is implemented.  ...  The gold transcript set is not large enough to produce state-of-theart neural language models, which are typically trained on a corpus on the scale of 1 billion words.  ... 
arXiv:1909.08723v3 fatcat:ssnd5gbb2fc5tfppvoqw5z7vuy

Fast approximate k-means via cluster closures

Jing Wang, Jingdong Wang, Qifa Ke, Gang Zeng, Shipeng Li
2012 2012 IEEE Conference on Computer Vision and Pattern Recognition  
and efficiency.  ...  The idea is to efficiently identify those active points by pre-assembling the data into groups of neighboring points using multiple random spatial partition trees, and to use the neighborhood information  ...  Acknowledgements The research work of Jing Wang and Gang Zeng is supported by NSFC Grant 61005037 and 90920304, and BJNSF Grant 4113071.  ... 
doi:10.1109/cvpr.2012.6248034 dblp:conf/cvpr/WangWKZL12 fatcat:pkxqitrfzjgt7oaclxunhxmefm

Semantic Channels for Fast Pedestrian Detection

Arthur Daniel Costea, Sergiu Nedevschi
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
In this work we propose a fast solution for achieving state of art results for both pedestrian detection and semantic segmentation.  ...  To also achieve fast pedestrian detection we employ a multiscale detection scheme based on a single flexible pedestrian model and a single image scale.  ...  These approaches retrieve visually similar images from large databases, use label-transfer techniques for predicting class-labels and are more practical for dynamically changing large datasets with high  ... 
doi:10.1109/cvpr.2016.259 dblp:conf/cvpr/CosteaN16 fatcat:pn2d7sxbqvbcfkigsk4zaec5lu

A Fast Panoptic Segmentation Network for Self-Driving Scene Understanding

Abdul Majid, Sumaira Kausar, Samabia Tehsin, Amina Jameel
2022 Computer systems science and engineering  
The primary focus of computer vision based scene understanding is to label each and every pixel in an image as the category of the object it belongs to.  ...  Very promising and encouraging results have been achieved that indicates the potential of the proposed method for robust scene understanding in a fast and reliable way.  ...  Funding Statement: The authors received no specific funding for this study. Conflicts of Interest: The authors declare that they have no conflicts of interest to report regarding the present study.  ... 
doi:10.32604/csse.2022.022590 fatcat:nhwya7l2f5czpfxjelcggcdl6i

GraPE: fast and scalable Graph Processing and Embedding [article]

Luca Cappelletti, Tommaso Fontana, Elena Casiraghi, Vida Ravanmehr, Tiffany J.Callahan, Marcin P. Joachimiak, Christopher J. Mungall, Peter N. Robinson, Justin Reese, Giorgio Valentini
2021 arXiv   pre-print
We present GraPE, a software resource for graph processing and random walk based embedding, that can scale with large and high-degree graphs and significantly speed up-computation.  ...  of the art software resources, with a corresponding boost in the performance of machine learning methods for edge and node label prediction and for the unsupervised analysis of graphs.GraPE is designed  ...  walks, graph embedding, node and edge label prediction, and a large range of graph processing algorithms that nicely scale with big graphs, using parallel computation and efficient data structures to  ... 
arXiv:2110.06196v1 fatcat:3dxkuwcutrfalbvblrn7up5sva

Fast and Incremental Loop Closure Detection with Deep Features and Proximity Graphs [article]

Shan An, Haogang Zhu, Dong Wei, Konstantinos A. Tsintotas, Antonios Gasteratos
2022 arXiv   pre-print
an appearance-based loop closure detection pipeline named "FILD++" (Fast and Incremental Loop closure Detection).First, the system is fed by consecutive images and, via passing them twice through a single  ...  Thus, in the proposed article, we propose a single network for global and local feature extraction in contrast to our previous work (FILD), while an exhaustive search for the verification process is adopted  ...  Mark Cummins for his kindly help, as well as Guangfu Che and Fangru Zhou, whose constructive suggestions helped the system evaluation.  ... 
arXiv:2010.11703v2 fatcat:5ptyfrq25vfwbmkxfszh3yhjmq

A generative framework for fast urban labeling using spatial and temporal context

Ingmar Posner, Mark Cummins, Paul Newman
2009 Autonomous Robots  
This efficiency, combined with low order MRFs resulting from our twostage approach, allows us to generate scene labels at speeds suitable for online deployment.  ...  Environmental cues are considered for classification at different scales. The first stage considers local scene properties using a probabilistic bag-of-words classifier.  ...  Pawan Kumar for many insightful conversations.  ... 
doi:10.1007/s10514-009-9110-6 fatcat:gokv44mgv5btviwisxecomnsdy

Fast Keypoint Recognition Using Random Ferns

M. Ozuysal, M. Calonder, V. Lepetit, P. Fua
2010 IEEE Transactions on Pattern Analysis and Machine Intelligence  
While feature point recognition is a key component of modern approaches to object detection, existing approaches require computationally expensive patch preprocessing to handle perspective distortion.  ...  In this paper, we show that formulating the problem in a naive Bayesian classification framework makes such preprocessing unnecessary and produces an algorithm that is simple, efficient, and robust.  ...  His research focuses on fast keypoint matching for object tracking and detection.  ... 
doi:10.1109/tpami.2009.23 pmid:20075471 fatcat:ekardog2yjdirom7amimdlk2zy

PCEDNet : A Lightweight Neural Network for Fast and Interactive Edge Detection in 3D Point Clouds [article]

Chems-Eddine Himeur, Thibault Lejemble, Thomas Pellegrini, Mathias Paulin, Loic Barthe, Nicolas Mellado
2021 arXiv   pre-print
Our architecture is compact, requires small learning sets, is very fast to train and classifies millions of points in seconds.  ...  These parameters, stored in a Scale-Space Matrix (SSM), provide a well suited information from which an adequate neural network can learn the description of edges and use it to efficiently detect them  ...  This is less clear for a processing relying on point patches (e.g. for style or large features recognition).  ... 
arXiv:2011.01630v2 fatcat:halmviikevhc7mewzjvnkqruue

Balancing Neural Trees To Improve Classification Performance

Asha Rani, Christian Micheloni, Gian Luca Foresti
2009 Zenodo  
In this paper, a neural tree (NT) classifier having a simple perceptron at each node is considered. A new concept for making a balanced tree is applied in the learning algorithm of the tree.  ...  Experiments are performed to check the efficiency and encouraging results are obtained in terms of accuracy and computational costs.  ...  ACKNOWLEDGEMENTS This work is partially supported by Ministry of Italian University and Scientific Research (MIUR).  ... 
doi:10.5281/zenodo.1071177 fatcat:wr2xqj4zpfcvvdlhqwzevz6ql4

Learning SURF Cascade for Fast and Accurate Object Detection

Jianguo Li, Yimin Zhang
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
This paper presents a novel learning framework for training boosting cascade based object detector from large scale dataset.  ...  Second, it adopts logistic regression as weak classifier for each local patch instead of decision trees in the VJ framework.  ...  Even with the great increase of computing power today, existing learning frameworks are still not efficient to handle such a large scale training problem.  ... 
doi:10.1109/cvpr.2013.445 dblp:conf/cvpr/Li013 fatcat:siy7plpncjgoxntupbdlkzrg7u
« Previous Showing results 1 — 15 out of 23,249 results