A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit the original URL.
The file type is application/pdf.
Filters
Attributes and categories for generic instance search from one example
2015
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
This paper aims for generic instance search from one example where the instance can be an arbitrary 3D object like shoes, not just near-planar and one-sided instances like buildings and logos. ...
Firstly, we evaluate state-of-the-art instance search methods on this problem. We observe that what works for buildings loses its generality on shoes. ...
Categories and attributes for generic instance search In this section, we consider searching for an instance from a dataset which contains instances from various categories. ...
doi:10.1109/cvpr.2015.7298613
dblp:conf/cvpr/TaoSC15
fatcat:xxkjwg5obrev5kd7rzzxjy6f3i
Generic Instance Search and Re-identification from One Example via Attributes and Categories
[article]
2016
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 2019; you can also visit the original URL.
The file type is application/pdf.
This paper aims for generic instance search from one example where the instance can be an arbitrary object like shoes, not just near-planar and one-sided instances like buildings and logos. ...
Searching among instances from the same category as the query, the category-specific attributes outperform existing approaches by a large margin on shoes and cars and perform on par with the state-of-the-art ...
Categories and attributes for generic instance search In this section, we consider searching for an instance from a dataset which contains instances from various categories. ...
arXiv:1605.07104v1
fatcat:5nyut6modvbrdasends6xzpy4i
Searching for A Thing
2017
Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval - ICMR '17
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.
With the offline-learned viewpoint-invariant category type and subtype (attributes) classification, the search for the target in the wild is surprisingly successful from one example [2] . ...
To generalize to searching for rigid 3D-objects from one example image the variability in view point variations is so big that one needs to learn about other viewpoints in general. ...
doi:10.1145/3078971.3079006
dblp:conf/mir/SmeuldersT17
fatcat:f7ntcdggjjdndo2nsomnk7mfxi
Playing by the rules
2013
Proceedings of the sixth ACM international conference on Web search and data mining - WSDM '13
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.
The method first generates query attributes using sources such as topics, concepts (entities), and keywords in queries. ...
In this paper, we propose a method to generate underperforming query identification rules instantly using topical and lexical attributes. ...
As a result, we can link a query instance to the categories via identified entities from the query texts, and use those categories as attributes. ...
doi:10.1145/2433396.2433414
dblp:conf/wsdm/KimHWW13
fatcat:tgh327bub5hkhkr5zfluan3vl4
Implementing Valiant's learnability theory using random sets
1992
Machine Learning
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.
This framework is based on the pac-learning formalism introduced by Valiant (1984) and generalized in set-theoretic terms by Blumer, et al., (1989) . ...
Its performance is then tested on the multiplexor class of problems. This class has been analyzed by others as a benchmark for decision trees and genetic classifiers. ...
Acknowledgments The author wishes to thank Oscar Manley of the Department of Energy's Office of Basic Energy Sciences for his continuing financial support of random set research. ...
doi:10.1007/bf00994005
fatcat:mncbay6xovhhza53hg2hgm5cxy
Modeling dwell time to predict click-level satisfaction
2014
Proceedings of the 7th ACM international conference on Web search and data mining - WSDM '14
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 2015; you can also visit the original URL.
The file type is application/pdf.
Clicks on search results are the most widely used behavioral signals for predicting search satisfaction. Even though clicks are correlated with satisfaction, they can also be noisy. ...
In this paper, we study the effect of different page characteristics on the time needed to achieve search satisfaction. ...
To the best of our knowledge, this is the first study to identify and characterize the effect of query-click attributes on click dwell time. ...
doi:10.1145/2556195.2556220
dblp:conf/wsdm/KimHWZ14
fatcat:zvskvygasngmxdglt4vklfmr4q
Learning a Large Scale of Ontology from Japanese Wikipedia
2010
2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology
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.
Experimental case studies show us that the learned Japanese Wikipedia Ontology goes better than already existing general linguistic ontologies, such as EDR and Japanese WordNet, from the points of building ...
Here is discussed how to learn a large scale of ontology from Japanese Wikipedia. ...
-A function that displays a list of instances from classes that were selected. -A function that displays the attributes possessed by a class. • functions for searching external databases. ...
doi:10.1109/wi-iat.2010.177
dblp:conf/webi/TamagawaSTMIY10
fatcat:663ocy7nqrhh5fs7da3h6mkgpa
AN APPROACH TO EXTENDING QUERY SENTENCE FOR SEMANTIC ORIENTED SEARCH ON KNOWLEDGE GRAPH
2021
Journal of Science and Technology - IUH
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.
Therefore, this paper introduces an approach to extending query sentences for semantic oriented search on knowledge graph. ...
It accomplishes this by specifying a set of generic concepts that characterizes the domain as well as their definitions and interrelationships. ...
RELATED WORKS As outline from Bergamaschi et al [3] , they showcased QUEST (QUEry generator for STructured sources), a search engine for relational databases that combines semantic and machine learning ...
doi:10.46242/jst-iuh.v50i08.980
fatcat:qwzvlq7d45cqxhhpbma6yf3ava
Accounting for graded performance within a discrete search framework
1996
Cognitive Science
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.
Then, using data from human experiments, we evaluate SCA's qualitative predictions an accuracy and response time on individual dataset instances. ...
For replicating human behavior, we first show how SCA exhibits some typicality effects in the course of learning responding faster and more accurately to more typical test examples. ...
By searching through the rule space from the most specific rule to the more general ones, the first matched rule typically produces the most common category for examples with the matched attributes. ...
doi:10.1016/s0364-0213(99)80013-5
fatcat:kbyia4sqm5bzrbxm3snzts2oty
Augmented Image Retrieval using Multi-order Object Layout with Attributes
2014
Proceedings of the ACM International Conference on Multimedia - MM '14
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 2015; you can also visit the original URL.
The file type is application/pdf.
Then, based on the def ned descriptor, our method ranks the images in the database according to the matching scores w.r.t. the category, attribute, and spatial relations. ...
Specif cally, we f rstly propose a structured descriptor to jointly represent the categories, attributes, and spatial relations among objects. ...
Suppose there are F instances within an image labeled by R different category labels (R ≤ F ), each instance is assigned a category label ranging from 1 to Q and the attribute label ranging from 1 to M ...
doi:10.1145/2647868.2654972
dblp:conf/mm/CaoWGHT14
fatcat:wbe6d7mfxvcxjghhv5eibycmfu
Relative Attributes for Enhanced Human-Machine Communication
2021
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
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 2022; you can also visit the original URL.
The file type is application/pdf.
For example, the models can capture that animal A is 'furrier' than animal B, or image X is 'brighter' than image B. ...
We show how these relative attribute predictions enable a variety of novel applications, including zero-shot learning from relative comparisons, automatic image description, image search with interactive ...
Acknowledgments This research is supported in part by ONR YIP and NSF IIS-1065390 (K.G. and A.K.). ...
doi:10.1609/aaai.v26i1.8443
fatcat:37xbrewr5zfopmdgpie2mbpeae
Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute Detection
[article]
2017
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.
Existing methods often ignore global context cues capturing the interactions among different object instances, and can only recognize a handful of types by exhaustively training individual detectors for ...
First, a directed semantic action graph is built using language priors to provide a rich and compact representation of semantic correlations between object categories, predicates, and attributes. ...
Figure 6 . 6 Qualitative comparison between VRD [16] and our VRL.
Figure 8 . 8 Examples of relationship and attribute detection results generated by VRL on the Visual Genome dataset. ...
arXiv:1703.03054v1
fatcat:3ez6jor7xvfc3kxjafdvarkd2q
Predicting the Category and Attributes of Visual Search Targets Using Deep Gaze Pooling
2017
2017 IEEE International Conference on Computer Vision Workshops (ICCVW)
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.
In contrast to previous work that focused on predicting specific instances of search targets, we propose the first approach to predict a target's category and attributes. ...
Predicting the target of visual search from human gaze data is a challenging problem. ...
We also thank Mykhaylo Andriluka for helpful comments on the paper. ...
doi:10.1109/iccvw.2017.322
dblp:conf/iccvw/SattarBF17
fatcat:7opkss22bnhxnmwp7cjamwinb4
NEIL: Extracting Visual Knowledge from Web Data
2013
2013 IEEE International Conference on Computer Vision
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 2015; you can also visit the original URL.
The file type is application/pdf.
As of 10 th October 2013, NEIL has been continuously running for 2.5 months on 200 core cluster (more than 350K CPU hours) and has an ontology of 1152 object categories, 1034 scene categories and 87 attributes ...
., "Corolla is a kind of/looks similar to Car","Wheel is a part of Car") and labels instances of the given visual categories. ...
Acknowledgements: This research was supported by ONR MURI N000141010934 and a gift from Google. The authors would like to thank Tom Mitchell and David Fouhey for insightful discussions. ...
doi:10.1109/iccv.2013.178
dblp:conf/iccv/ChenSG13
fatcat:qks2a3nkanf5vabuqxehikj7ee
Knowledge acquisition via incremental conceptual clustering
1987
Machine Learning
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 2013; you can also visit the original URL.
The file type is application/pdf.
Additionally, COBWEB is incremental and computationally economical, and thus can be flexibly applied in a variety of domains. ...
Conceptual clustering is an important way of summarizing and explaining data. ...
Acknowledgements I thank members of the UCI machine learning group for their helpful comments on earlier drafts of the paper, including Pat Langley, Jeff Schlimmer, Dennis Kibler, Rogers Hall, and Rick ...
doi:10.1007/bf00114265
fatcat:kodwzxdnhbgtjje3oun6h7bol4
« Previous
Showing results 1 — 15 out of 373,621 results