Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Design (3)
- DNN image representation (2)
- Image search (2)
- Subspace learning (2)
- Visualization (2)
-
- 3D navigation (1)
- Algorithms (1)
- Art making (1)
- Art therapy (1)
- Assembling (1)
- Background elimination (1)
- Binary quadratic programming (1)
- Celebrity annotation (1)
- Click-through data (1)
- Clickthrough data (1)
- Clustering (1)
- Collaboration (1)
- Collaborative systems (1)
- Concept detection (1)
- Construction (1)
- Constructionism (1)
- Constructivism (1)
- Controllers (1)
- Cross-view learning (1)
- Education (1)
- Emotion recognition; EmotiW 2014 challenge; Multiple kernels; Riemannian manifold (1)
- Error propagation (1)
- Euclidean-to-Riemannian metric learning; point-to-set classification (1)
- Event extraction (1)
- Experimentation (1)
Articles 1 - 27 of 27
Full-Text Articles in Physical Sciences and Mathematics
Scalable Visual Instance Mining With Threads Of Features, Wei Zhang, Hongzhi Li, Chong-Wah Ngo, Shih-Fu Chang
Scalable Visual Instance Mining With Threads Of Features, Wei Zhang, Hongzhi Li, Chong-Wah Ngo, Shih-Fu Chang
Research Collection School Of Computing and Information Systems
We address the problem of visual instance mining, which is to extract frequently appearing visual instances automatically from a multimedia collection. We propose a scalable mining method by exploiting Thread of Features (ToF). Specifically, ToF, a compact representation that links consistent features across images, is extracted to reduce noises, discover patterns, and speed up processing. Various instances, especially small ones, can be discovered by exploiting correlated ToFs. Our approach is significantly more effective than other methods in mining small instances. At the same time, it is also more efficient by requiring much fewer hash tables. We compared with several state-of-the-art …
Click-Through-Based Subspace Learning For Image Search, Yingwei Pan, Ting Yao, Xinmei Tian, Houqiang Li, Chong-Wah Ngo
Click-Through-Based Subspace Learning For Image Search, Yingwei Pan, Ting Yao, Xinmei Tian, Houqiang Li, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
One of the fundamental problems in image search is to rank image documents according to a given textual query. We address two limitations of the existing image search engines in this paper. First, there is no straightforward way of comparing textual keywords with visual image content. Image search engines therefore highly depend on the surrounding texts, which are often noisy or too few to accurately describe the image content. Second, ranking functions are trained on query-image pairs labeled by human labelers, making the annotation intellectually expensive and thus cannot be scaled up. We demonstrate that the above two fundamental challenges …
Combining Multiple Kernel Methods On Riemannian Manifold For Emotion Recognition In The Wild, M. Liu, R. Wang, S. Li, S. Shan, Zhiwu Huang, X. Chen
Combining Multiple Kernel Methods On Riemannian Manifold For Emotion Recognition In The Wild, M. Liu, R. Wang, S. Li, S. Shan, Zhiwu Huang, X. Chen
Research Collection School Of Computing and Information Systems
In this paper, we present the method for our submission to the Emotion Recognition in the Wild Challenge (EmotiW 2014). The challenge is to automatically classify the emotions acted by human subjects in video clips under realworld environment. In our method, each video clip can be represented by three types of image set models (i.e. linear subspace, covariance matrix, and Gaussian distribution) respectively, which can all be viewed as points residing on some Riemannian manifolds. Then different Riemannian kernels are employed on these set models correspondingly for similarity/distance measurement. For classification, three types of classifiers, i.e. kernel SVM, logistic regression, …
Hybrid Euclidean-And-Riemannian Metric Learning For Image Set Classification, Zhiwu Huang, R. Wang, S. Shan, X. Chen
Hybrid Euclidean-And-Riemannian Metric Learning For Image Set Classification, Zhiwu Huang, R. Wang, S. Shan, X. Chen
Research Collection School Of Computing and Information Systems
We propose a novel hybrid metric learning approach to combine multiple heterogenous statistics for robust image set classification. Specifically, we represent each set with multiple statistics – mean, covariance matrix and Gaussian distribution, which generally complement each other for set modeling. However, it is not trivial to fuse them since the mean vector with dd-dimension often lies in Euclidean space RdRd, whereas the covariance matrix typically resides on Riemannian manifold Sym+dSymd+. Besides, according to information geometry, the space of Gaussian distribution can be embedded into another Riemannian manifold Sym+d+1Symd+1+. To fuse these statistics from heterogeneous spaces, we propose a Hybrid …
Imagespirit: Verbal Guided Image Parsing, Ming-Ming Cheng, Shuai Zheng, Wen-Yan Lin, Vibhav Vineet, Paul Sturgess, Nigel Crook, Niloy J. Mitra, Philip Torr
Imagespirit: Verbal Guided Image Parsing, Ming-Ming Cheng, Shuai Zheng, Wen-Yan Lin, Vibhav Vineet, Paul Sturgess, Nigel Crook, Niloy J. Mitra, Philip Torr
Research Collection School Of Computing and Information Systems
Humans describe images in terms of nouns and adjectives while algorithms operate on images represented as sets of pixels. Bridging this gap between how humans would like to access images versus their typical representation is the goal of image parsing, which involves assigning object and attribute labels to pixels. In this article we propose treating nouns as object labels and adjectives as visual attribute labels. This allows us to formulate the image parsing problem as one of jointly estimating per-pixel object and attribute labels from a set of training images. We propose an efficient (interactive time) solution. Using the extracted …
Vireo-Tno @ Trecvid 2014: Multimedia Event Detection And Recounting (Med And Mer), Chong-Wah Ngo, Yi-Jie Lu, Hao Zhang, Ting Yao, Chun-Chet Tan, Lei Pang, Maaike De Boer, John Schavemaker, Klamer Schutte, Wessel Kraaij
Vireo-Tno @ Trecvid 2014: Multimedia Event Detection And Recounting (Med And Mer), Chong-Wah Ngo, Yi-Jie Lu, Hao Zhang, Ting Yao, Chun-Chet Tan, Lei Pang, Maaike De Boer, John Schavemaker, Klamer Schutte, Wessel Kraaij
Research Collection School Of Computing and Information Systems
This paper presents an overview and comparative analysis of our systems designed for TRECVID 2014 [1] multimedia event detection (MED) and recounting (MER) tasks, including all sub-tasks for Pre-Specified (PS) event detection, all sub-tasks except 100Ex for Ad-Hoc (AH) event detection, and 010Ex sub-task for both PS and AH event recounting. Multimedia Event Detection (MED) : Our main focus for the MED task is on the study of a new zero-example system, which aims to solve the 000Ex and SQ problems. The system can run either fully automatically or semi-automatically. Specifically, we test the automatic run in 000Ex submission and …
Celelabel: An Interactive System For Annotating Celebrities In Web Videos, Zhineng Chen, Jinfeng Bai, Chong-Wah Ngo, Bailan Feng, Bo Xu
Celelabel: An Interactive System For Annotating Celebrities In Web Videos, Zhineng Chen, Jinfeng Bai, Chong-Wah Ngo, Bailan Feng, Bo Xu
Research Collection School Of Computing and Information Systems
Manual annotation of celebrities in Web videos is an essential task in many people-related Web services. The task, however, poses a significant challenge even to skillful annotators, mainly due to the large quantity of unfamiliar and greatly varied celebrities, and the lack of a customized system for it. This work develops CeleLabel, an interactive system for manually annotating celebrities in the Web video domain. The peculiarity of CeleLabel is to exploit and display multiple types of information that could assist the annotation, including video content, context surrounding and within a video, celebrity images on the Web, and human factors. Using …
Organizing Video Search Results To Adapted Semantic Hierarchies For Topic-Based Browsing, Jiajun Wang, Yu-Gang Jiang, Qiang Wang, Kuiyuan Yang, Chong-Wah Ngo
Organizing Video Search Results To Adapted Semantic Hierarchies For Topic-Based Browsing, Jiajun Wang, Yu-Gang Jiang, Qiang Wang, Kuiyuan Yang, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
Organizing video search results into semantically structured hierarchies can greatly improve the efficiency of browsing complex query topics. Traditional hierarchical clustering techniques are inadequate since they lack the ability to generate semantically interpretable structures. In this paper, we introduce an approach to organize video search results to an adapted semantic hierarchy. As many hot search topics such as celebrities and famous cities have Wikipedia pages where hierarchical topic structures are available, we start from the Wikipedia hierarchies and adjust the structures according to the characteristics of the returned videos from a search engine. Ordinary clustering based on textual information of …
Vireo @ Trecvid 2014: Instance Search And Semantic Indexing, Wei Zhang, Hao Zhang, Ting Yao, Yijie Lu, Jingjing Chen, Chong-Wah Ngo
Vireo @ Trecvid 2014: Instance Search And Semantic Indexing, Wei Zhang, Hao Zhang, Ting Yao, Yijie Lu, Jingjing Chen, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
This paper summarizes the following two tasks participated by VIREO group: instance search and semantic indexing. We will present our approaches and analyze the results obtained in TRECVID 2014 benchmark evaluation
Designing An Immersive And Entertaining Pervasive Gameplay Experience With Spheros As Game And Interface Elements, Brennan Jones, Kody Dillman, Setareh Aghel Manesh, Ehud Sharlin, Anthony Tang
Designing An Immersive And Entertaining Pervasive Gameplay Experience With Spheros As Game And Interface Elements, Brennan Jones, Kody Dillman, Setareh Aghel Manesh, Ehud Sharlin, Anthony Tang
Research Collection School Of Computing and Information Systems
The Sphero is a robotic remote-controlled ball capable of rolling around on its own in any direction at multiple speeds. Numerous games have been designed for the Sphero for smartphones and tablets. However, most of these games provide an interface for controlling the Sphero that is far from natural. These games also do not put a strong focus on the physical environment around the Sphero. This work discusses a control scheme used to control a Sphero with another Sphero, and a pervasive game leveraging this scheme that emphasizes physical properties of the environment to create an immersive experience.
Saliency Detection With Flash And No-Flash Image Pairs, Shengfeng He, Rynson W.H. Lau
Saliency Detection With Flash And No-Flash Image Pairs, Shengfeng He, Rynson W.H. Lau
Research Collection School Of Computing and Information Systems
In this paper, we propose a new saliency detection method using a pair of flash and no-flash images. Our approach is inspired by two observations. First, only the foreground objects are significantly brightened by the flash as they are relatively nearer to the camera than the background. Second, the brightness variations introduced by the flash provide hints to surface orientation changes. Accordingly, the first observation is explored to form the background prior to eliminate background distraction. The second observation provides a new orientation cue to compute surface orientation contrast. These photometric cues from the two observations are independent of visual …
Name-Face Association In Web Videos: A Large-Scale Dataset, Baselines, And Open Issues, Zhi-Neng Chen, Chong-Wah Ngo, Wei Zhang, Juan Cao, Yu-Gang Jiang
Name-Face Association In Web Videos: A Large-Scale Dataset, Baselines, And Open Issues, Zhi-Neng Chen, Chong-Wah Ngo, Wei Zhang, Juan Cao, Yu-Gang Jiang
Research Collection School Of Computing and Information Systems
Associating faces appearing in Web videos with names presented in the surrounding context is an important task in many applications. However, the problem is not well investigated particularly under large-scale realistic scenario, mainly due to the scarcity of dataset constructed in such circumstance. In this paper, we introduce a Web video dataset of celebrities, named WebV-Cele, for name-face association. The dataset consists of 75 073 Internet videos of over 4 000 hours, covering 2 427 celebrities and 649 001 faces. This is, to our knowledge, the most comprehensive dataset for this problem. We describe the details of dataset construction, discuss …
Video Event Detection Using Motion Relativity And Feature Selection, Feng Wang, Zhanhu Sun, Yu-Gang Jiang, Chong-Wah Ngo
Video Event Detection Using Motion Relativity And Feature Selection, Feng Wang, Zhanhu Sun, Yu-Gang Jiang, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
Event detection plays an essential role in video content analysis. In this paper, we present our approach based on motion relativity and feature selection for video event detection. First, we propose a new motion feature, namely Expanded Relative Motion Histogram of Bag-of-Visual-Words (ERMH-BoW) to employ motion relativity for event detection. In ERMH-BoW, by representing what aspect of an event with Bag-of-Visual-Words (BoW), we construct relative motion histograms between different visual words to depict the objects' activities or how aspect of the event. ERMH-BoW thus integrates both what and how aspects for a complete event description. Meanwhile, we show that by …
Collaborative Error Reduction For Hierarchical Classification, Shiai Zhu, Xiao-Yong Wei, Chong-Wah Ngo
Collaborative Error Reduction For 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. The conventional method always selects the branch with the highest classification response. This branch selection strategy has a risk of propagating classification errors from higher levels of the hierarchy to the lower levels. We argue that the local strategy is too arbitrary, because the candidate nodes are considered individually, which ignores the semantic and context relationships among concepts. In this paper, we first propose a novel method for HC, which is able to utilize the semantic relationship among candidate nodes and their children …
Click-Through-Based Cross-View Learning For Image Search, Yingwei Pan, Ting Yao, Tao Mei, Houqiang Li, Chong-Wah Ngo, Yong Rui
Click-Through-Based Cross-View Learning For Image Search, Yingwei Pan, Ting Yao, Tao Mei, Houqiang Li, Chong-Wah Ngo, Yong Rui
Research Collection School Of Computing and Information Systems
One of the fundamental problems in image search is to rank image documents according to a given textual query. Existing search engines highly depend on surrounding texts for ranking images, or leverage the query-image pairs annotated by human labelers to train a series of ranking functions. However, there are two major limitations: 1) the surrounding texts are often noisy or too few to accurately describe the image content, and 2) the human annotations are resourcefully expensive and thus cannot be scaled up. We demonstrate in this paper that the above two fundamental challenges can be mitigated by jointly exploring the …
Daisy Filter Flow: A Generalized Discrete Approach To Dense Correspondences, Hongsheng Yang, Wen-Yan Lin, Jiangbo Lu
Daisy Filter Flow: A Generalized Discrete Approach To Dense Correspondences, Hongsheng Yang, Wen-Yan Lin, Jiangbo Lu
Research Collection School Of Computing and Information Systems
No abstract provided.
Placing Videos On A Semantic Hierarchy For Search Result Navigation, Song Tan, Yu-Gang Jiang, Chong-Wah Ngo
Placing Videos On A Semantic Hierarchy For Search Result Navigation, Song Tan, Yu-Gang Jiang, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
Organizing video search results in a list view is widely adopted by current commercial search engines, which cannot support efficient browsing for complex search topics that have multiple semantic facets. In this article, we propose to organize video search results in a highly structured way. Specifically, videos are placed on a semantic hierarchy that accurately organizes various facets of a given search topic. To pick the most suitable videos for each node of the hierarchy, we define and utilize three important criteria: relevance, uniqueness, and diversity. Extensive evaluations on a large YouTube video dataset demonstrate the effectiveness of our approach.
Constructive Visualization, Samuel Huron, Sheelagh Carpendale, Alice Thudt, Anthony Tang, Michael Mauerer
Constructive Visualization, Samuel Huron, Sheelagh Carpendale, Alice Thudt, Anthony Tang, Michael Mauerer
Research Collection School Of Computing and Information Systems
If visualization is to be democratized, we need to provide means for non-experts to create visualizations that allow them to engage directly with datasets. We present constructive visualization a new paradigm for the simple creation of flexible, dynamic visualizations. Constructive visualization is simple—in that the skills required to build and manipulate the visualizations are akin to kindergarten play; it is expressive— in that one can build within the constraints of the chosen environment, and it also supports dynamics — in that these constructed visualizations can be rebuilt and adjusted. We describe the conceptual components and processes underlying constructive visualization, and …
Interactive Two-Sided Transparent Displays: Designing For Collaboration, Jiannan Li, Saul Greenberg, Ehud Sharlin, Joaquim Jorge
Interactive Two-Sided Transparent Displays: Designing For Collaboration, Jiannan Li, Saul Greenberg, Ehud Sharlin, Joaquim Jorge
Research Collection School Of Computing and Information Systems
Transparent displays can serve as an important collaborative medium supporting face-to-face interactions over a shared visual work surface. Such displays enhance workspace awareness: when a person is working on one side of a transparent display, the person on the other side can see the other's body, hand gestures, gaze and what he or she is actually manipulating on the shared screen. Even so, we argue that designing such transparent displays must go beyond current offerings if it is to support collaboration. First, both sides of the display must accept interactive input, preferably by at least touch and / or pen, …
Learning Euclidean-To-Riemannian Metric For Point-To-Set Classification, Zhiwu Huang, R. Wang, S. Shan, X. Chen
Learning Euclidean-To-Riemannian Metric For Point-To-Set Classification, Zhiwu Huang, R. Wang, S. Shan, X. Chen
Research Collection School Of Computing and Information Systems
In this paper, we focus on the problem of point-to-set classification, where single points are matched against sets of correlated points. Since the points commonly lie in Euclidean space while the sets are typically modeled as elements on Riemannian manifold, they can be treated as Euclidean points and Riemannian points respectively. To learn a metric between the heterogeneous points, we propose a novel Euclidean-to-Riemannian metric learning framework. Specifically, by exploiting typical Riemannian metrics, the Riemannian manifold is first embedded into a high dimensional Hilbert space to reduce the gaps between the heterogeneous spaces and meanwhile respect the Riemannian geometry of …
Exploring Video Streaming In Public Settings: Shared Geocaching Over Distance Using Mobile Video Chat, Jason Procyk, Carman Neustaedter, Carolyn Pang, Anthony Tang, Tejinder K. Judge
Exploring Video Streaming In Public Settings: Shared Geocaching Over Distance Using Mobile Video Chat, Jason Procyk, Carman Neustaedter, Carolyn Pang, Anthony Tang, Tejinder K. Judge
Research Collection School Of Computing and Information Systems
Our research explores the use of mobile video chat in public spaces by people participating in parallel experiences, where both a local and remote person are doing the same activity together at the same time. We prototyped a wearable video chat experience and had pairs of friends and family members participate in 'shared geocaching' over distance. Our results show that video streaming works best for navigation tasks but is more challenging to use for fine-grained searching tasks. Video streaming also creates a very intimate experience with a remote partner, but this can lead to distraction from the 'real world' and …
One Space: Shared Visual Scenes For Active Free Play, Maayan Cohen, Kody Dillman, Haley Macleod, Seth Hunter, Anthony Tang
One Space: Shared Visual Scenes For Active Free Play, Maayan Cohen, Kody Dillman, Haley Macleod, Seth Hunter, Anthony Tang
Research Collection School Of Computing and Information Systems
Children engage in free play for emotional, physical and social development; researchers have explored supporting free play between physically remote playmates using videoconferencing tools. We show that the configuration of the video conferencing setup affects play. Specifically, we show that a shared visual scene configuration promotes fundamentally active forms of engaged, co-operative play.
Medical Imaging Specialists And 3d: A Domain Perspective On Mobile 3d Interactions, Teddy Seyed, Frank Maurer, Francisco Marinho Rodrigues, Anthony Tang
Medical Imaging Specialists And 3d: A Domain Perspective On Mobile 3d Interactions, Teddy Seyed, Frank Maurer, Francisco Marinho Rodrigues, Anthony Tang
Research Collection School Of Computing and Information Systems
3D volumetric medical images, such as MRIs, are commonly explored and interacted with by medical imaging experts using systems that require keyboard and mouse-based techniques. These techniques have presented challenges for medical imaging specialists: 3D spatial navigation is difficult, in addition to the detailed selection and analysis of 3D medical images being difficult due to depth perception and occlusion issues. In this work, we explore a potential solution to these challenges by using tangible interaction techniques with a mobile device to simplify 3D interactions for medical imaging specialists. We discuss preliminary observations from our design sessions with medical imaging specialists …
Supporting Non-Verbal Visual Communication In Online Group Art Therapy, Brennan Jones, Kate Collie, Sara Prins Hankinson, Anthony Tang
Supporting Non-Verbal Visual Communication In Online Group Art Therapy, Brennan Jones, Kate Collie, Sara Prins Hankinson, Anthony Tang
Research Collection School Of Computing and Information Systems
Art therapy provides therapeutic benefit to people suffering from chronic pain, and recent work has explored supporting art therapy through online tools such as chat forums and discussion boards. These tools give people the benefit of engaging in art therapy without the burden of having to leave one’s home (when transportation may be a challenge), and allowing people to reveal their identities through dialogue and activity rather than through one’s appearance. However, these tools also do not provide much opportunity for collaboration and shared art making. Because group members are not aware of each other’s actions and non-verbal cues in …
Celebrowser: An Example Of Browsing Big Data On Small Device, Song Tan, Chong-Wah Ngo, Jun Xu, Yong Rui
Celebrowser: An Example Of Browsing Big Data On Small Device, Song Tan, Chong-Wah Ngo, Jun Xu, Yong Rui
Research Collection School Of Computing and Information Systems
In this demonstration, we demonstrate a mobile-based celebrity video browsing system called CeleBrowser. Using this system, users can interactively switch among four views: people-centric, timeline-centric, month-centric and topic-centric, for browsing celebrity-related hot videos. A peculiarity of the demonstration is to highlight the advantage of multiperspective information organization and presentation in engaging users for exploratory browsing of large number of Web videos on a device with small screen. Technology-wise the demonstration shows how query logs collected for six months from two vertical search engines are leveraged for mining hot events and videos of celebrities.
Visual Typo Correction By Collocative Optimization: A Case Study On Merchandize Images, Xiao-Yong Wei, Zhen-Qun Yang, Chong-Wah Ngo, Wei Zhang
Visual Typo Correction By Collocative Optimization: A Case Study On Merchandize Images, Xiao-Yong Wei, Zhen-Qun Yang, Chong-Wah Ngo, Wei Zhang
Research Collection School Of Computing and Information Systems
Near-duplicate retrieval (NDR) in merchandize images is of great importance to a lot of online applications on e-Commerce websites. In those applications where the requirement of response time is critical, however, the conventional techniques developed for a general purpose NDR are limited, because expensive post-processing like spatial verification or hashing is usually employed to compromise the quantization errors among the visual words used for the images. In this paper, we argue that most of the errors are introduced because of the quantization process where the visual words are considered individually, which has ignored the contextual relations among words. We propose …
Sketch: Pen And Touch Recognition [Workshop Summary], Richard C. Davis, Aaron Adler
Sketch: Pen And Touch Recognition [Workshop Summary], Richard C. Davis, Aaron Adler
Research Collection School Of Computing and Information Systems
Sketch recognition has technically been around for 40 years, but it has come and gone several times due to the difficulty of the problem. With the rise of touch and pen enabled phones and tablets, sketch recognition is regaining popularity and public presence, and more people are becoming aware of and interested in this difficult, but valuable, problem. It is important to harness the Sketch Recognition community at this time to encourage the flourishing of this topic.