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
Double-walled carbon nanotube （DWCNT） macro-films with large areas, excellent flexibility and superhydrophobicity are reported. The area of the macro-film is larger than 30 cm×15 cm, and this large film can be ...Double-walled carbon nanotube （DWCNT） macro-films with large areas, excellent flexibility and superhydrophobicity are reported. The area of the macro-film is larger than 30 cm×15 cm, and this large film can be bended, or folded without any damage, and even can be tailored freely. After a simple modification of perfluoroalkysilane, the surface of the macro-film shows excellent superhydrophobicity with a water contact angle of 165.74-2 deg. and sliding angle lower than 3 deg., the prepared superhydrophobic films showing excellent antifouling, self-cleaning and water-repellent functions. The topographic roughness and perfluoroalkysilane modification are found to contribute to the observed superhydrophobicity. Considering the outstanding electronic, chemical and mechanical properties of DWCNTs, it is expected that this multifunctional DWCNT macro-film has potential applications in many fields.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supports by the National Natural Science Foundation of China (No. 50871067)the National 863 Project (No. 2007AA05Z128) from the Ministry of Science and Technology of China
文摘Double-walled carbon nanotube （DWCNT） macro-films with large areas, excellent flexibility and superhydrophobicity are reported. The area of the macro-film is larger than 30 cm×15 cm, and this large film can be bended, or folded without any damage, and even can be tailored freely. After a simple modification of perfluoroalkysilane, the surface of the macro-film shows excellent superhydrophobicity with a water contact angle of 165.74-2 deg. and sliding angle lower than 3 deg., the prepared superhydrophobic films showing excellent antifouling, self-cleaning and water-repellent functions. The topographic roughness and perfluoroalkysilane modification are found to contribute to the observed superhydrophobicity. Considering the outstanding electronic, chemical and mechanical properties of DWCNTs, it is expected that this multifunctional DWCNT macro-film has potential applications in many fields.
