Due to factors such as motion blur,video out-of-focus,and occlusion,multi-frame human pose estimation is a challenging task.Exploiting temporal consistency between consecutive frames is an efficient approach for addre...Due to factors such as motion blur,video out-of-focus,and occlusion,multi-frame human pose estimation is a challenging task.Exploiting temporal consistency between consecutive frames is an efficient approach for addressing this issue.Currently,most methods explore temporal consistency through refinements of the final heatmaps.The heatmaps contain the semantics information of key points,and can improve the detection quality to a certain extent.However,they are generated by features,and feature-level refinements are rarely considered.In this paper,we propose a human pose estimation framework with refinements at the feature and semantics levels.We align auxiliary features with the features of the current frame to reduce the loss caused by different feature distributions.An attention mechanism is then used to fuse auxiliary features with current features.In terms of semantics,we use the difference information between adjacent heatmaps as auxiliary features to refine the current heatmaps.The method is validated on the large-scale benchmark datasets PoseTrack2017 and PoseTrack2018,and the results demonstrate the effectiveness of our method.展开更多
Studies have shown that the use of pulsar timing arrays(PTAs)is among the approaches with the highest potential to detect very low-frequency gravitational waves in the near future.Although the capture of gravitational...Studies have shown that the use of pulsar timing arrays(PTAs)is among the approaches with the highest potential to detect very low-frequency gravitational waves in the near future.Although the capture of gravitational waves(GWs)by PTAs has not been reported yet,many related theoretical studies and some meaningful detection limits have been reported.In this study,we focused on the nanohertz GWs from individual supermassive binary black holes.Given specific pulsars(PSR J1909-3744,PSR J1713+0747,PSR J0437-4715),the corresponding GW-induced timing residuals in PTAs with Gaussian white noise can be simulated.Further,we report the classification of the simulated PTA data and parameter estimation for potential GW sources using machine learning based on neural networks.As a classifier,the convolutional neural network shows high accuracy when the combined signal to noise ratio≥1.33 for our simulated data.Further,we applied a recurrent neural network to estimate the chirp mass(M)of the source and luminosity distance(Dp)of the pulsars and Bayesian neural networks(BNNs)to obtain the uncertainties of chirp mass estimation.Knowledge of the uncertainties is crucial to astrophysical observation.In our case,the mean relative error of chirp mass estimation is less than 13.6%.Although these results are achieved for simulated PTA data,we believe that they will be important for realizing intelligent processing in PTA data analysis.展开更多
In this paper, we study an application of deep learning to the advanced laser interferometer gravitational wave observatory(LIGO)and advanced Virgo coincident detection of gravitational waves(GWs) from compact binary ...In this paper, we study an application of deep learning to the advanced laser interferometer gravitational wave observatory(LIGO)and advanced Virgo coincident detection of gravitational waves(GWs) from compact binary star mergers. This deep learning method is an extension of the Deep Filtering method used by George and Huerta(2017) for multi-inputs of network detectors.Simulated coincident time series data sets in advanced LIGO and advanced Virgo detectors are analyzed for estimating source luminosity distance and sky location. As a classifier, our deep neural network(DNN) can effectively recognize the presence of GW signals when the optimal signal-to-noise ratio(SNR) of network detectors ≥ 9. As a predictor, it can also effectively estimate the corresponding source space parameters, including the luminosity distance D, right ascension α, and declination δ of the compact binary star mergers. When the SNR of the network detectors is greater than 8, their relative errors are all less than 23%.Our results demonstrate that Deep Filtering can process coincident GW time series inputs and perform effective classification and multiple space parameter estimation. Furthermore, we compare the results obtained from one, two, and three network detectors;these results reveal that a larger number of network detectors results in a better source location.展开更多
基金supported by the National Key Research and Development Program of China(Nos.2021YFC2009200 and 2023YFC3606100)the Special Project of Technological Innovation and Application Development of Chongqing,China(No.cstc2019jscx-msxmX0167)。
文摘Due to factors such as motion blur,video out-of-focus,and occlusion,multi-frame human pose estimation is a challenging task.Exploiting temporal consistency between consecutive frames is an efficient approach for addressing this issue.Currently,most methods explore temporal consistency through refinements of the final heatmaps.The heatmaps contain the semantics information of key points,and can improve the detection quality to a certain extent.However,they are generated by features,and feature-level refinements are rarely considered.In this paper,we propose a human pose estimation framework with refinements at the feature and semantics levels.We align auxiliary features with the features of the current frame to reduce the loss caused by different feature distributions.An attention mechanism is then used to fuse auxiliary features with current features.In terms of semantics,we use the difference information between adjacent heatmaps as auxiliary features to refine the current heatmaps.The method is validated on the large-scale benchmark datasets PoseTrack2017 and PoseTrack2018,and the results demonstrate the effectiveness of our method.
基金supported by the National Natural Science Foundation of China(Grant Nos.11873001,11725313,and 11690024)the Natural Science Foundation of Chongqing(Grant No.cstc2018jcyj AX0767)+2 种基金the National Key Research and Development Program of China(Grant No.2017YFA0402600)the CAS International Partnership Program(Grant No.114A11KYSB20160008)the CAS Strategic Priority Research Program(Grant No.XDB23000000)。
文摘Studies have shown that the use of pulsar timing arrays(PTAs)is among the approaches with the highest potential to detect very low-frequency gravitational waves in the near future.Although the capture of gravitational waves(GWs)by PTAs has not been reported yet,many related theoretical studies and some meaningful detection limits have been reported.In this study,we focused on the nanohertz GWs from individual supermassive binary black holes.Given specific pulsars(PSR J1909-3744,PSR J1713+0747,PSR J0437-4715),the corresponding GW-induced timing residuals in PTAs with Gaussian white noise can be simulated.Further,we report the classification of the simulated PTA data and parameter estimation for potential GW sources using machine learning based on neural networks.As a classifier,the convolutional neural network shows high accuracy when the combined signal to noise ratio≥1.33 for our simulated data.Further,we applied a recurrent neural network to estimate the chirp mass(M)of the source and luminosity distance(Dp)of the pulsars and Bayesian neural networks(BNNs)to obtain the uncertainties of chirp mass estimation.Knowledge of the uncertainties is crucial to astrophysical observation.In our case,the mean relative error of chirp mass estimation is less than 13.6%.Although these results are achieved for simulated PTA data,we believe that they will be important for realizing intelligent processing in PTA data analysis.
基金supported by the National Natural Science Foundation of China(Grant Nos.11873001,11633001,11673008,and 61501069)the Natural Science Foundation of Chongqing(Grant No.cstc2018jcyjAX0767)+4 种基金the Strategic Priority Program of the Chinese Academy of Sciences(Grant No.XDB23040100)Newton International Fellowship Alumni Followon Fundingthe Fundamental Research Funds for the Central Universities Project(Grant Nos.106112017CDJXFLX0014,and 106112016CDJXY300002)Chinese State Scholarship FundNewton International Fellowship Alumni Follow on Funding
文摘In this paper, we study an application of deep learning to the advanced laser interferometer gravitational wave observatory(LIGO)and advanced Virgo coincident detection of gravitational waves(GWs) from compact binary star mergers. This deep learning method is an extension of the Deep Filtering method used by George and Huerta(2017) for multi-inputs of network detectors.Simulated coincident time series data sets in advanced LIGO and advanced Virgo detectors are analyzed for estimating source luminosity distance and sky location. As a classifier, our deep neural network(DNN) can effectively recognize the presence of GW signals when the optimal signal-to-noise ratio(SNR) of network detectors ≥ 9. As a predictor, it can also effectively estimate the corresponding source space parameters, including the luminosity distance D, right ascension α, and declination δ of the compact binary star mergers. When the SNR of the network detectors is greater than 8, their relative errors are all less than 23%.Our results demonstrate that Deep Filtering can process coincident GW time series inputs and perform effective classification and multiple space parameter estimation. Furthermore, we compare the results obtained from one, two, and three network detectors;these results reveal that a larger number of network detectors results in a better source location.