A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
Functional Task Tree Generation from a Knowledge Graph to Solve Unseen Problems
[article]
2021
arXiv
pre-print
Preserved Fulltext
To demonstrate the flexibility of our method, we randomly selected recipes from the Recipe1M+ dataset and generated their task trees. ...
Existing knowledge in the form of a knowledge graph is used as a base of reference to create task trees that are modified with new object or state combinations. ...
Long Activity Video
Understanding Using Functional Object-Oriented Network. ...
arXiv:2112.02433v1
fatcat:k3gtd2fonffzno37f7wykjt2cm
Long Activity Video Understanding using Functional Object-Oriented Network
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Experiments show that using functional object oriented network improves video understanding significantly. ...
The knowledge representation used in the pipeline is called the functional object-oriented network which is a graph-based network useful for encoding knowledge about manipulation tasks. ...
FUNCTIONAL OBJECT-ORIENTED NETWORK The functional object-oriented network, FOON, is a knowledge representation for encoding knowledge about manipulation tasks and, in extension, object affordances. ...
arXiv:1807.00983v1
fatcat:xbcdvvvadrgvhp6cmbl3tcqjem
Classifying cooking object's state using a tuned VGG convolutional neural network
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this paper, we have analyzed seven different cooking object states by tuning a convolutional neural network (CNN). ...
The work presented in this paper focuses on classification between various object states rather than task recognition or recipe prediction. ...
Paulius [19] presented FOON (functional object-oriented network), a novel knowledge structure representation to analyze the connectivity object's motion in manipulation tasks. ...
arXiv:1805.09391v2
fatcat:ztd2g6s43zgrtcgara7t34ht5y
Images and Recipes: Retrieval in the Cooking Context
2018
2018 IEEE 34th International Conference on Data Engineering Workshops (ICDEW)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2018 pre-print arXiv:1805.00900v1 fatcat:hwwmytfj5fcnrermxyuewawihe
In this paper, we tackle the picture-recipe alignment problem, having as target application the large-scale retrieval task (finding a recipe given a picture, and vice versa). ...
Our approach is validated on the Recipe1M dataset, composed of one million image-recipe pairs and additional class information, for which we achieve state-of-the-art results. ...
Taking into account the retrieval objective of our model, we apply the following evaluation methodology: given a query (whether image or recipe), we rank a collection of 1000 items from the other modality ...
doi:10.1109/icdew.2018.00035
dblp:conf/icde/CarvalhoCPSC18
fatcat:43smvsvqzvdj7dwd7susx7z6wm
Investigation of Practical Aspects of Single Channel Speech Separation for ASR
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
and continuous evaluation, respectively ...
Specifically, we investigate a two-stage training scheme that firstly applies a feature level optimization criterion for pretraining, followed by an ASR-oriented optimization criterion using an end-to-end ...
Table 3 : 3 WER (%) for utterance-wise evaluation with Cfmr small trained by the TS learning and ASR-oriented objective function. ...
arXiv:2107.01922v1
fatcat:4265lsndn5hrphry5dnyx4od6i
A Lightweight Framework of Home Automation Systems Based on the IFTTT Model
2015
Journal of Software
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Our framework differs from existing frameworks according to the integration of a simplified core script and a collection of trigger/action scripts. ...
There are two main functions for end users: recipe creation and recipe usage. ...
"IF-This-Then-That" activities is expressed in the form of a JSON configuration file which is generated from the recipe configuration page. 3) Required trigger/action scripts and software applications ...
doi:10.17706/jsw.10.12.1343-1350
fatcat:fa7w45o33jd3jh7srrwqpmquyq
Artificial Immune System Driven Evolution in Swarm Chemistry
2014
2014 IEEE Eighth International Conference on Self-Adaptive and Self-Organizing Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Starting from a restricted set of chemical recipes, we show that the system evolves to new states, using an autonomous method of detecting new shapes and behaviours free from any human interaction. ...
We present a novel mechanism for providing evolutionary features in swarm chemistry that takes inspiration from artificial immune system literature, more specifically regarding idiotypic networks. ...
how these 3D objects mutated over time. ...
doi:10.1109/saso.2014.16
dblp:conf/saso/CapodieciHC14
fatcat:vzpamjujpjb2pmtelswf6qy6gq
Lowering traffic without sacrificing performance in Networked Control Systems
2011
ETFA2011
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In Networked Control Systems (NCS), the amount of control data exchanged between sensors, controllers and actuators nodes highly depends on the control performance specifications given to each networked ...
The periodic execution of each loop helps meeting the control specifications while imposing a static network traffic. ...
It plots τ as a function of the state orientation. As it can be seen, the different τ values range from 0.8s to 1.65s approximately. ...
doi:10.1109/etfa.2011.6059023
dblp:conf/etfa/MartiVYM11
fatcat:ssj7ruorujgjvmorvbtgrocdmi
Training AI-Based Feature Extraction Algorithms, for Micro CT Images, Using Synthesized Data
2021
Journal of nondestructive evaluation
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
to construct a 3D object with internal features, and finally obtaining the X-ray CT image of the resulting 3D object. ...
We will do so by fabricating miniature features, with known geometry, position and orientation on thin silicon wafer layers using a femtosecond laser machining system, followed by stacking these layers ...
We showed that, using a femtosecond laser setup, miniature features could be implemented onto layers of a layered object to mimic the internal features of a generic object. ...
doi:10.1007/s10921-021-00758-w
fatcat:thp3ekw35rc3fpipzzmzhmei7a
AI Meets Physical World -- Exploring Robot Cooking
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
After "watching" over 200 instructional videos, a functional object-oriented network (FOON) is constructed to represent the observed manipulation skills. ...
Using the network, robots can take a high-level task command such as "I want BBQ Ribs for dinner," decipher the task goal, seek the correct objects to operate on, and then generate and execute a sequence ...
From the video, we construct a functional object-oriented network (FOON) to represent manipulation knowledge ( Figure 1 ) [18, 20, 25] . ...
arXiv:1804.07974v1
fatcat:m37e6wxzq5gv7m26aunyb4tuxq
Easyml: Easily Build And Evaluate Machine Learning Models
[article]
2017
bioRxiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Each recipe is robust, implements best practices specific to each algorithm, and generates a report with details about the model, its performance, as well as journal-quality visualizations. ...
The package's functional, modular, and extensible framework also allows researchers and more advanced users to easily implement new recipes for other algorithms. ...
Both languages are high-level, interpreted, employ functional and object-oriented paradigms, and have a wide ecosystem of mature machine learning libraries. ...
doi:10.1101/137240
fatcat:lnwjjzapcrc7fgcifl54gvwqvy
MCEN: Bridging Cross-Modal Gap between Cooking Recipes and Dish Images with Latent Variable Model
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, we focus on the task of cross-modal retrieval between food images and cooking recipes. ...
One of the most popular research topics in this domain is Food Retrieval, due to its profound influence on health-oriented applications. ...
speech [35] , recipe texts generation from flow graph [44] , workflow generation from recipe texts [58] , cooking action tracking [4] , recipe representation [36] , checklist recipe generation [ ...
arXiv:2004.01095v1
fatcat:bgxe4ogkobeqth5uldyettrwiq
An IoT based reference architecture for smart water management processes
2015
Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
themselves, building networks of interconnected objects, or with end-users or other entities
in the network. ...
Also, they publish subsystem capabilities, as a list of functions
supported by them, considering the capabilities of integrating objects. ...
doi:10.22667/jowua.2015.03.31.004
dblp:journals/jowua/RoblesAANCIL15
fatcat:ey6xa7ghbjb4nbwofw2j22go6q
Strengthening the Competitiveness and Sustainability of a Semiconductor Manufacturer with Cloud Manufacturing
2014
Sustainability
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Cloud manufacturing (CMfg) is a new-generation service-oriented networked manufacturing model that provides distributed users centralized managed manufacturing resources, ability, and services. ...
s view, CMfg is a new-generation service-oriented networked manufacturing model that can provide users distributed in different places with manufacturing resources and manufacturing ability services through ...
In addition, some of these systems operate on the basis of sequential operations, while others are object-oriented. ...
doi:10.3390/su6010251
fatcat:py53gensjvcadafxs2sci7u55e
cellPACK: a virtual mesoscope to model and visualize structural systems biology
2014
Nature Methods
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
computational models of the biological mesoscale, an intermediate scale (10 −7 -10 −8 m) between molecular and cellular biology. cellPACK's modular architecture unites existing and novel packing algorithms to generate ...
, visualize and analyze comprehensive 3D models of complex biological environments that integrate data from multiple experimental systems biology and structural biology sources. cellPACK is currently available ...
Size-dependent available volume graphs quantify the distribution of negative spaces to reveal pore networks accessible to objects of different sizes. ...
doi:10.1038/nmeth.3204
pmid:25437435
pmcid:PMC4281296
fatcat:nkerjapg25ef7kn3qzvlfpq6lm
« Previous
Showing results 1 — 15 out of 21,140 results