Vireo At Trecvid 2010: Semantic Indexing, Known-Item Search, And Content-Based Copy Detection,
2010
Singapore Management University
Vireo At Trecvid 2010: Semantic Indexing, Known-Item Search, And Content-Based Copy Detection, Chong-Wah Ngo, Shi-Ai Zhu, Hung-Khoon Tan, Wan-Lei Zhao
Research Collection School Of Computing and Information Systems
This paper presents our approaches and the comparative analysis of our results for the three TRECVID 2010 tasks that we participated in: semantic indexing, known-item search and content-based copy detection.
Semi-Autonomous Virtual Valet Parking,
2010
Singapore Management University
Semi-Autonomous Virtual Valet Parking, Arne Suppe, Luis Navarro-Serment, Aaron Steinfeld
Research Collection School Of Computing and Information Systems
Despite regulations specifying parking spots that support wheelchair vans, it is not uncommon for end users to encounter problems with clearance for van ramps. Even if a driver elects to park in the far reaches of a parking lot as a precautionary measure, there is no guarantee that the spot next to their van will be empty when they return. Likewise, the prevalence of older drivers who experience significant difficulty with ingress and egress from vehicles is nontrivial and the ability to fully open a car door is important. This work describes a method and user interaction for low cost, …
Efficient Mining Of Multiple Partial Near-Duplicate Alignments By Temporal Network,
2010
Singapore Management University
Efficient Mining Of Multiple Partial Near-Duplicate Alignments By Temporal Network, Hung-Khoon Tan, Chong-Wah Ngo, Tat-Seng Chua
Research Collection School Of Computing and Information Systems
This paper considers the mining and localization of near-duplicate segments at arbitrary positions of partial near-duplicate videos in a corpus. Temporal network is proposed to model the visual-temporal consistency between video sequence by embedding temporal constraints as directed edges in the network. Partial alignment is then achieved through network flow programming. To handle multiple alignments, we consider two properties of network structure: conciseness and divisibility, to ensure that the mining is efficient and effective. Frame-level matching is further integrated in the temporal network for alignment verification. This results in an iterative alignment-verification procedure to fine tune the localization of near-duplicate …
Program Transformations For Information Personalization,
2010
University of Dayton
Program Transformations For Information Personalization, Saverio Perugini, Naren Ramakrishnan
Computer Science Faculty Publications
Personalization constitutes the mechanisms necessary to automatically customize information content, structure, and presentation to the end user to reduce information overload. Unlike traditional approaches to personalization, the central theme of our approach is to model a website as a program and conduct website transformation for personalization by program transformation (e.g., partial evaluation, program slicing). The goal of this paper is study personalization through a program transformation lens and develop a formal model, based on program transformations, for personalized interaction with hierarchical hypermedia. The specific research issues addressed involve identifying and developing program representations and transformations suitable for classes of hierarchical …
Trajectory-Based Visualization Of Web Video Topics,
2010
Singapore Management University
Trajectory-Based Visualization Of Web Video Topics, Juan Cao, Chong-Wah Ngo, Yong-Dong Zhang, Dong-Ming Zhang, Liang Ma
Research Collection School Of Computing and Information Systems
While there have been research efforts in organizing largescale web videos into topics, efficient browsing of web video topics remains a challenging problem not yet addressed. The related issues include how to efficiently browse and track the evolution of topics and eventually locate the videos of interest. In this paper, we introduce a novel interface for visualizing video topics as evolution trajectories. The trajectory visualization is capable of highlighting milestone events and depicting the topical hotness over time. The interface also allows multi-level browsing from topics to events and to videos, resulting in search exploration could be more efficiently conducted …
Cast2face: Character Identification In Movie With Actor-Character Correspondence,
2010
National University of Singapore
Cast2face: Character Identification In Movie With Actor-Character Correspondence, Mengdi Xu, Xiaotong Yuan, Jialie Shen, Shuicheng Yan
Research Collection School Of Computing and Information Systems
We investigate the problem of automatically identifying characters in a movie with the supervision of actor-character name correspondence provided by the movie cast. Our proposed framework, namely Cast2Face, is featured by: (i) we restrict the names to assign within the set of character names in the cast; (ii) for each character, by using the corresponding actor's name as a key word, we retrieve from Google image search a group of face images to form the gallery set; and (iii) the probe face tracks in the movie are then identified as one of the actors by robust multi-task joint sparse representation …
Statistical Image Recovery From Laser Speckle Patterns With Polarization Diversity,
2010
Air Force Institute of Technology
Statistical Image Recovery From Laser Speckle Patterns With Polarization Diversity, Donald B. Dixon
Theses and Dissertations
This research extends the theory and understanding of the laser speckle imaging technique. This non-traditional imaging technique may be employed to improve space situational awareness and image deep space objects from a ground-based sensor system. The use of this technique is motivated by the ability to overcome aperture size limitations and the distortion effects from Earth’s atmosphere. Laser speckle imaging is a lensless, coherent method for forming two-dimensional images from their autocorrelation functions. Phase retrieval from autocorrelation data is an ill-posed problem where multiple solutions exist. This research introduces polarization diversity as a method for obtaining additional information so the …
Accelerating Malware Detection Via A Graphics Processing Unit,
2010
Air Force Institute of Technology
Accelerating Malware Detection Via A Graphics Processing Unit, Nicholas S. Kovach
Theses and Dissertations
Real-time malware analysis requires processing large amounts of data storage to look for suspicious files. This is a time consuming process that (requires a large amount of processing power) often affecting other applications running on a personal computer. This research investigates the viability of using Graphic Processing Units (GPUs), present in many personal computers, to distribute the workload normally processed by the standard Central Processing Unit (CPU). Three experiments are conducted using an industry standard GPU, the NVIDIA GeForce 9500 GT card. The goal of the first experiment is to find the optimal number of threads per block for calculating …
3dq: Threat Dome Visibility Querying On Mobile Devices,
2010
Technological University Dublin
3dq: Threat Dome Visibility Querying On Mobile Devices, James Carswell, Keith Gardiner, Junjun Yin
Articles
3DQ (Three Dimensional Query) is our mobile spatial interaction (MSI) prototype for location and orientation aware mobile devices (i.e. today's sensor enabled smartphones). The prototype tailors a military style threat dome query calculation using MSI with hidden query removal functionality for reducing “information overload” on these off-the-shelf devices. The effect gives a more accurate and expected query result for Location-Based Services (LBS) applications by returning information on only those objects visible within a user’s 3D field-of-view. Our standardised XML based request/response design enables any mobile device, regardless of operating system and/or programming language, to access the 3DQ web-service interfaces.
Learning Personal Agents With Adaptive Player Modeling In Virtual Worlds,
2010
Singapore Management University
Learning Personal Agents With Adaptive Player Modeling In Virtual Worlds, Yilin Kang, Ah-Hwee Tan
Research Collection School Of Computing and Information Systems
There has been growing interest in creating intelligent agents in virtual worlds that do not follow fixed scripts predefined by the developers, but react accordingly based on actions performed by human players during their interaction. In order to achieve this objective, previous approaches have attempted to model the environment and the user’s context directly. However, a critical component for enabling personalized virtual world experience is missing, namely the capability to adapt over time to the habits and eccentricity of a particular player. To address the above issue, this paper presents a cognitive agent with learning player model capability for personalized …
Automatic Generation Of Semantic Fields For Annotating Web Images,
2010
Singapore Management University
Automatic Generation Of Semantic Fields For Annotating Web Images, Gang Wang, Tat Seng Chua, Chong-Wah Ngo, Yong Cheng Wang
Research Collection School Of Computing and Information Systems
The overwhelming amounts of multimedia contents have triggered the need for automatically detecting the semantic concepts within the media contents. With the development of photo sharing websites such as Flickr, we are able to obtain millions of images with usersupplied tags. However, user tags tend to be noisy, ambiguous and incomplete. In order to improve the quality of tags to annotate web images, we propose an approach to build Semantic Fields for annotating the web images. The main idea is that the images are more likely to be relevant to a given concept, if several tags to the image belong …
Visual Occam: High Level Visualization And Design Of Process Networks,
2010
University of Nevada, Las Vegas
Visual Occam: High Level Visualization And Design Of Process Networks, Mikolaj M. Slomka
UNLV Theses, Dissertations, Professional Papers, and Capstones
With networks, multiprocessors, and multi-threaded systems becoming more common in our world it is increasingly evident that concurrent programming is not something to be ignored or marginalized even though many takes on concurrency (mainly by means of monitors or shared resources) have proven to be difficult to deal with on large scales. Thankfully, a good deal of work has already been done to combat this, through CSP, occam, and other such derivatives, to produce a scalable process oriented paradigm. Still, it is cumbersome to attempt to deal with the intricacies of such communicating networks down to every minutia; if, instead, …
On The Annotation Of Web Videos By Efficient Near-Duplicate Search,
2010
Singapore Management University
On The Annotation Of Web Videos By Efficient Near-Duplicate Search, Wan-Lei Zhao, Xiao Wu, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
With the proliferation of Web 2.0 applications, usersupplied social tags are commonly available in social media as a means to bridge the semantic gap. On the other hand, the explosive expansion of social web makes an overwhelming number of web videos available, among which there exists a large number of near-duplicate videos. In this paper, we investigate techniques which allow effective annotation of web videos from a data-driven perspective. A novel classifier-free video annotation framework is proposed by first retrieving visual duplicates and then suggesting representative tags. The significance of this paper lies in the addressing of two timely issues …
Co-Reranking By Mutual Reinforcement For Image Search,
2010
Singapore Management University
Co-Reranking By Mutual Reinforcement For Image Search, Ting Yao, Tao Mei, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
Most existing reranking approaches to image search focus solely on mining “visual” cues within the initial search results. However, the visual information cannot always provide enough guidance to the reranking process. For example, different images with similar appearance may not always present the same relevant information to the query. Observing that multi-modality cues carry complementary relevant information, we propose the idea of co-reranking for image search, by jointly exploring the visual and textual information. Co-reranking couples two random walks, while reinforcing the mutual exchange and propagation of information relevancy across different modalities. The mutual reinforcement is iteratively updated to constrain …
On The Sampling Of Web Images For Learning Visual Concept Classifiers,
2010
Singapore Management University
On The Sampling Of Web Images For Learning Visual Concept Classifiers, Shiai Zhu, Gang Wang, Chong-Wah Ngo, Yu-Gang Jiang
Research Collection School Of Computing and Information Systems
Visual concept learning often requires a large set of training images. In practice, nevertheless, acquiring noise-free training labels with sufficient positive examples is always expensive. A plausible solution for training data collection is by sampling the largely available user-tagged images from social media websites. With the general belief that the probability of correct tagging is higher than that of incorrect tagging, such a solution often sounds feasible, though is not without challenges. First, user-tags can be subjective and, to certain extent, are ambiguous. For instance, an image tagged with “whales” may be simply a picture about ocean museum. Learning concept …
Coherent Bag-Of Audio Words Model For Efficient Large-Scale Video Copy Detection,
2010
Singapore Management University
Coherent Bag-Of Audio Words Model For Efficient Large-Scale Video Copy Detection, Yang Liu, Wan-Lei Zhao, Chong-Wah Ngo, Chang-Sheng Xu, Han-Qing Lu
Research Collection School Of Computing and Information Systems
Current content-based video copy detection approaches mostly concentrate on the visual cues and neglect the audio information. In this paper, we attempt to tackle the video copy detection task resorting to audio information, which is equivalently important as well as visual information in multimedia processing. Firstly, inspired by bag-of visual words model, a bag-of audio words (BoA) representation is proposed to characterize each audio frame. Different from naive singlebased modeling audio retrieval approaches, BoA is a highlevel model due to its perceptual and semantical property. Within the BoA model, a coherency vocabulary indexing structure is adopted to achieve more efficient …
Cognitive Load Of Rating Scales,
2010
Macalester College
Cognitive Load Of Rating Scales, E. Isaac G. Sparling, Shilad Sen
Mathematics, Statistics, and Computer Science Honors Projects
Why does Netflix.com use star ratings, Digg.com use up/down votes and Face- book use a “like” but not a “dislike” button? In this paper, we extend existing research on rating scales with findings from an experiment we ran to measure the cognitive load users experience while rating. In this paper, we analyze the cognitive load and time required by different rating scales. Our analysis draws upon 14,000 movie and product ratings we collected from 348 users through an online survey. In the survey, we measured the speed and cognitive load users ex- perience under four scales: unary (‘like it’), binary …
Wii-Mote Head Tracking: A Three Dimensional Virtual Reality Display,
2010
California Polytechnic State University - San Luis Obispo
Wii-Mote Head Tracking: A Three Dimensional Virtual Reality Display, David Fairman
Computer Engineering
The goal of this project is to create a customizable three dimensional virtual reality display on a system available to any non-technical user. This System will use the infrared camera component of a standard Nintendo Wii-mote to track a user's head motions in all six major directions. The virtual reality will be a customizable image projected onto a screen or simply shown on a computer or TV monitor. In order to appear 3-dimensional, the image will continually change according to the position of the user's head. As the user moves their head to the left and right, portions of the …
Semantic Context Modeling With Maximal Margin Conditional Random Fields For Automatic Image Annotation,
2010
Singapore Management University
Semantic Context Modeling With Maximal Margin Conditional Random Fields For Automatic Image Annotation, Yu Xiang, Xiangdong Zhou, Zuotao Liu, Tat-Seng Chua, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
Context modeling for Vision Recognition and Automatic Image Annotation (AIA) has attracted increasing attentions in recent years. For various contextual information and resources, semantic context has been exploited in AIA and brings promising results. However, previous works either casted the problem into structural classification or adopted multi-layer modeling, which suffer from the problems of scalability or model efficiency. In this paper, we propose a novel discriminative Conditional Random Field (CRF) model for semantic context modeling in AIA, which is built over semantic concepts and treats an image as a whole observation without segmentation. Our model captures the interactions between semantic …
Real-Time Visualizations Of Ocean Data Collected By The Norus Glider,
2010
California Polytechnic State University, San Luis Obispo
Real-Time Visualizations Of Ocean Data Collected By The Norus Glider, Daniel M. Medina
Master's Theses
Scientific visualization computer applications generate visual representations of large and complex sets of science data. These types of applications allow scientists to gain greater knowledge and insight into their data. For example, the visualization of environmental data is of particular interest to biologists when trying to understand how complex variables interact. Modern robotics and sensors have expanded the ability to collect environmental data, thus, the size and variety of these data-sets have likewise grown. Oftentimes, the collected data are deposited into files and databases where they sit in their separate and unique formats. Without easy to use visualization tools, it …
