Open Access. Powered by Scholars. Published by Universities.®

Graphics and Human Computer Interfaces Commons™

Open Access. Powered by Scholars. Published by Universities.®

Singapore Management University

Discipline
Keyword
Publication Year
Publication
Publication Type

Articles 691 - 720 of 959

Full-Text Articles in Graphics and Human Computer Interfaces

Foreword To Special Section On Graphics Interface 2015, Hao Zhang, Anthony Tang Apr 2016

Foreword To Special Section On Graphics Interface 2015, Hao Zhang, Anthony Tang

Research Collection School Of Computing and Information Systems

This special section of the Computers & Graphics (C&G) Journal features expanded versions of five of the top graphics and interactions papers [1–5] that were originally presented at Graphics Interface (GI) 2015, which took place in Halifax, Nova Scotia, Canada, between June 3rd and 5th. GI, sponsored by the Canadian Human–Computer Communications Society, is an annual international conference devoted to computer graphics and human– computer interaction (HCI). With a graphics track and an HCI track having equal weights in the conference, GI offers a unique venue for a meeting of minds working on computer graphics and interactive techniques. GI is …

Go to article

Understanding The Determinants Of Human Computation Game Acceptance: The Effects Of Aesthetic Experience And Output Quality, Xiaohui Wang, Dion Hoe-Lian Goh, Ee-Peng Lim, Wei Liang Adrian Vu Apr 2016

Understanding The Determinants Of Human Computation Game Acceptance: The Effects Of Aesthetic Experience And Output Quality, Xiaohui Wang, Dion Hoe-Lian Goh, Ee-Peng Lim, Wei Liang Adrian Vu

Research Collection School Of Computing and Information Systems

Purpose: Human computation games (HCGs) that blend gaming with utilitarian purposes are a potentially effective channel for content creation. The purpose of this paper is to investigate the driving factors behind players’ adoption of HCGs through a music video tagging game. The effects of perceived aesthetic experience (PAE) and perceived output quality (POQ) on HCG acceptance are empirically examined. Design/methodology/approach: An integrative structural model is developed to explain how hedonic and utilitarian factors, including PAE and POQ, working with another salient factor – perceived usefulness (PU) – affect the acceptance of HCGs. The structural equation modeling method is used to …

Go to article

Opinion Question Answering By Sentiment Clip Localization, Lei Pang, Chong-Wah Ngo Mar 2016

Opinion Question Answering By Sentiment Clip Localization, Lei Pang, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

This article considers multimedia question answering beyond factoid and how-to questions. We are interested in searching videos for answering opinion-oriented questions that are controversial and hotly debated. Examples of questions include "Should Edward Snowden be pardoned?" and "Obamacare-unconstitutional or not?". These questions often invoke emotional response, either positively or negatively, hence are likely to be better answered by videos than texts, due to the vivid display of emotional signals visible through facial expression and speaking tone. Nevertheless, a potential answer of duration 60s may be embedded in a video of 10min, resulting in degraded user experience compared to reading the …

Go to article

A Tool-Free Calibration Method For Turntable-Based 3d Scanning Systems, Xufang Pang, Rynson W.H. Lau, Zhan Song, Shengfeng He, Shengfeng He Jan 2016

A Tool-Free Calibration Method For Turntable-Based 3d Scanning Systems, Xufang Pang, Rynson W.H. Lau, Zhan Song, Shengfeng He, Shengfeng He

Research Collection School Of Computing and Information Systems

Turntable-based 3D scanners are popular but require calibration of the turntable axis. Existing methods for turntable calibration typically make use of specially designed tools, such as a chessboard or criterion sphere, which users must manually install and dismount. In this article, the authors propose an automatic method to calibrate the turntable axis without any calibration tools. Given a scan sequence of the input object, they first recover the initial rotation axis from an automatic registration step. Then they apply an iterative procedure to obtain the optimized turntable axis. This iterative procedure alternates between two steps: refining the initial pose of …

Go to article

Object Pooling For Multimedia Event Detection And Evidence Localization, Ho Zhang, Chong-Wah Ngo, Chong-Wah Ngo Jan 2016

Object Pooling For Multimedia Event Detection And Evidence Localization, Ho Zhang, Chong-Wah Ngo, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Multimedia event detection (MED) and evidence hunting are two primary topics in the area of multimedia event search. The former serves to retrieve a list of relevant videos given an event query, whereas, the latter reasons why and how much the degree a retrieved video answers that query. Common practices deal with these two topics in separate methods, however, in this paper, we combine MED and evidence hunting into a joint framework. We propose a refined semantical representation named object pooling which can dynamically extract visual snippets corresponding to the location of when and where evidences might appear. The main …

Go to article

Ambiguityvis: Visualization Of Ambiguity In Graph Layouts, Yong Wang, Qiaomu Shen, Zhiguang Zhou, Min Zhu, Sixiao Yang, Qu Huamin Jan 2016

Ambiguityvis: Visualization Of Ambiguity In Graph Layouts, Yong Wang, Qiaomu Shen, Zhiguang Zhou, Min Zhu, Sixiao Yang, Qu Huamin

Research Collection School Of Computing and Information Systems

Node-link diagrams provide an intuitive way to explore networks and have inspired a large number of automated graph layout strategies that optimize aesthetic criteria. However, any particular drawing approach cannot fully satisfy all these criteria simultaneously, producing drawings with visual ambiguities that can impede the understanding of network structure. To bring attention to these potentially problematic areas present in the drawing. this paper presents a technique that highlights common types of visual ambiguities: ambiguous spatial relationships between nodes and edges, visual overlap between community structures, and ambiguity in edge bundling and metanodes. Metrics, including newly proposed metrics for abnormal edge …

Go to article

Aesthetic Experience And Acceptance Of Human Computation Games, Xiaohui Wang, Dion Hoe-Lian Goh, Ee-Peng Lim, Adrian Wei Liang Vu Dec 2015

Aesthetic Experience And Acceptance Of Human Computation Games, Xiaohui Wang, Dion Hoe-Lian Goh, Ee-Peng Lim, Adrian Wei Liang Vu

Research Collection School Of Computing and Information Systems

Human computation games (HCGs) are applications that leverage games to solve computational problems that are out reach of the capacity of computers. Game aesthetics are critical for HCG acceptance, and the game elements should motivate users to contribute time and effort. In this paper, we examine the effect of aesthetic experience on intention to use HCGs. A between-subjects experiment was conducted to compare a HCG and a human computation system (HCS). Results demonstrated that HCGs provided a greater sense of aesthetic experience and attracted more intentional usage than HCSs. Implications of this study are discussed.

Go to article

Mylife: An Online Personal Memory Album, Di Wang, Ah-Hwee Tan Dec 2015

Mylife: An Online Personal Memory Album, Di Wang, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

In this demo, we illustrate the formation, retrieval, and playback of autobiographical memory in an online personal memory album named MyLife. The memory in MyLife consists of pictorial snapshots of one's life together with the associated context, namely time, location, people, activity, imagery, and emotion. MyLife allows direct import of memories from other online personal photo repositories. For memory retrieval, users can use not only exact cues, but also partial, vague, inaccurate, and random ones. The retrieved memories are then played back as a movie-like slide show with various visual effects and background music. MyLife holds high potential in both …

Go to article

Oriented Object Proposals, Shengfeng He, Rynson W. H. Lau Dec 2015

Oriented Object Proposals, Shengfeng He, Rynson W. H. Lau

Research Collection School Of Computing and Information Systems

In this paper, we propose a new approach to generate oriented object proposals (OOPs) to reduce the detection error caused by various orientations of the object. To this end, we propose to efficiently locate object regions according to pixelwise object probability, rather than measuring the objectness from a set of sampled windows. We formulate the proposal generation problem as a generative probabilistic model such that object proposals of different shapes (i.e., sizes and orientations) can be produced by locating the local maximum likelihoods. The new approach has three main advantages. First, it helps the object detector handle objects of different …

Go to article

Flow Experience In Virtual Worlds: Individuals Versus Dyads, Fiona Fui-Hoon Nah, Brenda Eschenbrenner Dec 2015

Flow Experience In Virtual Worlds: Individuals Versus Dyads, Fiona Fui-Hoon Nah, Brenda Eschenbrenner

Research Collection School Of Computing and Information Systems

Flow is a state of mind in which one is deeply absorbed and immersed in an activity to the point where nothing else matters. Although flow can occur in solitary and social contexts, which context fosters greater flow is unclear. Consistent with self-determination theory, dyads working collaboratively achieved higher states of flow than individuals working alone. In other words, dyads achieved higher states of focused concentration and experienced greater temporal dissociation than individuals working alone. Surprisingly and contradictory to previous findings, dyads did not experience greater enjoyment than individuals working alone. We attributed this surprising finding to the hedonic nature …

Go to article

A Benchmark And Comparative Study Of Video-Based Face Recognition On Cox Face Database, Zhiwu Huang, S. Shan, R. Wang, H. Zhang, S. Lao, A. Kuerban, X. Chen Dec 2015

A Benchmark And Comparative Study Of Video-Based Face Recognition On Cox Face Database, Zhiwu Huang, S. Shan, R. Wang, H. Zhang, S. Lao, A. Kuerban, X. Chen

Research Collection School Of Computing and Information Systems

Face recognition with still face images has been widely studied, while the research on video-based face recognition is inadequate relatively, especially in terms of benchmark datasets and comparisons. Real-world video-based face recognition applications require techniques for three distinct scenarios: 1) Videoto-Still (V2S); 2) Still-to-Video (S2V); and 3) Video-to-Video (V2V), respectively, taking video or still image as query or target. To the best of our knowledge, few datasets and evaluation protocols have benchmarked for all the three scenarios. In order to facilitate the study of this specific topic, this paper contributes a benchmarking and comparative study based on a newly collected …

Go to article

Learning Query And Image Similarities With Ranking Canonical Correlation Analysis, Ting Yao, Tao Mei, Chong-Wah Ngo Dec 2015

Learning Query And Image Similarities With Ranking Canonical Correlation Analysis, Ting Yao, Tao Mei, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

One of the fundamental problems in image search is to learn the ranking functions, i.e., similarity between the query and image. The research on this topic has evolved through two paradigms: feature-based vector model and image ranker learning. The former relies on the image surrounding texts, while the latter learns a ranker based on human labeled query-image pairs. Each of the paradigms has its own limitation. The vector model is sensitive to the quality of text descriptions, and the learning paradigm is difficult to be scaled up as human labeling is always too expensive to obtain. We demonstrate in this …

Go to article

Dictionary Pair Learning On Grassmann Manifolds For Image Denoising, Xianhua Zeng, Wei Bian, Wei Liu, Jialie Shen, Dacheng Tao Nov 2015

Dictionary Pair Learning On Grassmann Manifolds For Image Denoising, Xianhua Zeng, Wei Bian, Wei Liu, Jialie Shen, Dacheng Tao

Research Collection School Of Computing and Information Systems

Image denoising is a fundamental problem in computer vision and image processing that holds considerable practical importance for real-world applications. The traditional patch-based and sparse coding-driven image denoising methods convert 2D image patches into 1D vectors for further processing. Thus, these methods inevitably break down the inherent 2D geometric structure of natural images. To overcome this limitation pertaining to the previous image denoising methods, we propose a 2D image denoising model, namely, the dictionary pair learning (DPL) model, and we design a corresponding algorithm called the DPL on the Grassmann-manifold (DPLG) algorithm. The DPLG algorithm first learns an initial dictionary …

Go to article

Deep Multimodal Learning For Affective Analysis And Retrieval, Lei Pang, Shiai Zhu, Chong-Wah Ngo Nov 2015

Deep Multimodal Learning For Affective Analysis And Retrieval, Lei Pang, Shiai Zhu, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Social media has been a convenient platform for voicing opinions through posting messages, ranging from tweeting a short text to uploading a media file, or any combination of messages. Understanding the perceived emotions inherently underlying these user-generated contents (UGC) could bring light to emerging applications such as advertising and media analytics. Existing research efforts on affective computation are mostly dedicated to single media, either text captions or visual content. Few attempts for combined analysis of multiple media are made, despite that emotion can be viewed as an expression of multimodal experience. In this paper, we explore the learning of highly …

Go to article

Direct Or Indirect Match? Selecting Right Concepts For Zero-Example Case, Yi-Jie Lu, Maaike De Boer, Hao Zhang, Klamer Schutte, Wessel Kraaij, Chong-Wah Ngo Nov 2015

Direct Or Indirect Match? Selecting Right Concepts For Zero-Example Case, Yi-Jie Lu, Maaike De Boer, Hao Zhang, Klamer Schutte, Wessel Kraaij, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

No abstract provided.

Go to article

Human Action Recognition In Unconstrained Videos By Explicit Motion Modeling, Yu-Gang Jiang, Qi Dai, Wei Liu, Xiangyang Xue, Chong-Wah Ngo Nov 2015

Human Action Recognition In Unconstrained Videos By Explicit Motion Modeling, Yu-Gang Jiang, Qi Dai, Wei Liu, Xiangyang Xue, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Human action recognition in unconstrained videos is a challenging problem with many applications. Most state-of-the-art approaches adopted the well-known bag-of-features representations, generated based on isolated local patches or patch trajectories, where motion patterns, such as object-object and object-background relationships are mostly discarded. In this paper, we propose a simple representation aiming at modeling these motion relationships. We adopt global and local reference points to explicitly characterize motion information, so that the final representation is more robust to camera movements, which widely exist in unconstrained videos. Our approach operates on the top of visual codewords generated on dense local patch trajectories, …

Go to article

Vireo-Tno @ Trecvid 2015: Multimedia Event Detection, Hao Zhang, Yi-Jie Lu, Maaike De Boer, Frank Ter Haar, Zhaofan Qiu, Klamer Schutte, Wessel Kraaij, Chong-Wah Ngo Nov 2015

Vireo-Tno @ Trecvid 2015: Multimedia Event Detection, Hao Zhang, Yi-Jie Lu, Maaike De Boer, Frank Ter Haar, Zhaofan Qiu, Klamer Schutte, Wessel Kraaij, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

This paper presents an overview and comparative analysis of our systems designed for the TRECVID 2015 [1] multimedia event detection (MED) task. We submitted 17 runs, of which 5 each for the zeroexample, 10-example and 100-example subtasks for the Pre-Specified (PS) event detection and 2 runs for the 10-example subtask for the Ad-Hoc (AH) event detection. We did not participate in the Interactive Run. This year we focus on three different parts of the MED task: 1) extending the size of our concept bank and combining it with improved dense trajectories; 2) exploring strategies for semantic query generation (SQG); and …

Go to article

Multimedia Event Detection: Strong By Integration, Hao Zhang, Maaike De Boer, Yi-Jie Lu, Klamer Schutte, Chong-Wah Ngo, Chong-Wah Ngo Nov 2015

Multimedia Event Detection: Strong By Integration, Hao Zhang, Maaike De Boer, Yi-Jie Lu, Klamer Schutte, Chong-Wah Ngo, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

No abstract provided.

Go to article

Face Recognition On Large-Scale Video In The Wild With Hybrid Euclidean-And-Riemannian Metric Learning, Zhiwu Huang, R. Wang, S. Shan, X Chen Oct 2015

Face Recognition On Large-Scale Video In The Wild With Hybrid Euclidean-And-Riemannian Metric Learning, Zhiwu Huang, R. Wang, S. Shan, X Chen

Research Collection School Of Computing and Information Systems

Face recognition on large-scale video in the wild is becoming increasingly important due to the ubiquity of video data captured by surveillance cameras, handheld devices, Internet uploads, and other sources. By treating each video as one image set, set-based methods recently have made great success in the field of video-based face recognition. In the wild world, videos often contain extremely complex data variations and thus pose a big challenge of set modeling for set-based methods. In this paper, we propose a novel Hybrid Euclidean-and-Riemannian Metric Learning (HERML) method to fuse multiple statistics of image set. Specifically, we represent each image …

Go to article

Applying Geocaching Principles To Site-Based Citizen Science And Eliciting Reactions Via A Technology Probe, Matthew A. Dunlap, Anthony Tang, Saul Greenberg Aug 2015

Applying Geocaching Principles To Site-Based Citizen Science And Eliciting Reactions Via A Technology Probe, Matthew A. Dunlap, Anthony Tang, Saul Greenberg

Research Collection School Of Computing and Information Systems

Site-based citizen science occurs when volunteers work with scientists to collect data at particular field locations. The benefit is greater data collection at lesser cost. Yet difficulties exist. We developed SCIENCECACHING, a prototype citizen science aid designed to mitigate four specific problems by applying aspects from another thriving location-based activity: geocaching as enabled by mobile devices. Specifically, to ease problems in data collection, SCIENCECACHING treats sites as geocaches: Volunteers find sites opportunistically via geocaching methods and use equipment and other materials pre-stored in cache containers. To ease problems in data validation, SCIENCECACHING flags outlier data as it is entered so …

Go to article

Effects Of The Use Of Points, Leaderboards And Badges On In-Game Purchases Of Virtual Goods, Fiona Fui-Hoon Nah, Lakshmi Sushma Daggubati, Amith Tarigonda, Raghu Vinay Nuvvula, Ofir Turel Aug 2015

Effects Of The Use Of Points, Leaderboards And Badges On In-Game Purchases Of Virtual Goods, Fiona Fui-Hoon Nah, Lakshmi Sushma Daggubati, Amith Tarigonda, Raghu Vinay Nuvvula, Ofir Turel

Research Collection School Of Computing and Information Systems

Game design elements are major factors in gamification. In this study, we seek to examine the impact of game design elements on users’ in-game purchases of virtual goods. The purchase of virtual goods due to players’ intrinsic motivation has been studied but little is known about the purchase of virtual goods due to the use of game design elements (i.e., Points, Leaderboards and Badges) built into the games. Extending our knowledge to this realm can help researchers to better understand gamers’ behaviors, and game designers and marketers to better promote and sell virtual goods in online games.

Go to article

Creating Greater Synergy Between Hci Academia And Practice, Fiona Fui-Hoon Nah, Dennis Galletta, Melinda Knight, James R. Lewis, John Pruitt, Gavriel Salvendy, Hong Sheng, Anna Wichansky Aug 2015

Creating Greater Synergy Between Hci Academia And Practice, Fiona Fui-Hoon Nah, Dennis Galletta, Melinda Knight, James R. Lewis, John Pruitt, Gavriel Salvendy, Hong Sheng, Anna Wichansky

Research Collection School Of Computing and Information Systems

This paper presents perspectives from both academia and practice on how both groups can collaborate and work together to create synergy in the development and advancement of human-computer interaction (HCI). Issues and challenges are highlighted, success cases are offered as examples, and suggestions are provided to further such collaborations.

Go to article

Topological Spatial Verification For Instance Search, Wei Zhang, Chong-Wah Ngo Aug 2015

Topological Spatial Verification For Instance Search, Wei Zhang, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

This paper proposes an elastic spatial verification method for Instance Search, particularly for dealing with non-planar and non-rigid queries exhibiting complex spatial transformations. Different from existing models that map keypoints between images based on a linear transformation (e.g., affine, homography), our model exploits the topological arrangement of keypoints to address the non-linear spatial transformations that are extremely common in real life situations. In particular, we propose a novel technique to elastically verify the topological spatial consistency with the triangulated graph through a "sketch-and-match" scheme. The spatial topology configuration, emphasizing relative positioning rather than absolute coordinates, is first sketched by a …

Go to article

Semi-Supervised Hashing With Semantic Confidence For Large Scale Visual Search, Yingwei Pan, Ting Yao, Houqiang Li, Chong-Wah Ngo, Tao Mei Aug 2015

Semi-Supervised Hashing With Semantic Confidence For Large Scale Visual Search, Yingwei Pan, Ting Yao, Houqiang Li, Chong-Wah Ngo, Tao Mei

Research Collection School Of Computing and Information Systems

Similarity search is one of the fundamental problems for large scale multimedia applications. Hashing techniques, as one popular strategy, have been intensively investigated owing to the speed and memory efficiency. Recent research has shown that leveraging supervised information can lead to high quality hashing. However, most existing supervised methods learn hashing function by treating each training example equally while ignoring the different semantic degree related to the label, i.e. semantic confidence, of different examples. In this paper, we propose a novel semi-supervised hashing framework by leveraging semantic confidence. Specifically, a confidence factor is first assigned to each example by neighbor …

Go to article

On Multipath Link Characterization And Adaptation For Device-Free Human Detection, Zimu Zhou, Zheng Yang, Chenshu Wu, Yunhao Liu, Lionel M. Ni Jul 2015

On Multipath Link Characterization And Adaptation For Device-Free Human Detection, Zimu Zhou, Zheng Yang, Chenshu Wu, Yunhao Liu, Lionel M. Ni

Research Collection School Of Computing and Information Systems

No abstract provided.

Go to article

Log-Euclidean Metric Learning On Symmetric Positive Definite Manifold With Application To Image Set Classification, Zhiwu Huang, R. Wang, S. Shan, X. Li, X. Chen Jul 2015

Log-Euclidean Metric Learning On Symmetric Positive Definite Manifold With Application To Image Set Classification, Zhiwu Huang, R. Wang, S. Shan, X. Li, X. Chen

Research Collection School Of Computing and Information Systems

The manifold of Symmetric Positive Definite (SPD) matrices has been successfully used for data representation in image set classification. By endowing the SPD manifold with Log-Euclidean Metric, existing methods typically work on vector-forms of SPD matrix logarithms. This however not only inevitably distorts the geometrical structure of the space of SPD matrix logarithms but also brings low efficiency especially when the dimensionality of SPD matrix is high. To overcome this limitation, we propose a novel metric learning approach to work directly on logarithms of SPD matrices. Specifically, our method aims to learn a tangent map that can directly transform the …

Go to article

Projection Metric Learning On Grassmann Manifold With Application To Video Based Face Recognition, Zhiwu Huang, R. Wang, S. Shan, X. Chen Jun 2015

Projection Metric Learning On Grassmann Manifold With Application To Video Based Face Recognition, Zhiwu Huang, R. Wang, S. Shan, X. Chen

Research Collection School Of Computing and Information Systems

In video based face recognition, great success has been made by representing videos as linear subspaces, which typically lie in a special type of non-Euclidean space known as Grassmann manifold. To leverage the kernel-based methods developed for Euclidean space, several recent methods have been proposed to embed the Grassmann manifold into a high dimensional Hilbert space by exploiting the well established Project Metric, which can approximate the Riemannian geometry of Grassmann manifold. Nevertheless, they inevitably introduce the drawbacks from traditional kernel-based methods such as implicit map and high computational cost to the Grassmann manifold. To overcome such limitations, we propose …

Go to article

Face Video Retrieval With Image Query Via Hashing Across Euclidean Space And Riemannian Manifold, Y. Li, R. Wang, Zhiwu Huang, S. Shan, X. Chen Jun 2015

Face Video Retrieval With Image Query Via Hashing Across Euclidean Space And Riemannian Manifold, Y. Li, R. Wang, Zhiwu Huang, S. Shan, X. Chen

Research Collection School Of Computing and Information Systems

Retrieving videos of a specific person given his/her face image as query becomes more and more appealing for applications like smart movie fast-forwards and suspect searching. It also forms an interesting but challenging computer vision task, as the visual data to match, i.e., still image and video clip are usually represented quite differently. Typically, face image is represented as point (i.e., vector) in Euclidean space, while video clip is seemingly modeled as a point (e.g., covariance matrix) on some particular Riemannian manifold in the light of its recent promising success. It thus incurs a new hashing-based retrieval problem of matching …

Go to article

Online Multimodal Co-Indexing And Retrieval Of Weakly Labeled Web Image Collections, Lei Meng, Ah-Hwee Tan, Cyril Leung, Liqiang Nie, Tan-Seng Chua, Chunyan Miao Jun 2015

Online Multimodal Co-Indexing And Retrieval Of Weakly Labeled Web Image Collections, Lei Meng, Ah-Hwee Tan, Cyril Leung, Liqiang Nie, Tan-Seng Chua, Chunyan Miao

Research Collection School Of Computing and Information Systems

Weak supervisory information of web images, such as captions, tags, and descriptions, make it possible to better understand images at the semantic level. In this paper, we propose a novel online multimodal co-indexing algorithm based on Adaptive Resonance Theory, named OMC-ART, for the automatic co-indexing and retrieval of images using their multimodal information. Compared with existing studies, OMC-ART has several distinct characteristics. First, OMCART is able to perform online learning of sequential data. Second, OMC-ART builds a two-layer indexing structure, in which the first layer co-indexes the images by the key visual and textual features based on the generalized distributions …

Go to article

Unsupervised Celebrity Face Naming In Web Videos, Lei Pang, Chong-Wah Ngo Jun 2015

Unsupervised Celebrity Face Naming In Web Videos, Lei Pang, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

This paper investigates the problem of celebrity face naming in unconstrained videos with user-provided metadata. Instead of relying on accurate face labels for supervised learning, a rich set of relationships automatically derived from video content and knowledge from image domain and social cues is leveraged for unsupervised face labeling. The relationships refer to the appearances of faces under different spatio-temporal contexts and their visual similarities. The knowledge includes Web images weakly tagged with celebrity names and the celebrity social networks. The relationships and knowledge are elegantly encoded using conditional random field (CRF) for label inference. Two versions of face annotation …

Go to article

First Prev Next Last