Luke McDowell - Academia.edu (original) (raw)
Papers by Luke McDowell
We use Sarnoff 's next-generation video processor, the PVT-200, to demonstrate real-time algo... more We use Sarnoff 's next-generation video processor, the PVT-200, to demonstrate real-time algorithms for stereo processing, obstacle detection, and terrain estimation from stereo cameras mounted on a moving vehicle. Sarnoff's stereo processing and obstacle detection capabilities are currently being used in several Unmanned Ground Vehi- cle (UGVprograms, including MDARS-E and DEMO 111. Sarnoff 's terrain estimation capabilities are founded on
Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201), 1998
We use Sarnoff's VFE-200 next-generation video processor to demonstrate real-tim... more We use Sarnoff's VFE-200 next-generation video processor to demonstrate real-time algorithms for camera fixation, mosaic construction, and moving object detection and tracking from a moving camera. The algorithms are all derived from our ability to perform real-time image alignment. These capabilities are currently being used in several unmanned aerial and ground surveillance programs
Proceedings of the 2014 IEEE 15th International Conference on Information Reuse and Integration (IEEE IRI 2014), 2014
Proceedings of the 22nd ACM international conference on Conference on information & knowledge management - CIKM '13, 2013
ABSTRACT Many classification tasks involve linked nodes, such as people connected by friendship l... more ABSTRACT Many classification tasks involve linked nodes, such as people connected by friendship links. For such networks, accuracy might be increased by including, for each node, the (a) labels or (b) attributes of neighboring nodes as model features. Recent work has focused on option (a), because early work showed it was more accurate and because option (b) fit poorly with discriminative classifiers. We show, however, that when the network is sparsely labeled, "relational classification" based on neighbor attributes often has higher accuracy than "collective classification" based on neighbor labels. Moreover, we introduce an efficient method that enables discriminative classifiers to be used with neighbor attributes, yielding further accuracy gains. We show that these effects are consistent across a range of datasets, learning choices, and inference algorithms, and that using both neighbor attributes and labels often produces the best accuracy.
ACM SIGPLAN Notices, 2003
Simultaneous multithreading (SMT) represents a fundamental shift in processor capability. SMT&... more Simultaneous multithreading (SMT) represents a fundamental shift in processor capability. SMT's ability to execute multiple threads simultaneously within a single CPU offers tremendous potential performance benefits. However, the structure and behavior of software affects the extent to which this potential can be achieved. Consequently, just like the earlier arrival of multiprocessors, the advent of SMT processors prompts a needed re-evaluation
ABSTRACT Recently, location-based applications and services for mobile users have attracted signi... more ABSTRACT Recently, location-based applications and services for mobile users have attracted significant attention. In this context, one challenging problem is predicting the future location of a mobile user given his or her current location and associated metadata. Solving this problem enables many interesting applications such as location-aware mobile advertisements, traffic warnings, etc. In this paper, we present an approach based on user-specific decision trees learned from each user's history. The classification tree is built ...
2012 IEEE 12th International Conference on Data Mining Workshops, 2012
Abstract Users of today's information networks need to digest large ... more Abstract Users of today's information networks need to digest large amounts of data. Therefore, tools that ease the task of filtering the relevant content are becoming necessary. One way to achieve this is to identify the users who generate content in a certain topic of interest. However, due to the diversity and ambiguity of the shared information, assigning users to topics in an automatic fashion is challenging. In this demo, we present Topick, a system that leverages state of the art techniques and tools to automatically distill high- ...
Lecture Notes in Computer Science, 2006
... Luke K. McDowell1 and Michael Cafarella2 ... Init: SearchSet = {R} + O.subclassesOf(R) Search... more ... Luke K. McDowell1 and Michael Cafarella2 ... Init: SearchSet = {R} + O.subclassesOf(R) SearchSet = {Animal} + {Amphibian, Arthropod, Bird, Fish,...} 1. C = PickAndRemoveClass (SearchSet) C =Bird 2. Phrases = ApplyPatterns(C) Phrases = {birds such as ..., birds including ...
ACM Transactions on Computer Systems, 2003
Page 1. An Evaluation of Speculative Instruction Execution on Simultaneous Multithreaded Processo... more Page 1. An Evaluation of Speculative Instruction Execution on Simultaneous Multithreaded Processors STEVEN SWANSON, LUKE K. McDOWELL, MICHAEL M. SWIFT, SUSAN J. EGGERS and HENRY M. LEVY University of Washington ...
Proceedings of the 13th conference on World Wide Web - WWW '04, 2004
This paper investigates how the vision of the Semantic Web can be carried overto the realm of ema... more This paper investigates how the vision of the Semantic Web can be carried overto the realm of email. We introduce a general notion of semantice mail, in which an email message consists of an RDF query or update coupled with corresponding explanatory text. Semantic email opens the door to a wide range of automated, email-mediated applications with formally guaranteed properties.
Lecture Notes in Computer Science, 2003
Numerous proposals for creating a semantic web have been made in recent years (eg, [3,6,17]), yet... more Numerous proposals for creating a semantic web have been made in recent years (eg, [3,6,17]), yet adoption of the semantic web is far from widespread. Several researchers have recently questioned whether participation in the semantic web is too difficult for “ordinary” ...
Web Semantics: Science, Services and Agents on the World Wide Web, 2008
The Semantic Web's need for machine understandable content has led researchers to attempt to auto... more The Semantic Web's need for machine understandable content has led researchers to attempt to automatically acquire such content from a number of sources, including the web. To date, such research has focused on "document-driven" systems that individually process a small set of documents, annotating each with respect to a given ontology. This article introduces OntoSyphon, an alternative that strives to more fully leverage existing ontological content while scaling to extract comparatively shallow content from millions of documents. OntoSyphon operates in an "ontology-driven" manner: taking any ontology as input, OntoSyphon uses the ontology to specify web searches that identify possible semantic instances, relations, and taxonomic information. Redundancy in the web, together with information from the ontology, is then used to automatically verify these candidate instances and relations, enabling OntoSyphon to operate in a fully automated, unsupervised manner. A prototype of OntoSyphon is fully implemented and we present experimental results that demonstrate substantial instance population in three domains based on independently constructed ontologies. We show that using the whole web as a corpus for verification yields the best results, but that using a much smaller web corpus can also yield strong performance. In addition, we consider the problem of selecting the best class for each candidate instance that is discovered, and the problem of ranking the final results. For both problems we introduce new solutions and demonstrate that, for both the small and large corpora, they consistently improve upon previously known techniques.
We use Sarnoff's next-generation video processor, the to demonstrate real-time algorithms for ste... more We use Sarnoff's next-generation video processor, the to demonstrate real-time algorithms for stereo processing, obstacle detection, and terrain estimation from stereo cameras mounted on a moving vehicle. Sarnoff's stereo processing and obstacle detection capabilities are currently being used in several Unmanned Ground Vehicle (UGV) programs, including MDARS-E and DEMO III. Sarnoff's terrain estimation capabilities are founded on a "model-based directed stereo" approach. We demonstrate ongoing collaborative research between Sarnoff and Universität der Bundeswehr München, where we are studying vision processing for autonomous off-road navigation as part of the AUTONAV program.
ABSTRACT Relational data representations have become an increasingly important topic due to the r... more ABSTRACT Relational data representations have become an increasingly important topic due to the recent proliferation of network datasets (e.g., social, biological, information networks) and a corresponding increase in the application of statistical relational learning (SRL) algorithms to these domains. In this article, we examine and categorize techniques for transforming graph-based relational data to improve SRL algorithms. In particular, appropriate transformations of the nodes, links, and/or features of the data can dramatically affect the capabilities and results of SRL algorithms. We introduce an intuitive taxonomy for data representation transformations in relational domains that incorporates link transformation and node transformation as symmetric representation tasks. More specifically, the transformation tasks for both nodes and links include (i) predicting their existence, (ii) predicting their label or type, (iii) estimating their weight or importance, and (iv) systematically constructing their relevant features. We motivate our taxonomy through detailed examples and use it to survey competing approaches for each of these tasks. We also discuss general conditions for transforming links, nodes, and features. Finally, we highlight challenges that remain to be addressed.
ABSTRACT Relational data representations have become an increasingly important topic due to the r... more ABSTRACT Relational data representations have become an increasingly important topic due to the recent proliferation of network datasets (e.g., social, biological, information networks) and a corresponding increase in the application of statistical relational learning (SRL) algorithms to these domains. In this article, we examine a range of representation issues for graph-based relational data. Since the choice of relational data representation for the nodes, links, and features can dramatically affect the capabilities of SRL algorithms, we survey approaches and opportunities for relational representation transformation designed to improve the performance of these algorithms. This leads us to introduce an intuitive taxonomy for data representation transformations in relational domains that incorporates link transformation and node transformation as symmetric representation tasks. In particular, the transformation tasks for both nodes and links include (i) predicting their existence, (ii) predicting their label or type, (iii) estimating their weight or importance, and (iv) systematically constructing their relevant features. We motivate our taxonomy through detailed examples and use it to survey and compare competing approaches for each of these tasks. We also discuss general conditions for transforming links, nodes, and features. Finally, we highlight challenges that remain to be addressed.
Poster Presentation at the …
International Workshop on the …
Categories and Subject Descriptors y (yha E d 4 { E az { pp H ¦ s ! { d T 7 A) d¥xI2IA E¥ 13V4)d ... more Categories and Subject Descriptors y (yha E d 4 { E az { pp H ¦ s ! { d T 7 A) d¥xI2IA E¥ 13V4)d q¤y 7 E ! sp 7 4 5 ¨ ! 4 4 A bz G q 4 { 5 b 4 z ! ¦ 8 G z ! ( A xvr 7 A) d¥dIYIA 3 ¦¥ 1HVE)d y ¡©y ¢h # $ Q£z { p H ¦ s ! ¨ ¨ zz ! p HE ! { d ¤¤ I2¥sx D9 13 ¦ A 5 YI
University of …
Despite numerous proposals for its creation, the semantic web has yet to achieve widespread adopt... more Despite numerous proposals for its creation, the semantic web has yet to achieve widespread adoption. Recently, some researchers have argued that participation in the semantic web is too difficult for “ordinary” people, limiting its growth and popularity. In response, ...
We use Sarnoff 's next-generation video processor, the PVT-200, to demonstrate real-time algo... more We use Sarnoff 's next-generation video processor, the PVT-200, to demonstrate real-time algorithms for stereo processing, obstacle detection, and terrain estimation from stereo cameras mounted on a moving vehicle. Sarnoff's stereo processing and obstacle detection capabilities are currently being used in several Unmanned Ground Vehi- cle (UGVprograms, including MDARS-E and DEMO 111. Sarnoff 's terrain estimation capabilities are founded on
Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201), 1998
We use Sarnoff's VFE-200 next-generation video processor to demonstrate real-tim... more We use Sarnoff's VFE-200 next-generation video processor to demonstrate real-time algorithms for camera fixation, mosaic construction, and moving object detection and tracking from a moving camera. The algorithms are all derived from our ability to perform real-time image alignment. These capabilities are currently being used in several unmanned aerial and ground surveillance programs
Proceedings of the 2014 IEEE 15th International Conference on Information Reuse and Integration (IEEE IRI 2014), 2014
Proceedings of the 22nd ACM international conference on Conference on information & knowledge management - CIKM '13, 2013
ABSTRACT Many classification tasks involve linked nodes, such as people connected by friendship l... more ABSTRACT Many classification tasks involve linked nodes, such as people connected by friendship links. For such networks, accuracy might be increased by including, for each node, the (a) labels or (b) attributes of neighboring nodes as model features. Recent work has focused on option (a), because early work showed it was more accurate and because option (b) fit poorly with discriminative classifiers. We show, however, that when the network is sparsely labeled, "relational classification" based on neighbor attributes often has higher accuracy than "collective classification" based on neighbor labels. Moreover, we introduce an efficient method that enables discriminative classifiers to be used with neighbor attributes, yielding further accuracy gains. We show that these effects are consistent across a range of datasets, learning choices, and inference algorithms, and that using both neighbor attributes and labels often produces the best accuracy.
ACM SIGPLAN Notices, 2003
Simultaneous multithreading (SMT) represents a fundamental shift in processor capability. SMT&... more Simultaneous multithreading (SMT) represents a fundamental shift in processor capability. SMT's ability to execute multiple threads simultaneously within a single CPU offers tremendous potential performance benefits. However, the structure and behavior of software affects the extent to which this potential can be achieved. Consequently, just like the earlier arrival of multiprocessors, the advent of SMT processors prompts a needed re-evaluation
ABSTRACT Recently, location-based applications and services for mobile users have attracted signi... more ABSTRACT Recently, location-based applications and services for mobile users have attracted significant attention. In this context, one challenging problem is predicting the future location of a mobile user given his or her current location and associated metadata. Solving this problem enables many interesting applications such as location-aware mobile advertisements, traffic warnings, etc. In this paper, we present an approach based on user-specific decision trees learned from each user's history. The classification tree is built ...
2012 IEEE 12th International Conference on Data Mining Workshops, 2012
Abstract Users of today's information networks need to digest large ... more Abstract Users of today's information networks need to digest large amounts of data. Therefore, tools that ease the task of filtering the relevant content are becoming necessary. One way to achieve this is to identify the users who generate content in a certain topic of interest. However, due to the diversity and ambiguity of the shared information, assigning users to topics in an automatic fashion is challenging. In this demo, we present Topick, a system that leverages state of the art techniques and tools to automatically distill high- ...
Lecture Notes in Computer Science, 2006
... Luke K. McDowell1 and Michael Cafarella2 ... Init: SearchSet = {R} + O.subclassesOf(R) Search... more ... Luke K. McDowell1 and Michael Cafarella2 ... Init: SearchSet = {R} + O.subclassesOf(R) SearchSet = {Animal} + {Amphibian, Arthropod, Bird, Fish,...} 1. C = PickAndRemoveClass (SearchSet) C =Bird 2. Phrases = ApplyPatterns(C) Phrases = {birds such as ..., birds including ...
ACM Transactions on Computer Systems, 2003
Page 1. An Evaluation of Speculative Instruction Execution on Simultaneous Multithreaded Processo... more Page 1. An Evaluation of Speculative Instruction Execution on Simultaneous Multithreaded Processors STEVEN SWANSON, LUKE K. McDOWELL, MICHAEL M. SWIFT, SUSAN J. EGGERS and HENRY M. LEVY University of Washington ...
Proceedings of the 13th conference on World Wide Web - WWW '04, 2004
This paper investigates how the vision of the Semantic Web can be carried overto the realm of ema... more This paper investigates how the vision of the Semantic Web can be carried overto the realm of email. We introduce a general notion of semantice mail, in which an email message consists of an RDF query or update coupled with corresponding explanatory text. Semantic email opens the door to a wide range of automated, email-mediated applications with formally guaranteed properties.
Lecture Notes in Computer Science, 2003
Numerous proposals for creating a semantic web have been made in recent years (eg, [3,6,17]), yet... more Numerous proposals for creating a semantic web have been made in recent years (eg, [3,6,17]), yet adoption of the semantic web is far from widespread. Several researchers have recently questioned whether participation in the semantic web is too difficult for “ordinary” ...
Web Semantics: Science, Services and Agents on the World Wide Web, 2008
The Semantic Web's need for machine understandable content has led researchers to attempt to auto... more The Semantic Web's need for machine understandable content has led researchers to attempt to automatically acquire such content from a number of sources, including the web. To date, such research has focused on "document-driven" systems that individually process a small set of documents, annotating each with respect to a given ontology. This article introduces OntoSyphon, an alternative that strives to more fully leverage existing ontological content while scaling to extract comparatively shallow content from millions of documents. OntoSyphon operates in an "ontology-driven" manner: taking any ontology as input, OntoSyphon uses the ontology to specify web searches that identify possible semantic instances, relations, and taxonomic information. Redundancy in the web, together with information from the ontology, is then used to automatically verify these candidate instances and relations, enabling OntoSyphon to operate in a fully automated, unsupervised manner. A prototype of OntoSyphon is fully implemented and we present experimental results that demonstrate substantial instance population in three domains based on independently constructed ontologies. We show that using the whole web as a corpus for verification yields the best results, but that using a much smaller web corpus can also yield strong performance. In addition, we consider the problem of selecting the best class for each candidate instance that is discovered, and the problem of ranking the final results. For both problems we introduce new solutions and demonstrate that, for both the small and large corpora, they consistently improve upon previously known techniques.
We use Sarnoff's next-generation video processor, the to demonstrate real-time algorithms for ste... more We use Sarnoff's next-generation video processor, the to demonstrate real-time algorithms for stereo processing, obstacle detection, and terrain estimation from stereo cameras mounted on a moving vehicle. Sarnoff's stereo processing and obstacle detection capabilities are currently being used in several Unmanned Ground Vehicle (UGV) programs, including MDARS-E and DEMO III. Sarnoff's terrain estimation capabilities are founded on a "model-based directed stereo" approach. We demonstrate ongoing collaborative research between Sarnoff and Universität der Bundeswehr München, where we are studying vision processing for autonomous off-road navigation as part of the AUTONAV program.
ABSTRACT Relational data representations have become an increasingly important topic due to the r... more ABSTRACT Relational data representations have become an increasingly important topic due to the recent proliferation of network datasets (e.g., social, biological, information networks) and a corresponding increase in the application of statistical relational learning (SRL) algorithms to these domains. In this article, we examine and categorize techniques for transforming graph-based relational data to improve SRL algorithms. In particular, appropriate transformations of the nodes, links, and/or features of the data can dramatically affect the capabilities and results of SRL algorithms. We introduce an intuitive taxonomy for data representation transformations in relational domains that incorporates link transformation and node transformation as symmetric representation tasks. More specifically, the transformation tasks for both nodes and links include (i) predicting their existence, (ii) predicting their label or type, (iii) estimating their weight or importance, and (iv) systematically constructing their relevant features. We motivate our taxonomy through detailed examples and use it to survey competing approaches for each of these tasks. We also discuss general conditions for transforming links, nodes, and features. Finally, we highlight challenges that remain to be addressed.
ABSTRACT Relational data representations have become an increasingly important topic due to the r... more ABSTRACT Relational data representations have become an increasingly important topic due to the recent proliferation of network datasets (e.g., social, biological, information networks) and a corresponding increase in the application of statistical relational learning (SRL) algorithms to these domains. In this article, we examine a range of representation issues for graph-based relational data. Since the choice of relational data representation for the nodes, links, and features can dramatically affect the capabilities of SRL algorithms, we survey approaches and opportunities for relational representation transformation designed to improve the performance of these algorithms. This leads us to introduce an intuitive taxonomy for data representation transformations in relational domains that incorporates link transformation and node transformation as symmetric representation tasks. In particular, the transformation tasks for both nodes and links include (i) predicting their existence, (ii) predicting their label or type, (iii) estimating their weight or importance, and (iv) systematically constructing their relevant features. We motivate our taxonomy through detailed examples and use it to survey and compare competing approaches for each of these tasks. We also discuss general conditions for transforming links, nodes, and features. Finally, we highlight challenges that remain to be addressed.
Poster Presentation at the …
International Workshop on the …
Categories and Subject Descriptors y (yha E d 4 { E az { pp H ¦ s ! { d T 7 A) d¥xI2IA E¥ 13V4)d ... more Categories and Subject Descriptors y (yha E d 4 { E az { pp H ¦ s ! { d T 7 A) d¥xI2IA E¥ 13V4)d q¤y 7 E ! sp 7 4 5 ¨ ! 4 4 A bz G q 4 { 5 b 4 z ! ¦ 8 G z ! ( A xvr 7 A) d¥dIYIA 3 ¦¥ 1HVE)d y ¡©y ¢h # $ Q£z { p H ¦ s ! ¨ ¨ zz ! p HE ! { d ¤¤ I2¥sx D9 13 ¦ A 5 YI
University of …
Despite numerous proposals for its creation, the semantic web has yet to achieve widespread adopt... more Despite numerous proposals for its creation, the semantic web has yet to achieve widespread adoption. Recently, some researchers have argued that participation in the semantic web is too difficult for “ordinary” people, limiting its growth and popularity. In response, ...