Daiming Qu

Yinuo Mei, Daiming Qu

An approach to selecting information indices for polar codes is proposed to form signals with spectral comb shapes under BPSK modulation, whereby the signal could be separated from periodic interference in spectrum. By confining information indices to an index set termed comb-shaping index set (CIS) proposed in this paper, a spectral comb shape signal is formed, which has periodic nulls and notch bands in its spectrum. Furthermore, we propose a novel construction for polar coding under the CIS constraint. Numerical results are given under periodic interference and AWGN noise, indicating that a considerable signal-to-noise power ratio (SNR) gain is accomplished in comparison with conventional polar codes.

Yong Huang, Ben Chen, Daiming Qu

Eye gaze estimation has become increasingly significant in computer vision.In this paper,we systematically study the mainstream of eye gaze estimation methods,propose a novel methodology to estimate eye gaze points and eye gaze directions simultaneously.First,we construct a local sharing network for feature extraction of gaze points and gaze directions estimation,which can reduce network computational parameters and converge quickly;Second,we propose a Multiview Multitask Learning (MTL) framework,for gaze directions,a coplanar constraint is proposed for the left and right eyes,for gaze points,three views data input indirectly introduces eye position information,a cross-view pooling module is designed, propose joint loss which handle both gaze points and gaze directions estimation.Eventually,we collect a dataset to use of gaze points,which have three views to exist public dataset.The experiment show our method is state-of-the-art the current mainstream methods on two indicators of gaze points and gaze directions.