Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Physical Sciences and Mathematics (4216)
- Computer Sciences (4213)
- Databases and Information Systems (1558)
- Software Engineering (1254)
- Artificial Intelligence and Robotics (747)
-
- Information Security (730)
- Graphics and Human Computer Interfaces (490)
- Numerical Analysis and Scientific Computing (454)
- Engineering (345)
- Programming Languages and Compilers (269)
- Computer Engineering (232)
- Social and Behavioral Sciences (214)
- Theory and Algorithms (212)
- Business (202)
- OS and Networks (148)
- Communication (103)
- Operations Research, Systems Engineering and Industrial Engineering (101)
- Social Media (83)
- Data Storage Systems (81)
- Medicine and Health Sciences (79)
- Education (66)
- Public Affairs, Public Policy and Public Administration (55)
- Computer and Systems Architecture (52)
- Health Information Technology (51)
- Transportation (51)
- Management Information Systems (49)
- Digital Communications and Networking (47)
- E-Commerce (44)
- Finance and Financial Management (40)
- Higher Education (30)
- Keyword
-
- Deep learning (71)
- Machine learning (59)
- Privacy (41)
- Empirical study (40)
- Deep Learning (35)
-
- Training (34)
- Security (33)
- Task analysis (32)
- Cloud computing (31)
- Data mining (31)
- Artificial intelligence (29)
- Reinforcement learning (29)
- Social media (29)
- Software engineering (29)
- Neural networks (28)
- Android (27)
- Blockchain (27)
- Feature extraction (27)
- Large Language Models (26)
- Model Check (26)
- Access control (25)
- Natural language processing (25)
- Authentication (24)
- Large language models (24)
- Privacy-preserving (24)
- Servers (24)
- Anomaly detection (23)
- Information retrieval (23)
- Visualization (23)
- Classification (22)
- Publication Year
Articles 3721 - 3750 of 4266
Full-Text Articles in Entire DC Network
When You Have To Dump It, M. Thulasidas
When You Have To Dump It, M. Thulasidas
Research Collection School Of Computing and Information Systems
It makes sense to cut further losses and such containment efforts are routine events in most establishments.
Columbia University/Vireo-Cityu/Irit Trecvid2008 High-Level Feature Extraction And Interactive Video Search, Shih-Fu Chang, Junfeng He, Yu-Gang Jiang, Elie El Khoury, Chong-Wah Ngo, Akira Yanagawa, Eric Zavesky
Columbia University/Vireo-Cityu/Irit Trecvid2008 High-Level Feature Extraction And Interactive Video Search, Shih-Fu Chang, Junfeng He, Yu-Gang Jiang, Elie El Khoury, Chong-Wah Ngo, Akira Yanagawa, Eric Zavesky
Research Collection School Of Computing and Information Systems
In this report, we present overview and comparative analysis of our HLF detection system, which achieves the top performance among all type-A submissions in 2008. We also describe preliminary evaluation of our video search system, CuZero, in the interactive search task.
Private Query On Encrypted Data In Multi-User Setting, Feng Bao, Robert H. Deng, Xuhua Ding, Yanjiang Yang
Private Query On Encrypted Data In Multi-User Setting, Feng Bao, Robert H. Deng, Xuhua Ding, Yanjiang Yang
Research Collection School Of Computing and Information Systems
Searchable encryption schemes allow users to perform keyword based searches on an encrypted database. Almost all existing such schemes only consider the scenario where a single user acts as both the data owner and the querier. However, most databases in practice do not just serve one user; instead, they support search and write operations by multiple users. In this paper, we systematically study searchable encryption in a practical multi-user setting. Our results include a set of security notions for multi-user searchable encryption as well as a construction which is provably secure under the newly introduced security notions.
Self-Organizing Neural Architectures And Cooperative Learning In A Multiagent Environment, Dan Xiao, Ah-Hwee Tan
Self-Organizing Neural Architectures And Cooperative Learning In A Multiagent Environment, Dan Xiao, Ah-Hwee Tan
Research Collection School Of Computing and Information Systems
Temporal-Difference–Fusion Architecture for Learning, Cognition, and Navigation (TD-FALCON) is a generalization of adaptive resonance theory (a class of self-organizing neural networks) that incorporates TD methods for real-time reinforcement learning. In this paper, we investigate how a team of TD-FALCON networks may cooperate to learn and function in a dynamic multiagent environment based on minefield navigation and a predator/prey pursuit tasks. Experiments on the navigation task demonstrate that TD-FALCON agent teams are able to adapt and function well in a multiagent environment without an explicit mechanism of collaboration. In comparison, traditional Q-learning agents using gradient-descent-based feedforward neural networks, trained with the …
Multi-Order Neurons For Evolutionary Higher Order Clustering And Growth, Kiruthika Ramanathan, Sheng Uei Guan
Multi-Order Neurons For Evolutionary Higher Order Clustering And Growth, Kiruthika Ramanathan, Sheng Uei Guan
Research Collection School Of Computing and Information Systems
This letter proposes to use multiorder neurons for clustering irregularly shaped data arrangements. Multiorder neurons are an evolutionary extension of the use of higher-order neurons in clustering. Higher-order neurons parametrically model complex neuron shapes by replacing the classic synaptic weight by higher-order tensors. The multiorder neuron goes one step further and eliminates two problems associated with higher-order neurons. First, it uses evolutionary algorithms to select the best neuron order for a given problem. Second, it obtains more information about the underlying data distribution by identifying the correct order for a given cluster of patterns. Empirically we observed that when the …
Understanding Highly Competent Information System Users, Brenda Eschenbrenner, Fiona Fui-Hoon Nah
Understanding Highly Competent Information System Users, Brenda Eschenbrenner, Fiona Fui-Hoon Nah
Research Collection School Of Computing and Information Systems
Individuals differ in their abilities to use information systems (IS) effectively, with some achieving exceptional performance in IS use. Using the Repertory Grid Technique, this research identifies attributes of highly competent IS users that distinguish them from less competent users. Using the Grounded Theory approach, we identified categories and sub-categories of these attributes and used them to develop a conceptual framework to explain IS User Competency. The findings indicate that highly competent users differ from less competent users in their Personality Traits and Disposition Factors, General Cognitive Abilities, Social Skills and Tendencies, Experiential Learning Factors, Domain Knowledge of and Skills …
Tuning Tabu Search Strategies Via Visual Diagnosis, Steven Halim, Hoong Chuin Lau
Tuning Tabu Search Strategies Via Visual Diagnosis, Steven Halim, Hoong Chuin Lau
Research Collection School Of Computing and Information Systems
While designing working metaheuristics can be straightforward, tuning them to solve the underlying combinatorial optimization problem well can be tricky. Several tuning methods have been proposed but they do not address the new aspect of our proposed classification of the metaheuristic tuning problem: tuning search strategies. We propose a tuning methodology based on Visual Diagnosis and a generic tool called Visualizer for Metaheuristics Development Framework(V-MDF) to address specifically the problem of tuning search (particularly Tabu Search) strategies. Under V-MDF, we propose the use of a Distance Radar visualizer where the human and computer can collaborate to diagnose the occurrence of …
On Improving Wikipedia Search Using Article Quality, Meiqun Hu, Ee Peng Lim, Aixin Sun, Hady Wirawan Lauw, Ba-Quy Vuong
On Improving Wikipedia Search Using Article Quality, Meiqun Hu, Ee Peng Lim, Aixin Sun, Hady Wirawan Lauw, Ba-Quy Vuong
Research Collection School Of Computing and Information Systems
Wikipedia is presently the largest free-and-open online encyclopedia collaboratively edited and maintained by volunteers. While Wikipedia offers full-text search to its users, the accuracy of its relevance-based search can be compromised by poor quality articles edited by non-experts and inexperienced contributors. In this paper, we propose a framework that re-ranks Wikipedia search results considering article quality. We develop two quality measurement models, namely Basic and PeerReview, to derive article quality based on co-authoring data gathered from articles' edit history. Compared with Wikipedia's full-text search engine, Google and Wikiseek, our experimental results showed that (i) quality-only ranking produced by PeerReview gives …
Machine-Assisted Proof Support For Validation Beyond Simulink, Chunqing Chen, Jin Song Dong, Jun Sun
Machine-Assisted Proof Support For Validation Beyond Simulink, Chunqing Chen, Jin Song Dong, Jun Sun
Research Collection School Of Computing and Information Systems
Simulink is popular in industry for modeling and simulating embedded systems. It is deficient to handle requirements of high-level assurance and timing analysis. Previously, we showed the idea of applying Timed Interval Calculus (TIC) to complement Simulink. In this paper, we develop machine-assisted proof support for Simulink models represented in TIC. The work is based on a generic theorem prover, Prototype Verification System (PVS). The TIC specifications of both Simulink models and requirements are transformed to PVS specifications automatically. Verification can be carried out at interval level with a high level of automation. Analysis of continuous and discrete behaviors is …
Modeling Semantics In Composite Web Service Requests By Utility Elicitation, Qianhui Althea Liang, Jen Yao Chung, Steven M. Miller
Modeling Semantics In Composite Web Service Requests By Utility Elicitation, Qianhui Althea Liang, Jen Yao Chung, Steven M. Miller
Research Collection School Of Computing and Information Systems
When meeting the challenges in automatic and semi-automatic Web service composition, capturing the user’s service demand and preferences is as important as knowing what the services can do. This paper discusses the idea of semantic service requests for composite services, and presents a multi-attribute utility theory (MAUT) based model of composite service requests. Service requests are modeled as user preferences and constraints. Two preference structures, additive independence and generalized additive independence, are utilized in calculating the expected utilities of service composition outcomes. The model is also based on an iterative and incremental scheme meant to better capture requirements in accordance …
Context-Aware Statistical Debugging: From Bug Predictors To Faulty Control Flow Paths, Lingxiao Jiang, Zhendong Su
Context-Aware Statistical Debugging: From Bug Predictors To Faulty Control Flow Paths, Lingxiao Jiang, Zhendong Su
Research Collection School Of Computing and Information Systems
Effective bug localization is important for realizing automated debugging. One attractive approach is to apply statistical techniques on a collection of evaluation profiles of program properties to help localize bugs. Previous research has proposed various specialized techniques to isolate certain program predicates as bug predictors. However, because many bugs may not be directly associated with these predicates, these techniques are often ineffective in localizing bugs. Relevant control flow paths that may contain bug locations are more informative than stand-alone predicates for discovering and understanding bugs. In this paper, we propose an approach to automatically generate such faulty control flow paths …
Mining Modal Scenarios-Based Specifications From Execution Trace Of Reactive Systems, David Lo, Shahar Maoz, Siau-Cheng Khoo
Mining Modal Scenarios-Based Specifications From Execution Trace Of Reactive Systems, David Lo, Shahar Maoz, Siau-Cheng Khoo
Research Collection School Of Computing and Information Systems
Specification mining is a dynamic analysis process aimed at automatically inferring suggested specifications of a program from its execution traces. We describe a novel method, framework, and tool, for mining inter-object scenario-based specifications in the form of a UML2-compliant variant of Damm and Harels Live Sequence Charts (LSC). LSC extends the classical partial order semantics of sequence diagrams with temporal liveness and symbolic class level lifelines, in order to generate compact and expressive specifications. The output of our algorithm is a sound and complete set of statistically significant LSCs (i.e., satisfying given thresholds of support and confidence), mined from an …
Model Checking In The Absence Of Code, Model And Properties, David Lo, Siau-Cheng Khoo
Model Checking In The Absence Of Code, Model And Properties, David Lo, Siau-Cheng Khoo
Research Collection School Of Computing and Information Systems
Model checking is a major approach in ensuring software correctness. It verifies a model converted from code against some formal properties. However, difficulties and programmers ’ reluctance to formalize formal properties have been some hurdles to its widespread industrial adoption. Also, with the advent of commercial off-the-shelf (COTS) components provided by third party vendors, model checking is further challenged as often only a binary version of the code is provided by vendors. Interestingly, latest instrumentation tools like PIN and Valgrind have enable execution traces to be collected dynamically from a running program. In this preliminary study, we investigate what can …
Light-Weight Encryption Schemes For Multimedia Data, Feng Bao, Robert H. Deng
Light-Weight Encryption Schemes For Multimedia Data, Feng Bao, Robert H. Deng
Research Collection School Of Computing and Information Systems
Due to the pervasiveness of high-speed networks and multimedia communications and storage, the demand for highspeed cryptosystems is ever increasing. It is widely believed that there is a tradeoff between speed and security in cryptosystem design. No existing encryption algorithms are both fast enough for high-speed operation and sufficiently secure to withstand powerful cryptanalysis. In this paper, we propose and analyze a generic construction of high-speed encryption schemes. Our solution is based on the fact that there exist secure but relatively slow block ciphers, e. g. AES, and super-fast but relatively weaker stream ciphers. We then combine a secure block …
Mining Modal Scenarios From Execution Traces, David Lo, Shahar Maoz, Siau-Cheng Khoo
Mining Modal Scenarios From Execution Traces, David Lo, Shahar Maoz, Siau-Cheng Khoo
Research Collection School Of Computing and Information Systems
Specification mining is a dynamic analysis process aimed at automatically inferring suggested specifications of a program from its execution traces. We describe a method, a framework, and a tool, for mining inter-object scenario-based specifications in the form of a UML2-compliant variant of Damm and Harel's Live Sequence Charts (LSC), which extends the classical partial order semantics of sequence diagrams with temporal liveness and symbolic class level lifelines, in order to generate compact and expressive specifications. Moreover, we use previous research work and tools developed for LSC to visualize, analyze, manipulate, test, and thus evaluate the scenario-based specifications we mine. Our …
Option-Based Risk Management: A Field Study Of Sequential Information Technology Investment Decisions, Michel Benaroch, Mark Jeffery, Robert John Kauffman, Sandeep Shah
Option-Based Risk Management: A Field Study Of Sequential Information Technology Investment Decisions, Michel Benaroch, Mark Jeffery, Robert John Kauffman, Sandeep Shah
Research Collection School Of Computing and Information Systems
This field study research evaluates the viability of applying an option-based risk management (OBRiM) framework, and its accompanying theoretical perspective and methodology, to real-world sequential information technology (IT) investment problems. These problems involve alternative investment structures that bear different risk profiles for the firm, and also may improve the payoffs of the associated projects and the organization's performance. We sought to surface the costs, benefits, and risks associated with a complex sequential investment setting that has the key features that OBRiM treats. We combine traditional, purchased real options that subsequently create strategic flexibility for the decision maker, with implicit or …
Follow The Leader? Price Change Timing In Internet-Based Selling, R. J. Kauffman, Charles A. Wood
Follow The Leader? Price Change Timing In Internet-Based Selling, R. J. Kauffman, Charles A. Wood
Research Collection School Of Computing and Information Systems
Internet technologies should lessen information asymmetry, prompting competitive price reactions, but this does not seem to be happening in Internet-based selling. We study empirical regularities of price change timing for music CD vendors and booksellers to assess several theoretical explanations. Our sample includes 123, 680 daily prices for 169 products and 53 firms. Bertrand competition is insufficient to explain our observation that sellers do not shift prices this way. Tacitly collusive responses to competitors' price changes are observed rather than price changes solely in response to demand or cost shifts as would be expected with Bertrand competition. We find evidence …
Analyzing Service Usage Patterns: Methodology And Simulation, Qianhui (Althea) Liang, Jen-Yao Chung
Analyzing Service Usage Patterns: Methodology And Simulation, Qianhui (Althea) Liang, Jen-Yao Chung
Research Collection School Of Computing and Information Systems
This paper proposes that service mining technology will power the construction of new business services via both intra- and inter-enterprise service assembly within the Service Oriented Architecture (SOA) framework. We investigate the methodologies of service mining at the component level of service usage. We also demonstrate how mining of service usage patterns is intended to be used to improve different aspects of service composition. Simulation experiments conducted for mining at the component level are analyzed. The processing details within a general service mining deployment are demonstrated.
Om-Based Video Shot Retrieval By One-To-One Matching, Yuxin Peng, Chong-Wah Ngo, Jianguo Xiao
Om-Based Video Shot Retrieval By One-To-One Matching, Yuxin Peng, Chong-Wah Ngo, Jianguo Xiao
Research Collection School Of Computing and Information Systems
This paper proposes a new approach for shot-based retrieval by optimal matching (OM), which provides an effective mechanism for the similarity measure and ranking of shots by one-to-one matching. In the proposed approach, a weighted bipartite graph is constructed to model the color similarity between two shots. Then OM based on Kuhn-Munkres algorithm is employed to compute the maximum weight of a constructed bipartite graph as the shot similarity value by one-to-one matching among frames. To improve the speed efficiency of OM, two improved algorithms are also proposed: bipartite graph construction based on subshots and bipartite graph construction based on …
A Multitude Of Opinions: Mining Online Rating Data, Hady Wirawan Lauw, Ee Peng Lim
A Multitude Of Opinions: Mining Online Rating Data, Hady Wirawan Lauw, Ee Peng Lim
Research Collection School Of Computing and Information Systems
Online rating system is a popular feature of Web 2.0 applications. It typically involves a set of reviewers assigning rating scores (based on various evaluation criteria) to a set of objects. We identify two objectives for research on online rating data, namely achieving effective evaluation of objects and learning behaviors of reviewers/objects. These two objectives have conventionally been pursued separately. We argue that the future research direction should focus on the integration of these two objectives, as well as the integration between rating data and other types of data.
Npake+: A Hierarchical Group Password-Authenticated Key Exchange Protocol Using Different Passwords, Zhiguo Wan, Robert H. Deng, Feng Bao, Bart Preneel
Npake+: A Hierarchical Group Password-Authenticated Key Exchange Protocol Using Different Passwords, Zhiguo Wan, Robert H. Deng, Feng Bao, Bart Preneel
Research Collection School Of Computing and Information Systems
Although two-party password-authenticated key exchange (PAKE) protocols have been intensively studied in recent years, group PAKE protocols have received little attention. In this paper, we propose a hierarchical group PAKE protocol nPAKE+ protocol under the setting where each party shares an independent password with a trusted server. The nPAKE+ protocol is a novel combination of the hierarchical key tree structure and the password-based Diffie-Hellman exchange, and hence it achieves substantial gain in computation efficiency. In particular, the computation cost for each client in our protocol is only O(logn). Additionally, the hierarchical feature of nPAKE+ enables every subgroup obtains their own …
Sketchwizard: Wizard Of Oz Prototyping Of Pen-Based User Interfaces, Richard C. Davis, T. Scott Saponas, Michael Shilman, James A. Landay
Sketchwizard: Wizard Of Oz Prototyping Of Pen-Based User Interfaces, Richard C. Davis, T. Scott Saponas, Michael Shilman, James A. Landay
Research Collection School Of Computing and Information Systems
SketchWizard allows designers to create Wizard of Oz prototypes of pen-based user interfaces in the early stages of design. In the past, designers have been inhibited from participating in the design of pen-based interfaces because of the inadequacy of paper prototypes and the difficulty of developing functional prototypes. In SketchWizard, designers and end users share a drawing canvas between two computers, allowing the designer to simulate the behavior of recognition or other technologies. Special editing features are provided to help designers respond quickly to end-user input. This paper describes the SketchWizard system and presents two evaluations of our approach. The …
Rushes Video Summarization By Object And Event Understanding, Feng Wang, Chong-Wah Ngo
Rushes Video Summarization By Object And Event Understanding, Feng Wang, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
This paper explores a variety of visual and audio analysis techniques in selecting the most representative video clips for rushes summarization at TRECVID 2007. These techniques include object detection, camera motion estimation, keypoint matching and tracking, audio classification and speech recognition. Our system is composed of two major steps. First, based on video structuring, we filter undesirable shots and minimize the inter-shot redundancy by repetitive shot detection. Second, a representability measure is proposed to model the presence of objects and four audio-visual events: motion activity of objects, camera motion, scene changes, and speech content, in a video clip. The video …
Ontology-Enriched Semantic Space For Video Search, Xiao-Yong Wei, Chong-Wah Ngo
Ontology-Enriched Semantic Space For Video Search, Xiao-Yong Wei, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
Multimedia-based ontology construction and reasoning have recently been recognized as two important issues in video search, particularly for bridging semantic gap. The lack of coincidence between low-level features and user expectation makes concept-based ontology reasoning an attractive midlevel framework for interpreting high-level semantics. In this paper, we propose a novel model, namely ontology-enriched semantic space (OSS), to provide a computable platform for modeling and reasoning concepts in a linear space. OSS enlightens the possibility of answering conceptual questions such as a high coverage of semantic space with minimal set of concepts, and the set of concepts to be developed for …
Practical Elimination Of Near-Duplicates From Web Video Search, Xiao Wu, Alexander G. Hauptmann, Chong-Wah Ngo
Practical Elimination Of Near-Duplicates From Web Video Search, Xiao Wu, Alexander G. Hauptmann, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
Current web video search results rely exclusively on text keywords or user-supplied tags. A search on typical popular video often returns many duplicate and near-duplicate videos in the top results. This paper outlines ways to cluster and filter out the nearduplicate video using a hierarchical approach. Initial triage is performed using fast signatures derived from color histograms. Only when a video cannot be clearly classified as novel or nearduplicate using global signatures, we apply a more expensive local feature based near-duplicate detection which provides very accurate duplicate analysis through more costly computation. The results of 24 queries in a data …
Anonymous And Authenticated Key Exchange For Roaming Networks, Guomin Yang, Duncan S. Wong, Xiaotie Deng
Anonymous And Authenticated Key Exchange For Roaming Networks, Guomin Yang, Duncan S. Wong, Xiaotie Deng
Research Collection School Of Computing and Information Systems
User privacy is a notable security issue in wireless communications. It concerns about user identities from being exposed and user movements and whereabouts from being tracked. The concern of user privacy is particularly signified in systems which support roaming when users are able to hop across networks administered by different operators. In this paper, we propose a novel construction approach of anonymous and authenticated key exchange protocols for a roaming user and a visiting server to establish a random session key in such a way that the visiting server authenticates the user's home server without knowing exactly who the user …
Deception In Cyberspace: A Comparison Of Text-Only Vs. Avatar-Supported Medium, Holtjona Galanxhi, Fiona Fui-Hoon Nah
Deception In Cyberspace: A Comparison Of Text-Only Vs. Avatar-Supported Medium, Holtjona Galanxhi, Fiona Fui-Hoon Nah
Research Collection School Of Computing and Information Systems
The use of anthropomorphic avatars provides Internet users the opportunity and freedom to manipulate their identity. As cyberspace becomes a haven for deceptive behavior, human–computer interaction research will need to be carried out to study and understand these deceptive behaviors. The objective of this research is to investigate the behavior of deceivers and non-deceivers (or truth-tellers) in the cyberspace environment. We examine if the intention to deceive others influences one's choice of avatars in the online chat environment. We also investigate if communication medium (text-only vs. avatar-supported chat) influences one's perception of trustworthiness of the communication partner. A lab experiment …
Difference Computation Of Large Models, Christoph Treude, Stefan Berlik, Sven Wenzel, Udo Kelter
Difference Computation Of Large Models, Christoph Treude, Stefan Berlik, Sven Wenzel, Udo Kelter
Research Collection School Of Computing and Information Systems
Modern software engineering practices lead to large models which exist in many versions. Version management systems should offer a service to compare, and possibly merge, these models. The computation of a difference between large models is a big challenge; current algorithms are too inefficient here. We present a new technique for computing differences between models. In practical tests, this technique has been an order of magnitude faster than currently known algorithms. The main idea is to use a high-dimensional search tree for efficiently finding similar model elements. Individual elements are mapped onto a vector of numerical values using a collection …
Globally Distributed Software Development Project Performance: An Empirical Analysis, Narayanasamy Ramasubbu, Rajesh Krishna Balan
Globally Distributed Software Development Project Performance: An Empirical Analysis, Narayanasamy Ramasubbu, Rajesh Krishna Balan
Research Collection School Of Computing and Information Systems
Software firms are increasingly distributing their software development effort across multiple locations. In this paper we present the results of a two year field study that investigated the effects of dispersion on the productivity and quality of distributed software development. We first develop a model of distributed software development. We then use the model, along with our empirically observed data, to understand the consequences of dispersion on software project performance. Our analysis reveals that, even in high process maturity environments, a) dispersion significantly reduces development productivity and has effects on conformance quality, and b) these negative effects of dispersion can …
Overview Of The Imageclef 2007 Object Retrieval Task, Thomas Deselaers, Steven C. H. Hoi
Overview Of The Imageclef 2007 Object Retrieval Task, Thomas Deselaers, Steven C. H. Hoi
Research Collection School Of Computing and Information Systems
We describe the object retrieval task of ImageCLEF 2007, give an overview of the methods of the participating groups, and present and discuss the results. The task was based on the widely used PASCAL object recognition data to train object recognition methods and on the IAPR TC-12 benchmark dataset from which images of objects of the ten different classes bicycles, buses, cars, motorbikes, cats, cows, dogs, horses, sheep, and persons had to be retrieved. Seven international groups participated using a wide variety of methods. The results of the evaluation show that the task was very challenging and that different methods …