Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Graphics and Human Computer Interfaces
Research Collection School Of Computing and Information Systems
- Keyword
-
- Click-through data (2)
- Image search (2)
- Annotation (1)
- Belief propagation (1)
- Chronic disease management (1)
-
- Circular reranking (1)
- Click-boosting (1)
- Community (1)
- Computer vision (1)
- Concept detection (1)
- Context modeling (1)
- Curve fitting (1)
- Deep neural networks (1)
- Distributed tabletops (1)
- Domain transfer (1)
- Embodiments (1)
- Emotion recognition; emotiw 2013 challenge; grassmannian manifolds; partial least squares regression (1)
- Entity search (1)
- Error propagation (1)
- Flip invariant scale-invariant feature transform (SIFT) (1)
- Friend suggestion (1)
- Geocaching (1)
- Geometric verification (1)
- Gestures (1)
- Global positioning system (GPS) (1)
- Healthcare (1)
- Image abstraction; object of interest segmentation; salient object detection; visual attention (1)
- Image matching (1)
- Image motion analysis (1)
- Image registration (1)
Articles 1 - 24 of 24
Full-Text Articles in Physical Sciences and Mathematics
Dense Image Correspondence Under Large Appearance Variations, Linlin Liu, Kok-Lim Low, Wen-Yan Lin
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 …
Partial Least Squares Regression On Grassmannian Manifold For Emotion Recognition, M. Liu, R. Wang, Zhiwu Huang, S. Shan, X. Chen
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 …
Search Of Small Objects By Topology Matching, Context Modeling, And Pattern Mining, Wei Zhang, Chong-Wah Ngo
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
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
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
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-theart 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 …
Error Recovered Hierarchical Classification, Shiai Zhu, Xiao-Yong Wei, Chong-Wah Ngo
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 …
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
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
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 …
The Vireo Team At Mediaeval 2013: Violent Scenes Detection By Mid-Level Concepts Learnt From Youtube, Chun Chet Tan, Chong-Wah Ngo
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 …
Click-Boosting Random Walk For Image Search Reranking, Xiaopeng Yang, Yongdong Zhang, Ting Yao, Zheng-Jun Zha, Chong-Wah Ngo
Click-Boosting Random Walk For Image Search Reranking, Xiaopeng Yang, Yongdong Zhang, Ting Yao, Zheng-Jun Zha, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
Image reranking is an effective way for improving the retrieval performance of keyword-based image search engines. A fundamental issue underlying the success of existing image reranking approaches is the ability in identifying potentially useful recurrent patterns or relevant training examples from the initial search results. Ideally, these patterns and examples can be leveraged to upgrade the ranks of visually similar images, which are also likely to be relevant. The challenge, nevertheless, originates from the fact that keyword-based queries are used to be ambiguous, resulting in difficulty in predicting the search intention. Mining useful patterns and examples without understanding query is …
Video Concept Detection By Learning From Web Images: A Case Study On Cross Domain Learning, Shiai Zhu, Ting Yao, Chong-Wah Ngo
Video Concept Detection By Learning From Web Images: A Case Study On Cross Domain Learning, Shiai Zhu, Ting Yao, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
Concept detection is probably the most important research problem in the area of multimedia. The need to model with sufficient and diverse training instances, however, makes the task computationally and resourcefully expensive. Meanwhile, the popularity of social media has generated massive amount of weakly tagged images which could be leveraged for concept model learning. Therefore, in this paper, we consider exploring weakly taggedWeb images to shed some light on video concept detection. Particularly, two sets of Web images downloaded from Flickr are utilized as training data for concept detection on two real-world large-scale video datasets released by TRECVID. Our experiments …
Unified Entity Search In Social Media Community, Ting Yao, Yuan Liu, Chong-Wah Ngo, Tao Mei
Unified Entity Search In Social Media Community, Ting Yao, Yuan Liu, Chong-Wah Ngo, Tao Mei
Research Collection School Of Computing and Information Systems
The search for entities is the most common search behavior on the Web, especially in social media communities where entities (such as images, videos, people, locations, and tags) are highly heterogeneous and correlated. While previous research usually deals with these social media entities separately, we are investigating in this paper a unified, multilevel, and correlative entity graph to represent the unstructured social media data, through which various applications (e.g., friend suggestion, personalized image search, image tagging, etc.) can be realized more effectively in one single framework. We regard the social media objects equally as “entities” and all of these applications …
Personal Informatics In Chronic Illness Management, Haley Macleod, Anthony Tang, Sheelagh Carpendale
Personal Informatics In Chronic Illness Management, Haley Macleod, Anthony Tang, Sheelagh Carpendale
Research Collection School Of Computing and Information Systems
Many people with chronic illness suffer from debilitating symptoms or episodes that inhibit normal day-to-day function. Pervasive tools offer the possibility to help manage these conditions, particularly by helping people understand their conditions. But, it is unclear how to design these tools, as prior designs have focused on effortful tracking and many see those tools as a burden to use. We report here on an interview study with 12 individuals with chronic illnesses who collect personal data. We learn that these people are motivated through self-discovery and curiosity. We explore how these concepts may support the design of tools that …
An Architecture For Online Semantic Labeling On Ugvs, Arne Suppe, Luis Navarro-Serment, Daniel Munoz, Drew Bagnell, Martial Hebert
An Architecture For Online Semantic Labeling On Ugvs, Arne Suppe, Luis Navarro-Serment, Daniel Munoz, Drew Bagnell, Martial Hebert
Research Collection School Of Computing and Information Systems
We describe an architecture to provide online semantic labeling capabilities to field robots operating in urban environments. At the core of our system is the stacked hierarchical classifier developed by Munoz et al.,1 which classifies regions in monocular color images using models derived from hand labeled training data. The classifier is trained to identify buildings, several kinds of hard surfaces, grass, trees, and sky. When taking this algorithm into the real world, practical concerns with difficult and varying lighting conditions require careful control of the imaging process. First, camera exposure is controlled by software, examining all of the image’s pixels, …
Searching Visual Instances With Topology Checking And Context Modeling, Wei Zhang, Chong-Wah Ngo
Searching Visual Instances With Topology Checking And Context Modeling, Wei Zhang, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
Instance Search (INS) is a realistic problem initiated by TRECVID, which is to retrieve all occurrences of the querying object, location, or person from a large video collection. It is a fundamental problem with many applications, and also a challenging problem different from the traditional concept or near-duplicate (ND) search, since the relevancy is defined at instance level. True responses could exhibit various visual variations, such as being small on the image with different background, or showing a non-homography spatial configuration. Based on the Bag-of-Words model, we propose two techniques tailored for Instance Search. Specifically, we explore the use of …
Circular Reranking For Visual Search, Ting Yao, Chong-Wah Ngo
Circular Reranking For Visual Search, Ting Yao, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
Search reranking is regarded as a common way to boost retrieval precision. The problem nevertheless is not trivial especially when there are multiple features or modalities to be considered for search, which often happens in image and video retrieval. This paper proposes a new reranking algorithm, named circular reranking, that reinforces the mutual exchange of information across multiple modalities for improving search performance, following the philosophy that strong performing modality could learn from weaker ones, while weak modality does benefit from interacting with stronger ones. Technically, circular reranking conducts multiple runs of random walks through exchanging the ranking scores among …
Data Visualization On Interactive Surfaces: A Research Agenda, Petra Isenberg, Tobias Isenberg, Tobias Hesselmann, Bongshin Lee, Ulrich Von Zadow, Anthony Tang
Data Visualization On Interactive Surfaces: A Research Agenda, Petra Isenberg, Tobias Isenberg, Tobias Hesselmann, Bongshin Lee, Ulrich Von Zadow, Anthony Tang
Research Collection School Of Computing and Information Systems
Interactive tabletops and surfaces (ITSs) provide rich opportunities for data visualization and analysis and consequently are used increasingly in such settings. A research agenda of some of the most pressing challenges related to visualization on ITSs emerged from discussions with researchers and practitioners in human-computer interaction, computer-supported collaborative work, and a variety of visualization fields at the 2011 Workshop on Data Exploration for Interactive Surfaces (Dexis 2011)
Flip-Invariant Sift For Copy And Object Detection, Wan-Lei Zhao, Chong-Wah Ngo
Flip-Invariant Sift For Copy And Object Detection, Wan-Lei Zhao, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
Scale-invariant feature transform (SIFT) feature has been widely accepted as an effective local keypoint descriptor for its invariance to rotation, scale, and lighting changes in images. However, it is also well known that SIFT, which is derived from directionally sensitive gradient fields, is not flip invariant. In real-world applications, flip or flip-like transformations are commonly observed in images due to artificial flipping, opposite capturing viewpoint, or symmetric patterns of objects. This paper proposes a new descriptor, named flip-invariant SIFT (or F-SIFT), that preserves the original properties of SIFT while being tolerant to flips. F-SIFT starts by estimating the dominant curl …
Kinectarms: A Toolkit For Capturing And Displaying Arm Embodiments In Distributed Tabletop Groupware, Aaron Genest, Carl Gutwin, Anthony Tang, Michael Kalyn, Zenja Ivkovic
Kinectarms: A Toolkit For Capturing And Displaying Arm Embodiments In Distributed Tabletop Groupware, Aaron Genest, Carl Gutwin, Anthony Tang, Michael Kalyn, Zenja Ivkovic
Research Collection School Of Computing and Information Systems
Gestures are a ubiquitous part of human communication over tables, but when tables are distributed, gestures become difficult to capture and represent. There are several problems: extracting arm images from video, representing the height of the gesture, and making the arm embodiment visible and understandable at the remote table. Current solutions to these problems are often expensive, complex to use, and difficult to set up. We have developed a new toolkit - KinectArms - that quickly and easily captures and displays arm embodiments. KinectArms uses a depth camera to segment the video and determine gesture height, and provides several visual …
Guest Editorial: Selected Papers From Icimcs 2011, Chong-Wah Ngo, Changsheng Xu, Xiao Wu, Abdulmotaleb El Saddik
Guest Editorial: Selected Papers From Icimcs 2011, Chong-Wah Ngo, Changsheng Xu, Xiao Wu, Abdulmotaleb El Saddik
Research Collection School Of Computing and Information Systems
International Conference on Internet Multimedia Computing and Services (ICIMCS) is an annual conference sponsored by ACM SIGMM China Chapter. The conference is especially interested in the latest technologies and applications that deal with the web-scale processing and management of heterogeneous data from the Internet for multimedia computing and service. ICIMCS 2011 held in Chengdu, China— the ancient hometown of lovely panda. The conference has attracted around 80 participants, including researchers from academia and industries across ten countries/regions, for sharing their recent works in the topics ranging from visual information analysis and mining, query processing and search, multimedia privacy and security.
Robust Non-Parametric Data Fitting For Correspondence Modeling, Wen-Yan Lin, Ming-Ming Cheng, Shuai Zheng, Jiangbo Lu, Nigel Crook
Robust Non-Parametric Data Fitting For Correspondence Modeling, Wen-Yan Lin, Ming-Ming Cheng, Shuai Zheng, Jiangbo Lu, Nigel Crook
Research Collection School Of Computing and Information Systems
We propose a generic method for obtaining nonparametric image warps from noisy point correspondences. Our formulation integrates a huber function into a motion coherence framework. This makes our fitting function especially robust to piecewise correspondence noise (where an image section is consistently mismatched). By utilizing over parameterized curves, we can generate realistic nonparametric image warps from very noisy correspondence. We also demonstrate how our algorithm can be used to help stitch images taken from a panning camera by warping the images onto a virtual push-broom camera imaging plane.
Efficient Salient Region Detection With Soft Image Abstraction, Ming-Ming Cheng, Jonathan Warrell, Wen-Yan Lin, Shuai Zheng, Vibhav Vineet, Nigel Crook
Efficient Salient Region Detection With Soft Image Abstraction, Ming-Ming Cheng, Jonathan Warrell, Wen-Yan Lin, Shuai Zheng, Vibhav Vineet, Nigel Crook
Research Collection School Of Computing and Information Systems
Detecting visually salient regions in images is one of the fundamental problems in computer vision. We propose a novel method to decompose an image into large scale perceptually homogeneous elements for efficient salient region detection, using a soft image abstraction representation. By considering both appearance similarity and spatial distribution of image pixels, the proposed representation abstracts out unnecessary image details, allowing the assignment of comparable saliency values across similar regions, and producing perceptually accurate salient region detection. We evaluate our salient region detection approach on the largest publicly available dataset with pixel accurate annotations. The experimental results show that the …
Creating Scalable Location-Based Games: Lessons From Geocaching, Carman Neustaedter, Anthony Tang, Tejinder K. Judge
Creating Scalable Location-Based Games: Lessons From Geocaching, Carman Neustaedter, Anthony Tang, Tejinder K. Judge
Research Collection School Of Computing and Information Systems
Location-based games seek to move computer gaming out from behind the PC and into the “real world” of cities, streets, parks, and other locations. This real-world physicality makes the experience fun for game players, yet it brings the unique challenge of creating and orchestrating such a game. That is, location-based games are often difficult to create, grow, and maintain over long periods of time. Our research investigates how location-based games can be designed to overcome this challenge of scalability. We studied the well-established location-based game of Geocaching through active participation and an online survey to better understand how it has …