hotauthor: lu_h* : Human-Computer Interaction Bibliography Search

[1] Learning Multi-view Deep Features for Small Object Retrieval in Surveillance Scenarios Poster Session 1 / Guo, Haiyun / Wang, Jinqiao / Xu, Min / Zha, Zheng-Jun / Lu, Hanqing Proceedings of the 2015 ACM International Conference on Multimedia 2015-10-26 p.859-862

ACM Digital Library Link

Summary: With the explosive growth of surveillance videos, object retrieval has become a significant task for security monitoring. However, visual objects in surveillance videos are usually of small size with complex light conditions, view changes and partial occlusions, which increases the difficulty level of efficiently retrieving objects of interest in a large-scale dataset. Although deep features have achieved promising results on object classification and retrieval and have been verified to contain rich semantic structure property, they lack of adequate color information, which is as crucial as structure information for effective object representation. In this paper, we propose to leverage discriminative Convolutional Neural Network (CNN) to learn deep structure and color feature to form an efficient multi-view object representation. Specifically, we utilize CNN trained on ImageNet to abstract rich semantic structure information. Meanwhile, we propose a CNN model supervised by 11 color names to extract deep color features. Compared with traditional color descriptors, deep color features can capture the common color property across different illumination conditions. Then, the complementary multi-view deep features are encoded into short binary codes by Locality-Sensitive Hash (LSH) and fused to retrieve objects. Retrieval experiments are performed on a dataset of 100k objects extracted from multi-camera surveillance videos. Comparison results with several popular visual descriptors show the effectiveness of the proposed approach.

[2] Spatio-Temporal Triangular-Chain CRF for Activity Recognition Poster Session 2 / Cao, Congqi / Zhang, Yifan / Lu, Hanqing Proceedings of the 2015 ACM International Conference on Multimedia 2015-10-26 p.1151-1154

ACM Digital Library Link

Summary: Understanding human activities in video is a fundamental problem in computer vision. In real life, human activities are composed of temporal and spatial arrangement of actions. Understanding such complex activities requires recognizing not only each individual action, but more importantly, capturing their spatio-temporal relationships. This paper addresses the problem of complex activity recognition with a unified hierarchical model. We expand triangular-chain CRFs (TriCRFs) to the spatial dimension. The proposed architecture can be perceived as a spatio-temporal version of the TriCRFs, in which the labels of actions and activity are modeled jointly and their complex dependencies are exploited. Experiments show that our model generates promising results, outperforming competing methods significantly. The framework also can be applied to model other structured sequential data.

[3] Semi- and Weakly- Supervised Semantic Segmentation with Deep Convolutional Neural Networks Poster Session 2 / Wang, Yuhang / Liu, Jing / Li, Yong / Lu, Hanqing Proceedings of the 2015 ACM International Conference on Multimedia 2015-10-26 p.1223-1226

ACM Digital Library Link

Summary: Successful semantic segmentation methods typically rely on the training datasets containing a large number of pixel-wise labeled images. To alleviate the dependence on such a fully annotated training dataset, in this paper, we propose a semi- and weakly-supervised learning framework by exploring images most only with image-level labels and very few with pixel-level labels, in which two stages of Convolutional Neural Network (CNN) training are included. First, a pixel-level supervised CNN is trained on very few fully annotated images. Second, given a large number of images with only image-level labels available, a collaborative-supervised CNN is designed to jointly perform the pixel-level and image-level classification tasks, while the pixel-level labels are predicted by the fully-supervised network in the first stage. The collaborative-supervised network can remain the discriminative ability of the fully-supervised model learned with fully labeled images, and further enhance the performance by importing more weakly labeled data. Our experiments on two challenging datasets, i.e, PASCAL VOC 2007 and LabelMe LMO, demonstrate the satisfactory performance of our approach, nearly matching the results achieved when all training images have pixel-level labels.

[4] Exclusive Constrained Discriminative Learning for Weakly-Supervised Semantic Segmentation Poster Session 2 / Ying, Peng / Liu, Jin / Lu, Hanqing / Ma, Songde Proceedings of the 2015 ACM International Conference on Multimedia 2015-10-26 p.1251-1254

ACM Digital Library Link

Summary: How to import image-level labels as weak supervision to direct the region-level labeling task is the core task of weakly-supervised semantic segmentation. In this paper, we focus on designing an effective but simple weakly-supervised constraint, and propose an exclusive constrained discriminative learning model for image semantic segmentation. To be specific, we employ a discriminative linear regression model to assign subsets of superpixels with different labels. During the assignment, we construct an exclusive weakly-supervised constraint term to suppress the labeling responses of each superpixel on the labels outside its parent image-level label set. Besides, a spectral smoothing term is integrated to encourage that both visually and semantically similar superpixels have similar labels. Combining these terms, we formulate the problem as a convex objective function, which can be easily optimized via alternative iterations. Extensive experiments on MSRC-21 and LabelMe datasets demonstrate the effectiveness of the proposed model.

[5] BiasWatch: A Lightweight System for Discovering and Tracking Topic-Sensitive Opinion Bias in Social Media Session 1F: Social Media 1 / Lu, Haokai / Caverlee, James / Niu, Wei Proceedings of the 2015 ACM Conference on Information and Knowledge Management 2015-10-19 p.213-222

ACM Digital Library Link

Summary: We propose a lightweight system for (i) semi-automatically discovering and tracking bias themes associated with opposing sides of a topic; (ii) identifying strong partisans who drive the online discussion; and (iii) inferring the opinion bias of "regular" participants. By taking just two hand-picked seeds to characterize the topic-space (e.g., "pro-choice" and "pro-life") as weak labels, we develop an efficient optimization-based opinion bias propagation method over the social/information network. We show how this approach leads to a 20% accuracy improvement versus a next-best alternative for bias estimation, as well as uncovering the opinion leaders and evolving themes associated with these topics. We also demonstrate how the inferred opinion bias can be integrated into user recommendation, leading to a 26% improvement in precision.

[6] Personalized Recommendation Meets Your Next Favorite Short Papers: Information Retrieval / Song, Qiang / Cheng, Jian / Yuan, Ting / Lu, Hanqing Proceedings of the 2015 ACM Conference on Information and Knowledge Management 2015-10-19 p.1775-1778

ACM Digital Library Link

Summary: A comprehensive understanding of user's item selection behavior is not only essential to many scientific disciplines, but also has a profound business impact on online recommendation. Recent researches have discovered that user's favorites can be divided into 2 categories: long-term and short-term. User's item selection behavior is a mixed decision of her long and short-term favorites. In this paper, we propose a unified model, namely States Transition pAir-wise Ranking Model (STAR), to address users' favorites mining for sequential-set recommendation. Our method utilizes a transition graph for collaborative filtering that accounts for mining user's short-term favorites, jointed with a generative topic model for expressing user's long-term favorites. Furthermore, a user's specific prior is introduced into our unified model for better modeling personalization. Technically, we develop a pair-wise ranking loss function for parameters learning. Empirically, we measure the effectiveness of our method using two real-world datasets and the results show that our method outperforms state-of-the-art methods.

[7] Exploiting Geo-Spatial Preference for Personalized Expert Recommendation Session 2a: Contextual Challenges / Lu, Haokai / Caverlee, James Proceedings of the 2015 ACM Conference on Recommender Systems 2015-09-16 p.67-74

ACM Digital Library Link

Summary: Experts are important for providing reliable and authoritative information and opinion, as well as for improving online reviews and services. While considerable previous research has focused on finding topical experts with broad appeal -- e.g., top Java developers, best lawyers in Texas -- we tackle the problem of personalized expert recommendation, to identify experts who have special personal appeal and importance to users. One of the key insights motivating our approach is to leverage the geo-spatial preferences of users and the variation of these preferences across different regions, topics, and social communities. Through a fine-grained GPS-tagged social media trace, we characterize these geo-spatial preferences for personalized experts, and integrate these preferences into a matrix factorization-based personalized expert recommender. Through extensive experiments, we find that the proposed approach can improve the quality of recommendation by 24% in precision compared to several baselines. We also find that users' geo-spatial preference of expertise and their underlying social communities can ameliorate the cold start problem by more than 20% in precision and recall.

[8] Incremental Matrix Factorization via Feature Space Re-learning for Recommender System Short Papers / Song, Qiang / Cheng, Jian / Lu, Hanqing Proceedings of the 2015 ACM Conference on Recommender Systems 2015-09-16 p.277-280

ACM Digital Library Link

Summary: Matrix factorization is widely used in Recommender Systems. Although existing popular incremental matrix factorization methods are effectively in reducing time complexity, they simply assume that the similarity between items or users is invariant. For instance, they keep the item feature matrix unchanged and just update the user matrix without re-training the entire model. However, with the new users growing continuously, the fitting error would be accumulated since the extra distribution information of items has not been utilized. In this paper, we present an alternative and reasonable approach, with a relaxed assumption that the similarity between items (users) is relatively stable after updating. Concretely, utilizing the prediction error of the new data as the auxiliary features, our method updates both feature matrices simultaneously, and thus users' preference can be better modeled than merely adjusting one corresponded feature matrix. Besides, our method maintains the feature dimension in a smaller size through taking advantage of matrix sketching. Experimental results show that our proposal outperforms the existing incremental matrix factorization methods.

[9] When Personalization Meets Conformity: Collective Similarity based Multi-Domain Recommendation Short Papers / Zhang, Xi / Cheng, Jian / Qiu, Shuang / Zhu, Zhenfeng / Lu, Hanqing Proceedings of the 2015 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval 2015-08-09 p.1019-1022

ACM Digital Library Link

Summary: Existing recommender systems place emphasis on personalization to achieve promising accuracy. However, in the context of multiple domain, users are likely to seek the same behaviors as domain authorities. This conformity effect provides a wealth of prior knowledge when it comes to multi-domain recommendation, but has not been fully exploited. In particular, users whose behaviors are significant similar with the public tastes can be viewed as domain authorities. To detect these users meanwhile embed conformity into recommendation, a domain-specific similarity matrix is intuitively employed. Therefore, a collective similarity is obtained to leverage the conformity with personalization. In this paper, we establish a Collective Structure Sparse Representation (CSSR) method for multi-domain recommendation. Based on adaptive k-Nearest-Neighbor framework, we impose the lasso and group lasso penalties as well as least square loss to jointly optimize the collective similarity. Experimental results on real-world data confirm the effectiveness of the proposed method.

[10] A Comparison of Hybrid Neural Network Based Breast Cancer Diagnosis Systems Analytics, Visualisation and Decision-making / Tsai, Hsine-Jen / Lu, Hao-Chun / Wu, Tung-Huan / Lee, Chiang-Sheng HCIB 2015: 2nd International Conference on HCI in Business 2015-08-02 p.633-639

Keywords: Neural network; Association rule; Genetic algorithm; Medical artificial intelligence

Link to Digital Content at Springer

Summary: Breast cancer is the second leading cause of death among the women aged between 40 and 59 in the world. The diagnosis of such disease has been a challenging research problem. With the advancement of artificial intelligence in medical science, numerous AI based breast cancer diagnosis system have been proposed. Many researches combine different algorithms to develop hybrid systems to improve the diagnosis accuracy. In this study, we propose three artificial neural network based hybrid diagnosis systems respectively combining association rule, correlation and genetic algorithm. The effectiveness of these systems is examined on Wisconsin Breast Cancer Dataset. We then compare the accuracy of these three hybrid diagnosis systems. The results indicated that the neural network combining with association rule not only has excellent dimensionality reduction ability but also has the similar accurate prediction with correlation based neural network which has best accurate prediction rate among all three systems compared.

[11] Tagging Personal Photos with Transfer Deep Learning Technical Papers / Fu, Jianlong / Mei, Tao / Yang, Kuiyuan / Lu, Hanqing / Rui, Yong Proceedings of the 2015 International Conference on the World Wide Web 2015-05-18 v.1 p.344-354

ACM Digital Library Link

Summary: The advent of mobile devices and media cloud services has led to the unprecedented growing of personal photo collections. One of the fundamental problems in managing the increasing number of photos is automatic image tagging. Existing research has predominantly focused on tagging general Web images with a well-labelled image database, e.g., ImageNet. However, they can only achieve limited success on personal photos due to the domain gaps between personal photos and Web images. These gaps originate from the differences in semantic distribution and visual appearance. To deal with these challenges, in this paper, we present a novel transfer deep learning approach to tag personal photos. Specifically, to solve the semantic distribution gap, we have designed an ontology consisting of a hierarchical vocabulary tailored for personal photos. This ontology is mined from 10,000 active users in Flickr with 20 million photos and 2.7 million unique tags. To deal with the visual appearance gap, we discover the intermediate image representations and ontology priors by deep learning with bottom-up and top-down transfers across two domains, where Web images are the source domain and personal photos are the target. Moreover, we present two modes (single and batch-modes) in tagging and find that the batch-mode is highly effective to tag photo collections. We conducted personal photo tagging on 7,000 real personal photos and personal photo search on the MIT-Adobe FiveK photo dataset. The proposed tagging approach is able to achieve a performance gain of 12.8% and 4.5% in terms of NDCG@5, against the state-of-the-art hand-crafted feature-based and deep learning-based methods, respectively.

[12] Exploring Heterogeneity for Multi-Domain Recommendation with Decisive Factors Selection Posters / Qiu, Shuang / Cheng, Jian / Zhang, Xi / Lu, Hanqing Companion Proceedings of the 2015 International Conference on the World Wide Web 2015-05-18 v.2 p.95-96

ACM Digital Library Link

Summary: To address the recommendation problems in the scenarios of multiple domains, in this paper, we propose a novel method, HMRec, which models both consistency and heterogeneity of users' multiple behaviors in a unified framework. Moreover, the decisive factors of each domain can also be captured by our approach successfully. Experiments on the real multi-domain dataset demonstrate the effectiveness of our model.

[13] Gesture On: Enabling Always-On Touch Gestures for Fast Mobile Access from the Device Standby Mode Gesture Elicitation & Recognition / Lu, Hao / Li, Yang Proceedings of the ACM CHI'15 Conference on Human Factors in Computing Systems 2015-04-18 v.1 p.3355-3364

ACM Digital Library Link

Summary: A significant percentage of mobile interaction involves short-period usages that originate from the standby mode-users wake up a device by pressing the power button, unlock the device by authenticating themselves, and then search for a target app or functionality on the device. These additional steps preceding a target task imposes significant overhead on users for each mobile device access. To address the issue, we developed Gesture On, a system that enables gesture shortcuts in the standby mode by which a user can draw a gesture on the touchscreen before the screen is turned on. Based on the gesture, our system directly brings up a target item onto the screen that bypasses all these additional steps in a mobile access. This paper examines several challenges in realizing Gesture On, including robustly rejecting accidental touches when the device is in standby, battery consumption incurred for continuous sensing and gesture-based user authentication methods for automatically device unlocking. Our analyses based on a set of user data indicated that Gesture On demonstrates a feasible approach for leveraging the standby mode for fast access to mobile content.

[14] Locality Preserving Discriminative Hashing Posters 3 / Zhao, Kang / Lu, Hongtao / He, Yangcheng / Feng, Shaokun Proceedings of the 2014 ACM International Conference on Multimedia 2014-11-03 p.1089-1092

ACM Digital Library Link

Summary: Hashing for large scale similarity search has become more and more popular because of its improvement in computational speed and storage reduction. Semi-supervised Hashing (SSH) has been proven effective since it integrates both labeled and unlabeled data to leverage semantic similarity while keeping robust to overfitting. However, it ignores the global label information and the local structure of the feature space. In this paper, we concentrate on these two issues and propose a novel semi-supervised hashing method called Locality Preserving Discriminative Hashing which combines two classical dimensionality reduction approaches, Linear Discriminant Analysis (LDA) and Locality Preserving Projection (LPP). The proposed method presents a rigorous formulation in which the supervised term tries to maintain the global information of the labeled data while the unsupervised term provides effective regularization to model local relationships of the unlabeled data. We apply an efficient sequential procedure to learn the hashing functions. Experimental comparisons with other state-of-the-art methods on three large scale datasets demonstrate the effectiveness and efficiency of our method.

[15] Mask Assisted Object Coding with Deep Learning for Object Retrieval in Surveillance Videos Posters 3 / Teng, Kezhen / Wang, Jinqiao / Xu, Min / Lu, Hanqing Proceedings of the 2014 ACM International Conference on Multimedia 2014-11-03 p.1109-1112

ACM Digital Library Link

Summary: Retrieving visual object from a large-scale video dataset is one of multimedia research focuses but a challenging task due to imprecise object extraction and partial occlusion. This paper presents a novel approach to efficiently encode and retrieve visual objects, which addresses some practical complications in surveillance videos. Specifically, we take advantage of the mask information to assist object representation, and develop an encoding method by utilizing highly nonlinear mapping with a deep neural network. Furthermore, we add some occluded noise into the learning process to enhance the robustness of dealing with background noise and partial occlusions. A real-life surveillance video data containing over 10 million objects are built to evaluate the proposed approach. Experimental results show our approach significantly outperforms state-of-the-art solutions for object retrieval in large-scale video dataset.

[16] Supervised Hashing with Soft Constraints IR Track Posters / Leng, Cong / Cheng, Jian / Wu, Jiaxiang / Zhang, Xi / Lu, Hanqing Proceedings of the 2014 ACM Conference on Information and Knowledge Management 2014-11-03 p.1851-1854

ACM Digital Library Link

Summary: Due to the ability to preserve semantic similarity in Hamming space, supervised hashing has been extensively studied recently. Most existing approaches encourage two dissimilar samples to have maximum Hamming distance. This may lead to an unexpected consequence that two unnecessarily similar samples would have the same code if they are both dissimilar with another sample. Besides, in existing methods, all labeled pairs are treated with equal importance without considering the semantic gap, which is not conducive to thoroughly leverage the supervised information. We present a general framework for supervised hashing to address the above two limitations. We do not toughly require a dissimilar pair to have maximum Hamming distance. Instead, a soft constraint which can be viewed as a regularization to avoid over-fitting is utilized. Moreover, we impose different weights to different training pairs, and these weights can be automatically adjusted in the learning process. Experiments on two benchmarks show that the proposed method can easily outperform other state-of-the-art methods.

[17] Improving Recommendation Accuracy by Combining Trust Communities and Collaborative Filtering KM Track Posters / Ma, Xiao / Lu, Hongwei / Gan, Zaobin Proceedings of the 2014 ACM Conference on Information and Knowledge Management 2014-11-03 p.1951-1954

ACM Digital Library Link

Summary: With the booming of online social networks, social trust has been used to cluster users in recommender systems. It has been proven to improve the recommendation accuracy when trust communities are integrated into memory-based collaborative filtering algorithms. However, existing trust community mining methods only consider the trust relationships, regardless of the distrust information. In this paper, considering both the trust and distrust relationships, a SVD signs based community mining method is proposed to process the trust relationship matrix in order to discover the trust communities. A modified trust metric which considers a given user's expertise level in a community is presented to obtain the indirect trust values between users. Then some missing ratings of the given user are complemented by the weighted average preference of his/her trusted neighbors selected in the same community during the random walk procedures. Finally, the prediction for a given item is generated by the conventional collaborative filtering. The comparison experiments on Epinions data set demonstrate that our approach outperforms other state-of-the-art methods in terms of RMSE and RC.

[18] Unobtrusive gait verification for mobile phones Sensing the body / Lu, Hong / Huang, Jonathan / Saha, Tanwistha / Nachman, Lama Proceedings of the 2014 International Symposium on Wearable Computers 2014-09-13 v.1 p.91-98

ACM Digital Library Link

Summary: Continuously and unobtrusively identifying the phone's owner using accelerometer sensing and gait analysis has a great potential to improve user experience on the go. However, a number of challenges, including gait modeling and training data acquisition, must be addressed before unobtrusive gait verification is practical. In this paper, we describe a gait verification system for mobile phone without any assumption of body placement or device orientation. Our system uses a combination of supervised and unsupervised learning techniques to verify the user continuously and automatically learn unseen gait pattern from the user over time. We demonstrate that it is capable of recognizing the user in natural settings. We also investigated an unobtrusive training method that makes it feasible to acquire training data without explicit user annotation.

[19] Classifying the mode of transportation on mobile phones using GIS information Cities & transportation / Shah, Rahul C. / Wan, Chieh-yih / Lu, Hong / Nachman, Lama Proceedings of the 2014 International Joint Conference on Pervasive and Ubiquitous Computing 2014-09-13 v.1 p.225-229

ACM Digital Library Link

Summary: Determining the mode of transport of an individual is an important element of contextual information. In particular, we focus on differentiating between different forms of motorized transport such as car, bus, subway etc. Our approach uses location information and features derived from transit route information (schedule information, not real-time) published by transit agencies. This enables no up-front training or learning of routes and can be deployed instantly to a new place since most transit agencies publish this information. Combined with motion detection using phone accelerometers, we obtain a classification accuracy of around 90% on 50+ hours of car and transit data.

[20] Optimistic Programming of Touch Interaction / Li, Yang / Lu, Hao / Zhang, Haimo ACM Transactions on Computer-Human Interaction 2014-08 v.21 n.4 p.24

ACM Digital Library Link

Summary: Touch-sensitive surfaces have become a predominant input medium for computing devices. In particular, multitouch capability of these devices has given rise to developing rich interaction vocabularies for "real" direct manipulation of user interfaces. However, the richness and flexibility of touch interaction often comes with significant complexity for programming these behaviors. Particularly, finger touches, though intuitive, are imprecise and lead to ambiguity. Touch input often involves coordinated movements of multiple fingers as opposed to the single pointer of a traditional WIMP interface. It is challenging in not only detecting the intended motion carried out by these fingers but also in determining the target objects being manipulated due to multiple focus points. Currently, developers often need to build touch behaviors by dealing with raw touch events that is effort consuming and error-prone. In this article, we present Touch, a tool that allows developers to easily specify their desired touch behaviors by demonstrating them live on a touch-sensitive device or selecting them from a list of common behaviors. Developers can then integrate these touch behaviors into their application as resources and via an API exposed by our runtime framework. The integrated tool support enables developers to think and program optimistically about how these touch interactions should behave, without worrying about underlying complexity and technical details in detecting target behaviors and invoking application logic. We discuss the design of several novel inference algorithms that underlie these tool supports and evaluate them against a multitouch dataset that we collected from end users. We also demonstrate the usefulness of our system via an example application.

[21] Group latent factor model for recommendation with multiple user behaviors Poster session (short papers) / Cheng, Jian / Yuan, Ting / Wang, Jinqiao / Lu, Hanqing Proceedings of the 2014 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval 2014-07-06 p.995-998

ACM Digital Library Link

Summary: Recently, some recommendation methods try to relieve the data sparsity problem of Collaborative Filtering by exploiting data from users' multiple types of behaviors. However, most of the exist methods mainly consider to model the correlation between different behaviors and ignore the heterogeneity of them, which may make improper information transferred and harm the recommendation results. To address this problem, we propose a novel recommendation model, named Group Latent Factor Model (GLFM), which attempts to learn a factorization of latent factor space into subspaces that are shared across multiple behaviors and subspaces that are specific to each type of behaviors. Thus, the correlation and heterogeneity of multiple behaviors can be modeled by these shared and specific latent factors. Experiments on the real-world dataset demonstrate that our model can integrate users' multiple types of behaviors into recommendation better.

[22] Random subspace for binary codes learning in large scale image retrieval Poster session (short papers) / Leng, Cong / Cheng, Jian / Lu, Hanqing Proceedings of the 2014 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval 2014-07-06 p.1031-1034

ACM Digital Library Link

Summary: Due to the fast query speed and low storage cost, hashing based approximate nearest neighbor search methods have attracted much attention recently. Many state of the art methods are based on eigenvalue decomposition. In these approaches, the information caught in different dimensions is unbalanced and generally most of the information is contained in the top eigenvectors. We demonstrate that this leads to an unexpected phenomenon that longer hashing code does not necessarily yield better performance. In this work, we introduce a random subspace strategy to address this limitation. At first, a small fraction of the whole feature space is randomly sampled to train the hashing algorithms each time and only the top eigenvectors are kept to generate one piece of short code. This process will be repeated several times and then the obtained many pieces of short codes are concatenated into one piece of long code. Theoretical analysis and experiments on two benchmarks confirm the effectiveness of the proposed strategy for hashing.

[23] Item group based pairwise preference learning for personalized ranking Poster session (short papers) / Qiu, Shuang / Cheng, Jian / Yuan, Ting / Leng, Cong / Lu, Hanqing Proceedings of the 2014 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval 2014-07-06 p.1219-1222

ACM Digital Library Link

Summary: Collaborative filtering with implicit feedbacks has been steadily receiving more attention, since the abundant implicit feedbacks are more easily collected while explicit feedbacks are not necessarily always available. Several recent work address this problem well utilizing pairwise ranking method with a fundamental assumption that a user prefers items with positive feedbacks to the items without observed feedbacks, which also implies that the items without observed feedbacks are treated equally without distinction. However, users have their own preference on different items with different degrees which can be modeled into a ranking relationship. In this paper, we exploit this prior information of a user's preference from the nearest neighbor set by the neighbors' implicit feedbacks, which can split items into different item groups with specific ranking relations. We propose a novel PRIGP (Personalized Ranking with Item Group based Pairwise preference learning) algorithm to integrate item based pairwise preference and item group based pairwise preference into the same framework. Experimental results on three real-world datasets demonstrate the proposed method outperforms the competitive baselines on several ranking-oriented evaluation metrics.

[24] Gesturemote: interacting with remote displays through touch gestures Gestural interaction / Lü, Hao / Negulescu, Matei / Li, Yang Proceedings of the 2014 International Conference on Advanced Visual Interfaces 2014-05-27 p.325-328

ACM Digital Library Link

Summary: We present Gesturemote, a technique for interacting with remote displays through touch gestures on a handheld touch surface. By combining a variety of different touch gestures and connecting them smoothly, Gesturemote supports a wide range of interaction behaviors, from low pixel-level interaction such as pointing and clicking, to medium-level interaction such as structured navigation of a user interface, to high-level interaction such as invoking a function directly (e.g. shortcuts). Gesturemote requires no visual attention to use and thus is eyes-free. We received positive initial feedback for Gesturemote from the participants in an interview where we walked them through the design. In addition, we investigated the usability of our gesture-based target acquisition technique by comparing it with a trackpad in a target acquisition task. The results indicate that Gesturemote performs better when visual search is required and is preferable to a general-purpose trackpad.

[25] Toward an understanding of the behavioral intention to use a social networking site: An extension of task-technology fit to social-technology fit / Lu, Hsi-Peng / Yang, Yi-Wen Computers in Human Behavior 2014-05 v.34 n.0 p.323-332

Keywords: Social networking sites

Keywords: Task-technology fit

Keywords: Technology acceptance

Keywords: Social capital theory

Keywords: Partial least squares

Link to Article at sciencedirect

Summary: Social networking sites (SNS) are one of the recent popular social media platforms. Successful SNS can attract millions of users in a few years, which has drawn much attention in the study of SNS. Understanding the relationships between a user's intention and the utilization of SNS is an essential step in engaging the SNS as a marketing or educational tool. However, current research models for technology acceptance can hardly explain the impact on the intention of using SNS from the perspective of technology fit due to the lack of social constructs. This study examines and compares the impact of task, social, and technology characteristics on users' intentions in using SNS by integrating the task-technology fit model and social capital theory. Data of 315 Facebook users were collected from the online questionnaire, and processed using the SmartPLS version 2.0 for path analysis and hypotheses tests. The results reveal that the social-technology fit has a dominant impact over the task-technology fit on users' intentions to employ SNS. For SNS research, it suggests a reconceptualization of the current task-technology fit model by adding social constructs if necessary.