Filters








251,989 Hits in 5.7 sec

A Dual-hierarchy Semantic Graph for Robust Object Recognition [article]

Isaac Weiss
2020 arXiv   pre-print
We present a system for object recognition based on a semantic graph representation, which the system can learn from image examples.  ...  Our system performs both the learning and recognition by an algorithm that traverses both hierarchies at the same time, combining the advantages of top-down and bottom-up strategies.  ...  Conclusion We have presented an object recognition system based on the structure and geometry of objects, using a machinelearnable model graph.  ... 
arXiv:1909.06867v3 fatcat:yhrx2erjwjdz5n5v5qpymgkray

Robust Abandoned Object Detection Using Dual Foregrounds

Fatih Porikli, Yuri Ivanov, Tetsuji Haga
2007 EURASIP Journal on Advances in Signal Processing  
Recommended by Enis Ahmet Ç etin As an alternative to the tracking-based approaches that heavily depend on accurate detection of moving objects, which often fail for crowded scenarios, we present a pixelwise  ...  method that employs dual foregrounds to extract temporally static image regions.  ...  ACKNOWLEDGMENT The authors thank their colleagues Jay Thornton and Keisuke Kojima for their constructive comments.  ... 
doi:10.1155/2008/197875 fatcat:blzdfdymqfd4ld6gybfredsvxa

Dual Path Structural Contrastive Embeddings for Learning Novel Objects [article]

Bingbin Li, Elvis Han Cui, Yanan Li, Donghui Wang, Weng Kee Wong
2022 arXiv   pre-print
in either an inductive or transductive inference setting.  ...  To maintain both the generalization ability across base and novel classes and discrimination ability within each class, we propose a dual path feature learning scheme that effectively combines structural  ...  Delta-encoder: an effective sample synthesis method for few- SACL regards all other images in a batch as positives of an shot object recognition. 2018.  ... 
arXiv:2112.12359v3 fatcat:x3utnehujrbwrirkap7qvu3v4i

Lifelong 3D Object Recognition and Grasp Synthesis Using Dual Memory Recurrent Self-Organization Networks [article]

Krishnakumar Santhakumar, Hamidreza Kasaei
2022 arXiv   pre-print
In this paper, we proposed a hybrid model architecture consists of a dynamically growing dual-memory recurrent neural network (GDM) and an autoencoder to tackle object recognition and grasping simultaneously  ...  In autonomous systems, the agents also need to mitigate similar behavior to continually learn the new object categories and adapt to new environments.  ...  An extended version of the GWR model, called Gamma-GWR [16] , embeds the gamma memory [21] during the neuron growth for learning the short-term temporal relation representations of the input data distribution  ... 
arXiv:2109.11544v2 fatcat:44zgnmobvbh7rlhrqumtgexqr4

Achieving diverse and monoallelic olfactory receptor selection through dual-objective optimization design

Xiao-Jun Tian, Hang Zhang, Jens Sannerud, Jianhua Xing
2016 Proceedings of the National Academy of Sciences of the United States of America  
Multiple-objective optimization is common in biological systems.  ...  designed, and particularly underscores cooperativity and synergy as a general design principle for multi-objective optimization in biology.  ...  J.S. was supported by NSF/Department of Defense DBI-1263020, which funds the TECBio Research Experiences for Undergraduates (REU) program.  ... 
doi:10.1073/pnas.1601722113 pmid:27162367 pmcid:PMC4889386 fatcat:gjqwnmavnzf3nb6sqvaqtlkg5y

Scale Estimation with Dual Quadrics for Monocular Object SLAM [article]

Shuangfu Song, Junqiao Zhao, Tiantian Feng, Chen Ye, Lu Xiong
2022 arXiv   pre-print
In this paper, we present a novel scale estimation approach based on an object-level SLAM system.  ...  We adopt the dual quadric to represent objects for its ability to fit objects compactly and accurately.  ...  SLAM++ [19] is considered as the first objectlevel SLAM system which used an RGB-D camera to detect objects by matching prior CAD models.  ... 
arXiv:2202.04816v1 fatcat:zzjmfwnvznc3hdj54atjxl5u7a

UML Design for Performance Evaluation of Object Oriented Programs on Dual Core Processors

Vipin Saxena, Manish Shrivastava
2009 Journal of clean energy technologies  
Saxena et al. [5] proposed the UML model for the Multiplex system for the processes which are executing in distributed environment.  ...  Before evaluating the performance of these processors, an efficient UML model is designed for the program execution.  ... 
doi:10.7763/ijcte.2009.v1.64 fatcat:2fwsyn2oc5e2pgz5zt3jsmii2a

Object Position Estimation based on Dual Sight Perspective Configuration

Dion Setiawan, Maulana Ifdhil Hanafi, Indra Riyanto, Akhmad Musafa
2021 Jurnal Infotel  
This method is based on the Indoor Positioning System (IPS) idea and object position estimation with the multi-camera system (i.e., stereo vision).  ...  Therefore, the capability to process and display data-related positions of objects around the robots is necessary. This paper provides a method to predict an object's position.  ...  The alpha distance value is obtained in an image form for the Dual-Sight Perspective design, so the alpha value is in pixel value.  ... 
doi:10.20895/infotel.v13i2.546 fatcat:o4ok7z2hyfggnbnmj7gs7zkepu

Dual-Objective Energy Management Strategy for HEV

Nan-Chyuan Tsai
2017 International Journal of Automation and Smart Technology  
The proposed bi-object equivalent consumption minimization strategy (BOECMS) possesses three key features: being realtime, causal and capable of fulfilling two objects, namely, (i) minimizing fuel consumption  ...  According to computer simulation results, fuel economy improved by 40.39 % over pure ICE vehicles for the "MANHATTAN" drive cycle.  ...  A backward-facing model features a runningbackward time frame, making it suitable for the optimization approach.  ... 
doi:10.5875/ausmt.v7i3.1422 fatcat:dbnpzdjcwnepbjrvuoyhouaqqe

A Dual-Objective Substation Energy Consumption Optimization Problem in Subway Systems

Hongjie Liu, Tao Tang, Jidong Lv, Ming Chai
2019 Energies  
Afterwards, we design an ϵ -constraint method to transform the dual-objective optimization problem into several single-objective optimization problems, and accordingly design an improved artificial bee  ...  We first propose a dual-objective optimization problem to simultaneously minimize substation energy consumption and the total cost of WESS.  ...  [16] propose a timetable optimization model for an underground rail system to maximize regenerative energy utilization. Fournier et al.  ... 
doi:10.3390/en12101876 fatcat:eajlr4py6jclvotl7yx2ykjeya

Markov dynamics on the dual object to the infinite-dimensional unitary group [article]

Grigori Olshanski
2013 arXiv   pre-print
These are notes for a mini-course of 3 lectures given at the St. Petersburg School in Probability and Statistical Physics (June 2012).  ...  My aim was to explain, on the example of a particular model, how ideas from the representation theory of big groups can be applied in probabilistic problems.  ...  Thus, we may take Ω N as the set of parameters for the dual object to U(N).  ... 
arXiv:1310.6155v1 fatcat:d7pl2qakxvdazhux2ehlyj3yda

The development of a green supply chain dual-objective facility by considering different levels of uncertainty

Sasan Torabzadeh Khorasani, Maryam Almasifard
2017 Journal of Industrial Engineering International  
This paper presents a dual-objective facility programming model for a green supply chain network.  ...  An industrial case study is also analyzed to reveal the feasibility of the proposed model and its application.  ...  This study develops a fuzzy dual-objective facility programming model of a green supply chain system. Facility programming is employed to model uncertainty of parameters in the network.  ... 
doi:10.1007/s40092-017-0245-3 fatcat:apbo5dikxzhrhgngnzagiv3dim

Dual Graph Embedding for Object-Tag LinkPrediction on the Knowledge Graph [article]

Chenyang Li and Xu Chen and Ya Zhang and Siheng Chen and Dan Lv and Yanfeng Wang
2020 arXiv   pre-print
Here the dual graphs contain an object graph and a tag graph that explicitly depict the high-order object-object and tag-tag proximities in the KG.  ...  This paper concentrates on an attractive application which aims to predict the object-tag links in the KG for better tag recommendation and object explanation.  ...  The dual graphs here indicate an object graph and a tag graph containing the high-order object-object and tag-tag proximities in the KG respectively.  ... 
arXiv:2007.08304v1 fatcat:3ezn2wvddjgohm4kpdttdetcf4

A Single-Layer Dual-Mesh Boundary Element Method for Multiscale Electromagnetic Modeling of Penetrable Objects in Layered Media [article]

Shashwat Sharma, Piero Triverio
2021 arXiv   pre-print
However, existing BEM formulations either lead to a poorly conditioned system matrix for multiscale problems, or are computationally expensive for objects embedded in layered substrates.  ...  for multiscale EM modeling.  ...  For penetrable objects, the BEM requires solving an internal problem to model fields within objects, and an external problem to model the coupling between them.  ... 
arXiv:2106.06184v1 fatcat:l7cbmv7e7benbkkf6pvuzblsba

Primal-Dual Frank-Wolfe for Constrained Stochastic Programs with Convex and Non-convex Objectives [article]

Xiaohan Wei, Michael J. Neely
2018 arXiv   pre-print
We establish convergence time guarantees for the case of both convex and non-convex objective functions.  ...  We study constrained stochastic programs where the decision vector at each time slot cannot be chosen freely but is tied to the realization of an underlying random state vector.  ...  Furthermore, this result also implies a precise convergence time guarantee for the primal dual gradient algorithm (6) in earlier works. • When the objective is non-convex, we show our proposed algorithm  ... 
arXiv:1806.00709v1 fatcat:ezbhgave4jcefm5fs4rvswujxe
« Previous Showing results 1 — 15 out of 251,989 results