We show that dually supervised manifold embedding can improve the performance of machine learning based person-independent and thus calibration-free gaze estimation. For this purpose, we perform a manifold embedding f...
详细信息
We show that dually supervised manifold embedding can improve the performance of machine learning based person-independent and thus calibration-free gaze estimation. For this purpose, we perform a manifold embedding for each person in the training dataset and then learn a linear transformation that aligns the individual, person-dependent manifolds. We evaluate the effect of manifold alignment on the recently presented Columbia dataset, where we analyze the influence on 6 regression methods and 8 feature variants. Using manifold alignment, we are able to improve the person-independent gaze estimation performance by up to 31.2 % compared to the best approach without manifold alignment.
On the Internet, plain text documents created and viewed by users constitute ever changing document streams. Lots of the literature is devoted to topic modeling, while the sequential patterns of topics in document str...
详细信息
ISBN:
(纸本)9781450324694
On the Internet, plain text documents created and viewed by users constitute ever changing document streams. Lots of the literature is devoted to topic modeling, while the sequential patterns of topics in document streams are ignored. In this paper, we deal with the problem of mining user related rare sequential patterns of topics in the Internet document streams, which can be used in many fields, such as real-time user behavioral monitoring on the Internet. We propose an approach to discover rare patterns based on the temporal and probabilistic information of topics. Experiments show that the proposed approach can discover user related rare patterns of topic effectively. Copyright 2014 ACM.
The International Agency for Research on Cancer classifies radiofrequency (RF) electromagnetic emissions of cell phones as possibly carcinogenic to humans [1] and suggests the use of hands-free devices such as earphon...
详细信息
Alternative systems ranging from self-organized skill sharing to alternative micro-economies have been critical channels of community engagement and bonding. Technology is increasingly playing a role in the way people...
详细信息
ISBN:
(纸本)9781450331463
Alternative systems ranging from self-organized skill sharing to alternative micro-economies have been critical channels of community engagement and bonding. Technology is increasingly playing a role in the way people connect to these services at the (hyper)local level. While there has been considerable research on designing technology to support conventional, established systems of community organization and governance;mobile and ubiquitous technologies offer strong potential for alternative systems to be established in the local level. Do It Yourself (DIY) and maker movements are enabling grassroots activist groups to develop their own technologies or to hack existing tools to support bottom-up systems of self-organization, democracy and commerce. Based on these trends and the recent worldwide economic, political and societal crisis, this workshop will bring together researchers, practitioners and activists to re-envision how HCI tools can support alternative systems of local civic engagement.
Virtual risk experiences have been proposed in persuasive technology as an approach to change people's attitudes and behaviors concerning safety topics. This paper advances the investigation of virtual risk experi...
详细信息
In this paper, we propose a prototype of machine-to-machine interaction system using a single RGBD camera. Based on the 3D arm pointing and tracking algorithm, system enables user to select multiple objects using thei...
详细信息
Searching the Internet and the ability to competently use search engines are increasingly becoming an important part of children’s daily lives. Whether mobile or at home, children use search interfaces to explore per...
ISBN:
(数字)9781608454440
Searching the Internet and the ability to competently use search engines are increasingly becoming an important part of children’s daily lives. Whether mobile or at home, children use search interfaces to explore personal interests, complete academic assignments, and have social interaction. However, engaging with search also means engaging with an ever-changing and evolving search landscape. There are continual software updates, multiple devices used to search (e.g., phones, tablets), an increasing use of social media, and constantly updated Internet content. For young searchers, this can require infinite adaptability or mean being hopelessly confused. This book offers a perspective centered on children’s search experiences as a whole instead of thinking of search as a process with separate and potentially problematic steps. Reading the prior literature with a child-centered view of search reveals that children have been remarkably consistent over time as searchers, displaying the same search strategies regardless of the landscape of search. However, no research has synthesized these consistent patterns in children’s search across the literature, and only recently have these patterns been uncovered as distinct search roles, or searcher types. Based on a four-year longitudinal study on children’s search experiences, this book weaves together the disparate evidence in the literature through the use of 9 search roles for children ages 7-15. The search role framework has a distinct advantage because it encourages adult stakeholders to design children’s search tools to support and educate children at their existing levels of search strength and deficit, rather than expecting children to adapt to a transient search landscape.
The wealth of resources online has empowered individuals and businesses with an unprecedented volume of information to aid in decision making processes. However, finding the many details needed for a non-trivial decis...
详细信息
In popular music genres, typical songs are pre-composed and leave little or no space for improvisation during a live performance. That applies for the performing musicians as well as for the spectators in terms of int...
详细信息
Since its release, Kinect has been the de facto standard for low-cost RGB-D sensors. An infrared laser ray shot through an holographic diffraction grating projects a fixed dot pattern which is captured using an infrar...
详细信息
ISBN:
(纸本)9781479957521
Since its release, Kinect has been the de facto standard for low-cost RGB-D sensors. An infrared laser ray shot through an holographic diffraction grating projects a fixed dot pattern which is captured using an infrared camera. The pseudo-random pattern ensures that a simple block matching algorithm suffices to provide reliable depth estimates, allowing a cost-effective implementation. In this paper, we analyze the software limitations of Kinect's method, which allows us to propose algorithms that provide better precision. First, we analyze the dot pattern: we measure its pincushion distortion and its effect on the dot density, which is smaller towards the edges of the image. Then, we analyze the behavior of Block Matching algorithms, we show how Kinect's Block Matching implementation is;in general;limited by the dot density of the pattern, and a significant spatial bias is introduced as a result. We propose an efficient approach to estimate the disparity of each dot, allowing us to produce a point cloud with better spatial resolution than Block Matching algorithms.
暂无评论