Action recognition is an important topic in computer vision. Recently, deep learning technologies have been successfully used in lots of applications including video data for sloving recognition problems. However, mos...Action recognition is an important topic in computer vision. Recently, deep learning technologies have been successfully used in lots of applications including video data for sloving recognition problems. However, most existing deep learning based recognition frameworks are not optimized for action in the surveillance videos. In this paper, we propose a novel method to deal with the recognition of different types of actions in outdoor surveillance videos. The proposed method first introduces motion compensation to improve the detection of human target. Then, it uses three different types of deep models with single and sequenced images as inputs for the recognition of different types of actions. Finally, predictions from different models are fused with a linear model. Experimental results show that the proposed method works well on the real surveillance videos.展开更多
Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression...Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression is crucial for deploying deep neural network(DNN)models on resource-constrained embedded devices.展开更多
As a key property of hadrons,the total width is quite difficult to obtain in theory due to the extreme complexity of the strong and electroweak interactions.In this work,a deep neural network model with the Transforme...As a key property of hadrons,the total width is quite difficult to obtain in theory due to the extreme complexity of the strong and electroweak interactions.In this work,a deep neural network model with the Transformer architecture is built to precisely predict meson widths in the range of 10^(-14)-625 Me V based on meson quantum numbers and masses.The relative errors of the predictions are 0.12%,2.0%,and 0.54% in the training set,the test set,and all the data,respectively.We present the predicted meson width spectra for the currently discovered states and some theoretically predicted ones.The model is also used as a probe to study the quantum numbers and inner structures for some undetermined states,including the exotic states.Notably,this data-driven model is found to spontaneously exhibit good charge conjugation symmetry and approximate isospin symmetry consistent with physical principles.The results indicate that the deep neural network can serve as an independent complementary research paradigm to describe and explore the hadron structures and the complicated interactions in particle physics alongside traditional experimental measurements,theoretical calculations,and lattice simulations.展开更多
Super-pixel algorithms based on convolutional neural networks with fuzzy C-means clustering are widely used for high-spatial-resolution remote sensing images segmentation.However,this model requires the number of clus...Super-pixel algorithms based on convolutional neural networks with fuzzy C-means clustering are widely used for high-spatial-resolution remote sensing images segmentation.However,this model requires the number of clusters to be set manually,resulting in a low automation degree due to the complexity of the iterative clustering process.To address this problem,a segmentation method based on a self-learning super-pixel network(SLSP-Net)and modified automatic fuzzy clustering(MAFC)is proposed.SLSP-Net performs feature extraction,non-iterative clustering,and gradient reconstruction.A lightweight feature embedder is adopted for feature extraction,thus expanding the receiving range and generating multi-scale features.Automatic matching is used for non-iterative clustering,and the overfitting of the network model is overcome by adaptively adjusting the gradient weight parameters,providing a better irregular super-pixel neighborhood structure.An optimized density peak algorithm is adopted for MAFC.Based on the obtained super-pixel image,this maximizes the robust decision-making interval,which enhances the automation of regional clustering.Finally,prior entropy fuzzy C-means clustering is applied to optimize the robust decision-making and obtain the final segmentation result.Experimental results show that the proposed model offers reduced experimental complexity and achieves good performance,realizing not only automatic image segmentation,but also good segmentation results.展开更多
Training large-scale deep neural networks(DNNs)is prone to software and hardware failures,with critical failures often requiring full-machine reboots that substantially prolong training.Existing checkpoint-recovery so...Training large-scale deep neural networks(DNNs)is prone to software and hardware failures,with critical failures often requiring full-machine reboots that substantially prolong training.Existing checkpoint-recovery solutions either cannot tolerate such critical failures or suffer from slow checkpointing and recovery due to constrained input/output bandwidth.In this paper,we propose FastCheck,a checkpoint-recovery framework that accelerates checkpointing and recovery through parallel transmission and tailored compression.First,FastCheck partitions checkpoints into shards and leverages multiple nodes for parallel checkpointing and recovery.Second,it further reduces checkpoint size and overhead with delta compression for weights and index compression for momentum.Third,FastCheck employs lightweight and consistent health status maintenance that accurately tracks node health,preventing checkpoint transmission to failed nodes.We implement FastCheck in PyTorch and evaluate it on multiple DNN models against two baselines.Experimental results show that FastCheck reduces the checkpointing time by up to 78.42%and the recovery time by up to 77.41%,while consistently improving efficiency across different training stages.展开更多
文摘Action recognition is an important topic in computer vision. Recently, deep learning technologies have been successfully used in lots of applications including video data for sloving recognition problems. However, most existing deep learning based recognition frameworks are not optimized for action in the surveillance videos. In this paper, we propose a novel method to deal with the recognition of different types of actions in outdoor surveillance videos. The proposed method first introduces motion compensation to improve the detection of human target. Then, it uses three different types of deep models with single and sequenced images as inputs for the recognition of different types of actions. Finally, predictions from different models are fused with a linear model. Experimental results show that the proposed method works well on the real surveillance videos.
基金supported by the Science and Technology Innovation Key R&D Program of Chongqing(CSTB2025TIAD-STX0032)National Key Research and Development Program of China(2024YFF0908200)+1 种基金the Chongqing Technology Innovation and Application Development Special Key Project(CSTB2024TIAD-KPX0018)the Southwest University Graduate Student Research Innovation(SWUB24051)。
文摘Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression is crucial for deploying deep neural network(DNN)models on resource-constrained embedded devices.
基金supported by the National Key R&D Program of China(Grant No.2022YFA1604803)the Natural Science Basic Research Program of Shaanxi(Grant No.2025JC-YBMS-020)the National Natural Science Foundation of China(Grant Nos.12047503,12575097,12005169,12075301,and 11821505)。
文摘As a key property of hadrons,the total width is quite difficult to obtain in theory due to the extreme complexity of the strong and electroweak interactions.In this work,a deep neural network model with the Transformer architecture is built to precisely predict meson widths in the range of 10^(-14)-625 Me V based on meson quantum numbers and masses.The relative errors of the predictions are 0.12%,2.0%,and 0.54% in the training set,the test set,and all the data,respectively.We present the predicted meson width spectra for the currently discovered states and some theoretically predicted ones.The model is also used as a probe to study the quantum numbers and inner structures for some undetermined states,including the exotic states.Notably,this data-driven model is found to spontaneously exhibit good charge conjugation symmetry and approximate isospin symmetry consistent with physical principles.The results indicate that the deep neural network can serve as an independent complementary research paradigm to describe and explore the hadron structures and the complicated interactions in particle physics alongside traditional experimental measurements,theoretical calculations,and lattice simulations.
基金funded by Scientific and Technological Innovation Team of Universities in Henan Province,grant number 22IRTSTHN008Innovative Research Team(in Philosophy and Social Science)in University of Henan Province grant number 2022-CXTD-02the National Natural Science Foundation of China,grant number 41371524.
文摘Super-pixel algorithms based on convolutional neural networks with fuzzy C-means clustering are widely used for high-spatial-resolution remote sensing images segmentation.However,this model requires the number of clusters to be set manually,resulting in a low automation degree due to the complexity of the iterative clustering process.To address this problem,a segmentation method based on a self-learning super-pixel network(SLSP-Net)and modified automatic fuzzy clustering(MAFC)is proposed.SLSP-Net performs feature extraction,non-iterative clustering,and gradient reconstruction.A lightweight feature embedder is adopted for feature extraction,thus expanding the receiving range and generating multi-scale features.Automatic matching is used for non-iterative clustering,and the overfitting of the network model is overcome by adaptively adjusting the gradient weight parameters,providing a better irregular super-pixel neighborhood structure.An optimized density peak algorithm is adopted for MAFC.Based on the obtained super-pixel image,this maximizes the robust decision-making interval,which enhances the automation of regional clustering.Finally,prior entropy fuzzy C-means clustering is applied to optimize the robust decision-making and obtain the final segmentation result.Experimental results show that the proposed model offers reduced experimental complexity and achieves good performance,realizing not only automatic image segmentation,but also good segmentation results.
基金supported by the National Natural Science Foundation of China(Nos.62025203 and 62372419).
文摘Training large-scale deep neural networks(DNNs)is prone to software and hardware failures,with critical failures often requiring full-machine reboots that substantially prolong training.Existing checkpoint-recovery solutions either cannot tolerate such critical failures or suffer from slow checkpointing and recovery due to constrained input/output bandwidth.In this paper,we propose FastCheck,a checkpoint-recovery framework that accelerates checkpointing and recovery through parallel transmission and tailored compression.First,FastCheck partitions checkpoints into shards and leverages multiple nodes for parallel checkpointing and recovery.Second,it further reduces checkpoint size and overhead with delta compression for weights and index compression for momentum.Third,FastCheck employs lightweight and consistent health status maintenance that accurately tracks node health,preventing checkpoint transmission to failed nodes.We implement FastCheck in PyTorch and evaluate it on multiple DNN models against two baselines.Experimental results show that FastCheck reduces the checkpointing time by up to 78.42%and the recovery time by up to 77.41%,while consistently improving efficiency across different training stages.
