Empirical experience and observations have shown us when powerful and highly tunable classifiers such as maximum entropy classifiers, boosting and SVMs are applied to language processing tasks, it is possible to achie...
详细信息
This paper describes a new technique for clustering short time series comingfrom gene expression data. The technique is based on the labelling of the time series through temporal trend abstractions and a consequent cl...
详细信息
This paper describes control algorithm for continuous walking interactions at various terrains with a 12-DOF locomotion interface. The walking control algorithm is suggested for human to walk continuously on infinite ...
详细信息
In recent studies of graphical dialogue, the level of communicative interaction has been identified as an important influence on the form of graphical representations. Here, we report the results of a ‘Pictionary-lik...
详细信息
Models allow us to describe complex systems at different abstract and conceptual levels, hence amplify our analytical and problem solving capabilities, However, a lot of human effort and experience is needed to build ...
详细信息
We introduce a conservative error correcting model, Stacked TBL, that is designed to improve the performance of even high-performing models like boosting, with little risk of accidentally degrading performance. Stacke...
详细信息
ISBN:
(纸本)2951740816
We introduce a conservative error correcting model, Stacked TBL, that is designed to improve the performance of even high-performing models like boosting, with little risk of accidentally degrading performance. Stacked TBL is particularly well suited for corpus-based natural language applications involving high-dimensional feature spaces, since it leverages the characteristics of the TBL paradigm that we appropriate. We consider here the task of automatically annonating named entities in text corpora. The task does pose a number of challenges for TBL, to which there are some simple yet effective solutions. We discuss the empirical behavior of Stacked T BL, and consider evidence that despite its simplicity, more complex and time-consuming variants are not generally required.
Particle filtering is a very popular technique for sequential state estimation problem. However its convergence greatly depends on the balance between the number of particles/hypotheses and the fitness of the dynamic ...
详细信息
Particle filtering is a very popular technique for sequential state estimation problem. However its convergence greatly depends on the balance between the number of particles/hypotheses and the fitness of the dynamic model. In particular, in cases where the dynamics are complex or poorly modeled, thousands of particles are usually required for real applications. This paper presents a hybrid sampling solution that combines the sampling in the image feature space and in the state space via RANSAC and particle filtering, respectively. We show that the number of particles can be reduced to dozens for a full 3D tracking problem which contains considerable noise of different types. For unexpected motions, a specific set of dynamics may not exist, but it is avoided in our algorithm. The theoretical convergence proof [1, 3] for particle filtering when integrating RANSAC is difficult, but we address this problem by analyzing the likelihood distribution of particles from a real tracking example. The sampling efficiency (on the more likely areas) is much higher by the use of RANSAC. We also discuss the tracking quality measurement in the sense of entropy or statistical testing. The algorithm has been applied to the problem of 3D face pose tracking with changing moderate or intense expressions. We demonstrate the validity of our approach with several video sequences acquired in an unstructured environment.
The goal of this panel is to discuss theoretical and methodological approaches that may inform and support the design of temporal aspects of interactive systems. Time Design is an emerging research and development dom...
The goal of this panel is to discuss theoretical and methodological approaches that may inform and support the design of temporal aspects of interactive systems. Time Design is an emerging research and development domain that emphasizes the functional, causal role of time in human control behavior. It draws on a diverse literature on time in cognitive psychology, psychophysics, sociology, computerscience, engineering, human Factors and HCI. Relevant research domains include heuristics and biases in temporal decisions, temporal aspects of human-automation interaction, planning and scheduling, visualisation of temporal information, and the timing of alarms and interruptions.
The perceptual satisfaction of a user watching video on a tiny mobile device is constrained by the display capability and network bandwidth. To maximize the user's perceptual satisfaction in this constrained envir...
详细信息
ISBN:
(纸本)0780386035
The perceptual satisfaction of a user watching video on a tiny mobile device is constrained by the display capability and network bandwidth. To maximize the user's perceptual satisfaction in this constrained environment, we propose a new method to adaptively represent the video content in real-time on tiny devices according to the user's attention. In our framework, firstly, a sampling based dynamic attention model is proposed to obtain and maintain the user's attention in the video streams. Secondly, based on the most attended regions and sequences extracted, the attention based representation is introduced to achieve a higher perceptual satisfaction on a small display. Experiments with users show the effectiveness of our proposed method in a video surveillance application domain.
This paper describes a novel clustering-based text summarization system that uses Multiple Sequence Alignment to improve the alignment of sentences within topic clusters. While most current clustering-based summarizat...
详细信息
ISBN:
(纸本)2951740816
This paper describes a novel clustering-based text summarization system that uses Multiple Sequence Alignment to improve the alignment of sentences within topic clusters. While most current clustering-based summarization systems base their summaries only on the common information contained in a collection of highly-related sentences, our system constructs more informative summaries that incorporate both the redundant and unique contributions of the sentences in the cluster. When evaluated using ROUGE, the summaries produced by our system represent a substantial improvement over the baseline, which is at 63% of the human performance.
暂无评论