Simultaneous EEG-fMRI measurements can combine the high spatial resolution of fMRI with the high temporal resolution of EEG. Therefore, we applied this approach to the study of peripheral vision. More specifically, we...
详细信息
Simultaneous EEG-fMRI measurements can combine the high spatial resolution of fMRI with the high temporal resolution of EEG. Therefore, we applied this approach to the study of peripheral vision. More specifically, we presented visual field quadrant fragments of checkerboards and a full central checkerboard in a simple detection task. A technique called "integration-by-prediction" was used to integrate EEG and fMRI data. In particular, we used vectors of single-trial ERP amplitude differences between left and right occipital electrodes as regressors in an ERP-informed fMRI analysis. The amplitude differences for the regressors were measured at the latencies of the visual P1 and N1 components. Our results indicated that the traditional event-related fMRI analysis revealed mostly activations in the vicinity of the primary visual cortex and in the ventral visual stream, while both P1 and N1 regressors revealed activation of areas in the temporo-parietal junction. We conclude that simultaneous EEG-fMRI in a spatial detection task can separate visual processing at 100200 ms from stimulus onset from the rest of the information processing in the brain. (C) 2010 Elsevier Inc. All rights reserved.
Fine-grained classification is a challenging problem, due to subtle differences among highly-confused categories. Most approaches address this difficulty by learning discriminative representation of individual input i...
详细信息
作者：
Feng XueZengwei JiangVCC Division
School of Computer and Information The International Conference on Multimedia Technology Hefei University of Technology Hefei China
MeanShift algorithm is a popular method for searching for local extreme value in the density distribution of a set of data. Traditional MeanShift object tracking algorithm mainly uses a single histogram to describe th...
详细信息
ISBN:
(纸本)9781612847719
MeanShift algorithm is a popular method for searching for local extreme value in the density distribution of a set of data. Traditional MeanShift object tracking algorithm mainly uses a single histogram to describe the color characteristics of an object, and the detection precision and stability are not good enough in a complex background due to its lacking of spatial information of pixel colors. As for this defect, this paper presents a new method combined with distribution information of space to reduce the effect of image flaws by setting a weight to pixels, on the basis of the distance from the center point of target to the current point. The experiment results show that our method promotes the tracking accuracy of moving object under a complicated environment and has better stability.
This paper surveys the state of the art on multimodal gesture recognition and introduces the JMLR special topic on gesture recognition2011-2015. We began right at the start of the Kinect™ revolution when inexpensive ...
详细信息
This paper surveys the state of the art on multimodal gesture recognition and introduces the JMLR special topic on gesture recognition2011-2015. We began right at the start of the Kinect™ revolution when inexpensive infrared cameras providing image depth recordings became available. We published papers using this technology and other more conventional methods, including regular video cameras, to record data, thus providing a good overview of uses of machine learning and computervision using multimodal data in this area of application. Notably, we organized a series of challenges and made available several datasets we recorded for that purpose, including tens of thousands of videos, which are available to conduct further research. We also overview recent state of the art works on gesture recognition based on a proposed taxonomy for gesture recognition, discussing challenges and future lines of research.
暂无评论