Graphics and Human Computer Interfaces Commons^™

Reconstructing Point Clouds Of Mid-Size Objects, Spencer Woodworth

Computer Science and Software Engineering

This project explores the use of an inexpensive 3D camera for the acquisition and reconstruction of mid-size objects. The disparity of objects between stereo image pairs are used to calculate depth and generate a depth map. The depth map is used to generate a point cloud representation of the object from a single view. Finally, point clouds are generated from several views of an object and then aligned and merged into a seamless 360-degree point cloud.

Conceptual, Impact-Based Publications Recommendations, Ann Smittu Joseph

Graduate Theses and Dissertations

CiteSeerx is a digital library for scientific publications by computer science researchers. It also functions as a search engine with several features including autonomous citation indexing, automatic metadata extraction, full-text indexing and reference linking. Users are able to retrieve relevant documents from the CiteSeer^x database directly using search queries and will further benefit if the system suggests document recommendations to the user based on their preferences and search history. Therefore, recommender systems were initially developed and continue to evolve to recommend more relevant documents to the CiteSeer^x users. In this thesis, we introduce the Conceptual, Impact-Based Recommender (CIBR), …

A Bandwidth-Conserving Architecture For Crawling Virtual Worlds, Dipesh Gautam

Graduate Theses and Dissertations

A virtual world is a computer-based simulated environment intended for its users to inhabit via avatars. Content in virtual worlds such as Second Life or OpenSimulator is increasingly presented using three-dimensional (3D) dynamic presentation technologies that challenge traditional search technologies. As 3D environments become both more prevalent and more fragmented, the need for a data crawler and distributed search service will continue to grow. By increasing the visibility of content across virtual world servers in order to better collect and integrate the 3D data we can also improve the crawling and searching efficiency and accuracy by avoiding crawling unchanged regions …

Partial Least Squares Regression On Grassmannian Manifold For Emotion Recognition, M. Liu, R. Wang, Zhiwu Huang, S. Shan, X. Chen

Research Collection School Of Computing and Information Systems

In this paper, we propose a method for video-based human emotion recognition. For each video clip, all frames are represented as an image set, which can be modeled as a linear subspace to be embedded in Grassmannian manifold. After feature extraction, Class-specific One-to-Rest Partial Least Squares (PLS) is learned on video and audio data respectively to distinguish each class from the other confusing ones. Finally, an optimal fusion of classifiers learned from both modalities (video and audio) is conducted at decision level. Our method is evaluated on the Emotion Recognition In The Wild Challenge (EmotiW 2013). The experimental results on …

Dense Image Correspondence Under Large Appearance Variations, Linlin Liu, Kok-Lim Low, Wen-Yan Lin

Research Collection School Of Computing and Information Systems

This paper addresses the difficult problem of finding dense correspondence across images with large appearance variations. Our method uses multiple feature samples at each pixel to deal with the appearance variations based on our observation that pre-defined single feature sample provides poor results in nearest neighbor matching. We apply the idea in a flow-based matching framework and utilize the best feature sample for each pixel to determine the flow field. We propose a novel energy function and use dual-layer loopy belief propagation to minimize it where the correspondence, the feature scale and rotation parameters are solved simultaneously. Our method is …

Tonescale Compression For Electroluminescent Display, Michael E. Miller, Christopher J. White

AFIT Patents

A method for controlling an electroluminescent display to produce an image for display that has reduced luminance to reduce burn-in on the display while maintaining visible contrast, includes providing the electroluminescent (EL) display having a plurality of EL emitters, the luminance of the light produced by each EL emitter being responsive to a respective drive signal; receiving a respective input image signal for each EL emitter; and transforming the input image signals to a plurality of drive signals that have a reduced peak frame luminance value but maintains contrast in the displayed image to reduce burn-in by adjusting the drive …

Caver Quest 3d Virtual Cave Simulation Of Snowy River In Fort Stanton Cave, Ronald J. Lipinski, Pete Lindsley

National Cave and Karst Management Symposium 2013

Virtual worlds, or 3D simulations through which an avatar can travel, is becoming a common means to display products or provide training in new environments. This paper describes the steps in producing the 3D virtual simulation of Snowy River in Fort Stanton Cave, New Mexico. A traditional cave survey and map with cross sections was used to produce a 3D meshed surface of the cave walls using the Blender software package. Photographs were taken of the walls, ceiling, and floor and merged together. The merged montage was applied to the 3D mesh walls as a “texture”. Unity3D was used to …

Search Of Small Objects By Topology Matching, Context Modeling, And Pattern Mining, Wei Zhang, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

No abstract provided.

Vireo/Ecnu @ Trecvid 2013: A Video Dance Of Detection, Recounting And Search With Motion Relativity And Concept Learning From Wild, Chong-Wah Ngo, Feng Wang, Wei Zhang, Chun-Chet Tan, Zhanhu Sun, Shi-Ai Zhu, Ting Yao

Research Collection School Of Computing and Information Systems

The VIREO group participated in four tasks: instance search, multimedia event recounting, multimedia event detection, and semantic indexing. In this paper, we will present our approaches and discuss the evaluation results

Multimedia Modeling, Chong-Wah Ngo, Klaus Schoeffmann, Yiannis Andreopoulos, Christian Breiteneder

Research Collection School Of Computing and Information Systems

Multimedia modeling aims to study computational models for addressing real-world multimedia problems from various perspectives, including information fusion, perceptual understanding, performance evaluation and social media. The topic becomes increasingly important with the massive amount of data available over the Internet, representing different pieces of information in heterogeneous forms that need to be consolidated before being used for multimedia problems. On the other hand, the advancement in technologies such as mobile and sensing devices drive the needs for revisiting the existing models for not only dealing with audio-visual cues but also incorporating various sensory modalities that have potential in providing cheaper …

Symmetry Robust Descriptor For Non-Rigid Surface Matching, Zhiyuan Zhang, Kangkang Yin, Kelvin W. C. Foong

Research Collection School Of Computing and Information Systems

In this paper, we propose a novel shape descriptor that is robust in differentiating intrinsic symmetric points on geometric surfaces. Our motivation is that even the state-of-theart shape descriptors and non-rigid surface matching algorithms suffer from symmetry flips. They cannot differentiate surface points that are symmetric or near symmetric. Hence a left hand of one human model may be matched to a right hand of another. Our Symmetry Robust Descriptor (SRD) is based on a signed angle field, which can be calculated from the gradient fields of the harmonic fields of two point pairs. Experiments show that the proposed shape …

Web-Based Visual Analytics For Social Media Data, Jun Xiang Tee, David S. Ebert

The Summer Undergraduate Research Fellowship (SURF) Symposium

Social media data provides valuable information about different events, trends and happenings around the world. Visual data analysis tasks for social media data have large computational and storage space requirements. Due to these restrictions, subdivision of data analysis tools into several layers such as Data, Business Logic or Algorithms, and Presentation Layer is often necessary to make them accessible for variety of clients. On server side, social media data analysis algorithms can be implemented and published in the form of web services. Visual Interface can then be implemented in the form of thin clients that call these web services for …

Static Saliency Vs. Dynamic Saliency: A Comparative Study, Tam Nguyen, Mengdi Xu, Guangyu Gao, Mohan Kankanhalli, Qi Tian, Shuicheng Yan

Computer Science Faculty Publications

Recently visual saliency has attracted wide attention of researchers in the computer vision and multimedia field. However, most of the visual saliency-related research was conducted on still images for studying static saliency. In this paper, we give a comprehensive comparative study for the first time of dynamic saliency (video shots) and static saliency (key frames of the corresponding video shots), and two key observations are obtained: 1) video saliency is often different from, yet quite related with, image saliency, and 2) camera motions, such as tilting, panning or zooming, affect dynamic saliency significantly.

Motivated by these observations, we propose a …

Interactive Focus+Context Glyph And Streamline Vector Visualization, Joshua Joseph Anghel

Boise State University Theses and Dissertations

With data sets growing in size, more efficient methods of visualizing and analyzing data are required. A user can become overwhelmed if too much data is displayed at once and be distracted from identifying potentially important features. This thesis presents methods for focus+context visualization of vector fields. Users can interact with the data in real time to choose which regions should have more emphasis through a mouse or touch interface. Streamlines and hedgehog based visualizations are used to provide focus+context to vector visualizations. The presented visualization methods are shown to be more computationally efficient and are shown to scale well …

Image Search By Graph-Based Label Propagation With Image Representation From Dnn, Yingwei Pan, Yao Ting, Kuiyuan Yang, Houqiang Li, Chong-Wah Ngo, Jingdong Wang, Tao Mei

Research Collection School Of Computing and Information Systems

Our objective is to estimate the relevance of an image to a query for image search purposes. We address two limitations of the existing image search engines in this paper. First, there is no straightforward way of bridging the gap between semantic textual queries as well as users’ search intents and image visual content. Image search engines therefore primarily rely on static and textual features. Visual features are mainly used to identify potentially useful recurrent patterns or relevant training examples for complementing search by image reranking. Second, image rankers are trained on query-image pairs labeled by human experts, making the …

Annotation For Free: Video Tagging By Mining User Search Behavior, Yao Ting, Tao Mei, Chong-Wah Ngo, Shipeng Li

Research Collection School Of Computing and Information Systems

The problem of tagging is mostly considered from the perspectives of machine learning and data-driven philosophy. A fundamental issue that underlies the success of these approaches is the visual similarity, ranging from the nearest neighbor search to manifold learning, to identify similar instances of an example for tag completion. The need to searching for millions of visual examples in high-dimensional feature space, however, makes the task computationally expensive. Moreover, the results can suffer from robustness problem, when the underlying data, such as online videos, are rich of semantics and the similarity is difficult to be learnt from low-level features. This …

Error Recovered Hierarchical Classification, Shiai Zhu, Xiao-Yong Wei, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Hierarchical classification (HC) is a popular and efficient way for detecting the semantic concepts from the images. However, the conventional HC, which always selects the branch with the highest classification response to go on, has the risk of propagating serious errors from higher levels of the hierarchy to the lower levels. We argue that the highestresponse-first strategy is too arbitrary, because the candidate nodes are considered individually which ignores the semantic relationship among them. In this paper, we propose a novel method for HC, which is able to utilize the semantic relationship among candidate nodes and their children to recover …

The Vireo Team At Mediaeval 2013: Violent Scenes Detection By Mid-Level Concepts Learnt From Youtube, Chun Chet Tan, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

The Violent Scenes Detection task continues to pose challenge in detecting violent scenes in Hollywood movies. In this working notes paper, we present the framework of our system and briefly discuss the performance results obtained in both objective and subjective subtasks. Besides using the low-level features for training the SVM classifiers for violent scenes detection, we show the feasibility in using the concept detectors to infer the occurrence of violent scenes. External Youtube data is exploited in our implementation to provide more diverse definition to violent scene concepts. Furthermore, we explore the feasibility of using Conditional Random Fields (CRF) to …

Sitting On The Digital Divide, Singapore Management University

Perspectives@SMU

Persuading the ‘digital resistant’ while balancing the digital:traditional media budget is a challenge for marketers

A Robust Rgbd Slam System For 3d Environment With Planar Surfaces, Po-Chang Su, Ju Shen, Sen-Ching S. Cheung

Computer Science Faculty Publications

With the increasing popularity of RGB-depth (RGB-D) sensors such as the Microsoft Kinect, there have been much research on capturing and reconstructing 3D environments using a movable RGB-D sensor. The key process behind these kinds of simultaneous location and mapping (SLAM) systems is the iterative closest point or ICP algorithm, which is an iterative algorithm that can estimate the rigid movement of the camera based on the captured 3D point clouds. While ICP is a well-studied algorithm, it is problematic when it is used in scanning large planar regions such as wall surfaces in a room. The lack of depth …