The mining sector historically drove the global economy but at the expense of severe environmental and health repercussions,posing sustainability challenges[1]-[3].Recent advancements on artificial intelligence(AI)are...The mining sector historically drove the global economy but at the expense of severe environmental and health repercussions,posing sustainability challenges[1]-[3].Recent advancements on artificial intelligence(AI)are revolutionizing mining through robotic and data-driven innovations[4]-[7].While AI offers mining industry advantages,it is crucial to acknowledge the potential risks associated with its widespread use.Over-reliance on AI may lead to a loss of human control over mining operations in the future,resulting in unpredictable consequences.展开更多
Due to ever-growing soccer data collection approaches and progressing artificial intelligence(AI) methods, soccer analysis, evaluation, and decision-making have received increasing interest from not only the professio...Due to ever-growing soccer data collection approaches and progressing artificial intelligence(AI) methods, soccer analysis, evaluation, and decision-making have received increasing interest from not only the professional sports analytics realm but also the academic AI research community. AI brings gamechanging approaches for soccer analytics where soccer has been a typical benchmark for AI research. The combination has been an emerging topic. In this paper, soccer match analytics are taken as a complete observation-orientation-decision-action(OODA) loop.In addition, as in AI frameworks such as that for reinforcement learning, interacting with a virtual environment enables an evolving model. Therefore, both soccer analytics in the real world and virtual domains are discussed. With the intersection of the OODA loop and the real-virtual domains, available soccer data, including event and tracking data, and diverse orientation and decisionmaking models for both real-world and virtual soccer matches are comprehensively reviewed. Finally, some promising directions in this interdisciplinary area are pointed out. It is claimed that paradigms for both professional sports analytics and AI research could be combined. Moreover, it is quite promising to bridge the gap between the real and virtual domains for soccer match analysis and decision-making.展开更多
Traditional expert-designed branching rules in branch-and-bound(B&B) are static, often failing to adapt to diverse and evolving problem instances. Crafting these rules is labor-intensive, and may not scale well wi...Traditional expert-designed branching rules in branch-and-bound(B&B) are static, often failing to adapt to diverse and evolving problem instances. Crafting these rules is labor-intensive, and may not scale well with complex problems.Given the frequent need to solve varied combinatorial optimization problems, leveraging statistical learning to auto-tune B&B algorithms for specific problem classes becomes attractive. This paper proposes a graph pointer network model to learn the branch rules. Graph features, global features and historical features are designated to represent the solver state. The graph neural network processes graph features, while the pointer mechanism assimilates the global and historical features to finally determine the variable on which to branch. The model is trained to imitate the expert strong branching rule by a tailored top-k Kullback-Leibler divergence loss function. Experiments on a series of benchmark problems demonstrate that the proposed approach significantly outperforms the widely used expert-designed branching rules. It also outperforms state-of-the-art machine-learning-based branch-and-bound methods in terms of solving speed and search tree size on all the test instances. In addition, the model can generalize to unseen instances and scale to larger instances.展开更多
Monocular 3D object detection is challenging due to the lack of accurate depth information.Some methods estimate the pixel-wise depth maps from off-the-shelf depth estimators and then use them as an additional input t...Monocular 3D object detection is challenging due to the lack of accurate depth information.Some methods estimate the pixel-wise depth maps from off-the-shelf depth estimators and then use them as an additional input to augment the RGB images.Depth-based methods attempt to convert estimated depth maps to pseudo-LiDAR and then use LiDAR-based object detectors or focus on the perspective of image and depth fusion learning.However,they demonstrate limited performance and efficiency as a result of depth inaccuracy and complex fusion mode with convolutions.Different from these approaches,our proposed depth-guided vision transformer with a normalizing flows(NF-DVT)network uses normalizing flows to build priors in depth maps to achieve more accurate depth information.Then we develop a novel Swin-Transformer-based backbone with a fusion module to process RGB image patches and depth map patches with two separate branches and fuse them using cross-attention to exchange information with each other.Furthermore,with the help of pixel-wise relative depth values in depth maps,we develop new relative position embeddings in the cross-attention mechanism to capture more accurate sequence ordering of input tokens.Our method is the first Swin-Transformer-based backbone architecture for monocular 3D object detection.The experimental results on the KITTI and the challenging Waymo Open datasets show the effectiveness of our proposed method and superior performance over previous counterparts.展开更多
An effective approach is proposed for 3D urban scene reconstruction in the form of point cloud with semantic labeling. Starting from high resolution oblique aerial images,our approach proceeds through three main stage...An effective approach is proposed for 3D urban scene reconstruction in the form of point cloud with semantic labeling. Starting from high resolution oblique aerial images,our approach proceeds through three main stages: geographic reconstruction, geometrical reconstruction and semantic reconstruction. The absolute position and orientation of all the cameras relative to the real world are recovered in the geographic reconstruction stage. Then, in the geometrical reconstruction stage,an improved multi-view stereo matching method is employed to produce 3D dense points with color and normal information by taking into account the prior knowledge of aerial imagery.Finally the point cloud is classified into three classes(building,vegetation, and ground) by a rule-based hierarchical approach in the semantic reconstruction step. Experiments on complex urban scene show that our proposed 3-stage approach could generate reasonable reconstruction result robustly and efficiently.By comparing our final semantic reconstruction result with the manually labeled ground truth, classification accuracies from86.75% to 93.02% are obtained.展开更多
A review of our experience in range of electron spectroscopy of the physical vapor-phase deposition and growth of single- and multilayer nanostructures with atomic scale interfaces is presented. The foundation of an i...A review of our experience in range of electron spectroscopy of the physical vapor-phase deposition and growth of single- and multilayer nanostructures with atomic scale interfaces is presented. The foundation of an innovative methodology for the combined AES-EELS analysis of layered nanostructures is developed. The methodology includes: 1) determination of the composition, thickness, and the mechanism of phase transitions in nanocoatings under the probing depth most appropriated for the range of film thickness 1 - 10 ML;2) quantitative iteration Auger-analysis of the composition, thickness and growth mechanism of nanocoating;3) structural and phase analysis of nanocoatings with use of the analysis of position, shape and energy of the plasmon EELS peak and with subtracting the contribution from the substrate;4) analysis of phase transitions with use of the shift of the plasmon Auger-satellite and 5) non-destructive profiling of the composition of nanocoatings over depth with use of a dependence of the intensity and energy of EELS peaks on the value of the primary electron energy.展开更多
The video compression sensing method based onmulti hypothesis has attracted extensive attention in the research of video codec with limited resources.However,the formation of high-quality prediction blocks in the mult...The video compression sensing method based onmulti hypothesis has attracted extensive attention in the research of video codec with limited resources.However,the formation of high-quality prediction blocks in the multi hypothesis prediction stage is a challenging task.To resolve this problem,this paper constructs a novel compressed sensing-based high-quality adaptive video reconstruction optimizationmethod.Itmainly includes the optimization of prediction blocks(OPBS),the selection of searchwindows and the use of neighborhood information.Specifically,the OPBS consists of two parts:the selection of blocks and the optimization of prediction blocks.We combine the high-quality optimization reconstruction of foreground block with the residual reconstruction of the background block to improve the overall reconstruction effect of the video sequence.In addition,most of the existing methods based on predictive residual reconstruction ignore the impact of search windows and reference frames on performance.Therefore,Block-level search window(BSW)is constructed to cover the position of the optimal hypothesis block as much as possible.To maximize the availability of reference frames,Nearby reference frame information(NRFI)is designed to reconstruct the current block.The proposed method effectively suppresses the influence of the fluctuation of the prediction block on reconstruction and improves the reconstruction performance.Experimental results showthat the proposed compressed sensing-based high-quality adaptive video reconstruction optimization method significantly improves the reconstruction performance in both objective and supervisor quality.展开更多
One of the challenges of face recognition in surveillance is the low resolution of face region. Therefore many superresolution(SR) face reconstruction methods are proposed to produce a high-resolution face image from ...One of the challenges of face recognition in surveillance is the low resolution of face region. Therefore many superresolution(SR) face reconstruction methods are proposed to produce a high-resolution face image from one or a set of low-resolution face images. However, existing dictionary learning based algorithms are sensitive to noise and very time-consuming.In this paper, we define and prove the multi-scale linear combination consistency. In order to improve the performance of SR, we propose a novel SR face reconstruction method based on nonlocal similarity and multi-scale linear combination consistency(NLS-MLC). We further proposed a new recognition approach for very low resolution face images based on resolution scale invariant feature(RSIF). A series of experiments are conducted on two public face image databases to test feasibility of our proposed methods. Experimental results show that the proposed SR method is more robust and computationally effective in face hallucination, and the recognition accuracy of RSIF is higher than some state-of-art algorithms.展开更多
This paper presents a novel medical image registration algorithm named total variation constrained graphregularization for non-negative matrix factorization(TV-GNMF).The method utilizes non-negative matrix factorizati...This paper presents a novel medical image registration algorithm named total variation constrained graphregularization for non-negative matrix factorization(TV-GNMF).The method utilizes non-negative matrix factorization by total variation constraint and graph regularization.The main contributions of our work are the following.First,total variation is incorporated into NMF to control the diffusion speed.The purpose is to denoise in smooth regions and preserve features or details of the data in edge regions by using a diffusion coefficient based on gradient information.Second,we add graph regularization into NMF to reveal intrinsic geometry and structure information of features to enhance the discrimination power.Third,the multiplicative update rules and proof of convergence of the TV-GNMF algorithm are given.Experiments conducted on datasets show that the proposed TV-GNMF method outperforms other state-of-the-art algorithms.展开更多
The number of available control sources is a limiting factor to many network control tasks.A lack of input sources can result in compromised controllability and/or sub-optimal network performance,as noted in engineeri...The number of available control sources is a limiting factor to many network control tasks.A lack of input sources can result in compromised controllability and/or sub-optimal network performance,as noted in engineering applications such as the smart grids.The mechanism can be explained by a linear timeinvariant model,where structural controllability sets a lower bound on the number of required sources.Inspired by the ubiquity of time-varying topologies in the real world,we propose the strategy of spatiotemporal input control to overcome the source-related limit by exploiting temporal variation of the network topology.We theoretically prove that under this regime,the required number of sources can always be reduced to 2.It is further shown that the cost of control depends on two hyperparameters,the numbers of sources and intervals,in a trade-off fashion.As a demonstration,we achieve controllability over a complex network resembling the nervous system of Caenorhabditis elegans using as few as 6%of the sources predicted by a static control model.This example underlines the potential of utilizing topological variation in complex network control problems.展开更多
This paper investigates sampling dependent stability for aperiodic sampled-data systems by employing a Lyapunov-like functional that is time-dependent,and not imposed to be definite positive.Based on the system inform...This paper investigates sampling dependent stability for aperiodic sampled-data systems by employing a Lyapunov-like functional that is time-dependent,and not imposed to be definite positive.Based on the system information on the sampling interval wholly rather than partly,a new Lyapunovlike functional is constructed,which extends existing ones by introducing the integral of the system state and the cross terms among this integral and the sampled state.To take advantage of the integral of the system state,integral equations of the sampled-data system are explored when estimating the derivative of the extended functional.By the Lyapunov-like functional theory,a new sampling dependent stability result is obtained for sampled-data systems without uncertainties.Then,the stability result is applied to sampled-data systems with polytopic uncertainties and a robust stability result is derived.At last,numerical examples are given to illustrate that the stability results improve over some existing ones.展开更多
文摘The mining sector historically drove the global economy but at the expense of severe environmental and health repercussions,posing sustainability challenges[1]-[3].Recent advancements on artificial intelligence(AI)are revolutionizing mining through robotic and data-driven innovations[4]-[7].While AI offers mining industry advantages,it is crucial to acknowledge the potential risks associated with its widespread use.Over-reliance on AI may lead to a loss of human control over mining operations in the future,resulting in unpredictable consequences.
基金supported by the National Key Research,Development Program of China (2020AAA0103404)the Beijing Nova Program (20220484077)the National Natural Science Foundation of China (62073323)。
文摘Due to ever-growing soccer data collection approaches and progressing artificial intelligence(AI) methods, soccer analysis, evaluation, and decision-making have received increasing interest from not only the professional sports analytics realm but also the academic AI research community. AI brings gamechanging approaches for soccer analytics where soccer has been a typical benchmark for AI research. The combination has been an emerging topic. In this paper, soccer match analytics are taken as a complete observation-orientation-decision-action(OODA) loop.In addition, as in AI frameworks such as that for reinforcement learning, interacting with a virtual environment enables an evolving model. Therefore, both soccer analytics in the real world and virtual domains are discussed. With the intersection of the OODA loop and the real-virtual domains, available soccer data, including event and tracking data, and diverse orientation and decisionmaking models for both real-world and virtual soccer matches are comprehensively reviewed. Finally, some promising directions in this interdisciplinary area are pointed out. It is claimed that paradigms for both professional sports analytics and AI research could be combined. Moreover, it is quite promising to bridge the gap between the real and virtual domains for soccer match analysis and decision-making.
基金supported by the Open Project of Xiangjiang Laboratory (22XJ02003)Scientific Project of the National University of Defense Technology (NUDT)(ZK21-07, 23-ZZCX-JDZ-28)+1 种基金the National Science Fund for Outstanding Young Scholars (62122093)the National Natural Science Foundation of China (72071205)。
文摘Traditional expert-designed branching rules in branch-and-bound(B&B) are static, often failing to adapt to diverse and evolving problem instances. Crafting these rules is labor-intensive, and may not scale well with complex problems.Given the frequent need to solve varied combinatorial optimization problems, leveraging statistical learning to auto-tune B&B algorithms for specific problem classes becomes attractive. This paper proposes a graph pointer network model to learn the branch rules. Graph features, global features and historical features are designated to represent the solver state. The graph neural network processes graph features, while the pointer mechanism assimilates the global and historical features to finally determine the variable on which to branch. The model is trained to imitate the expert strong branching rule by a tailored top-k Kullback-Leibler divergence loss function. Experiments on a series of benchmark problems demonstrate that the proposed approach significantly outperforms the widely used expert-designed branching rules. It also outperforms state-of-the-art machine-learning-based branch-and-bound methods in terms of solving speed and search tree size on all the test instances. In addition, the model can generalize to unseen instances and scale to larger instances.
基金supported in part by the Major Project for New Generation of AI (2018AAA0100400)the National Natural Science Foundation of China (61836014,U21B2042,62072457,62006231)the InnoHK Program。
文摘Monocular 3D object detection is challenging due to the lack of accurate depth information.Some methods estimate the pixel-wise depth maps from off-the-shelf depth estimators and then use them as an additional input to augment the RGB images.Depth-based methods attempt to convert estimated depth maps to pseudo-LiDAR and then use LiDAR-based object detectors or focus on the perspective of image and depth fusion learning.However,they demonstrate limited performance and efficiency as a result of depth inaccuracy and complex fusion mode with convolutions.Different from these approaches,our proposed depth-guided vision transformer with a normalizing flows(NF-DVT)network uses normalizing flows to build priors in depth maps to achieve more accurate depth information.Then we develop a novel Swin-Transformer-based backbone with a fusion module to process RGB image patches and depth map patches with two separate branches and fuse them using cross-attention to exchange information with each other.Furthermore,with the help of pixel-wise relative depth values in depth maps,we develop new relative position embeddings in the cross-attention mechanism to capture more accurate sequence ordering of input tokens.Our method is the first Swin-Transformer-based backbone architecture for monocular 3D object detection.The experimental results on the KITTI and the challenging Waymo Open datasets show the effectiveness of our proposed method and superior performance over previous counterparts.
基金supported in part by the National Natural Science Foundation of China (61421004,61402316,61333015,61632003)Doctoral Research Fund of Taiyuan University of Science and Technology under grant (20162009)National Key Technologies R&D Program(2016YFB0502002)
文摘An effective approach is proposed for 3D urban scene reconstruction in the form of point cloud with semantic labeling. Starting from high resolution oblique aerial images,our approach proceeds through three main stages: geographic reconstruction, geometrical reconstruction and semantic reconstruction. The absolute position and orientation of all the cameras relative to the real world are recovered in the geographic reconstruction stage. Then, in the geometrical reconstruction stage,an improved multi-view stereo matching method is employed to produce 3D dense points with color and normal information by taking into account the prior knowledge of aerial imagery.Finally the point cloud is classified into three classes(building,vegetation, and ground) by a rule-based hierarchical approach in the semantic reconstruction step. Experiments on complex urban scene show that our proposed 3-stage approach could generate reasonable reconstruction result robustly and efficiently.By comparing our final semantic reconstruction result with the manually labeled ground truth, classification accuracies from86.75% to 93.02% are obtained.
文摘A review of our experience in range of electron spectroscopy of the physical vapor-phase deposition and growth of single- and multilayer nanostructures with atomic scale interfaces is presented. The foundation of an innovative methodology for the combined AES-EELS analysis of layered nanostructures is developed. The methodology includes: 1) determination of the composition, thickness, and the mechanism of phase transitions in nanocoatings under the probing depth most appropriated for the range of film thickness 1 - 10 ML;2) quantitative iteration Auger-analysis of the composition, thickness and growth mechanism of nanocoating;3) structural and phase analysis of nanocoatings with use of the analysis of position, shape and energy of the plasmon EELS peak and with subtracting the contribution from the substrate;4) analysis of phase transitions with use of the shift of the plasmon Auger-satellite and 5) non-destructive profiling of the composition of nanocoatings over depth with use of a dependence of the intensity and energy of EELS peaks on the value of the primary electron energy.
基金supported by the National Natural Science Foundation of China under Grant No.61806138KeyR&DProgram of Shanxi Province(International Cooperation)under Grant No.201903D421048+1 种基金National Key Research and Development Program of China under Grant No.2018YFC1604000School Level Postgraduate Education Innovation Projects under Grant No.XCX212082.
文摘The video compression sensing method based onmulti hypothesis has attracted extensive attention in the research of video codec with limited resources.However,the formation of high-quality prediction blocks in the multi hypothesis prediction stage is a challenging task.To resolve this problem,this paper constructs a novel compressed sensing-based high-quality adaptive video reconstruction optimizationmethod.Itmainly includes the optimization of prediction blocks(OPBS),the selection of searchwindows and the use of neighborhood information.Specifically,the OPBS consists of two parts:the selection of blocks and the optimization of prediction blocks.We combine the high-quality optimization reconstruction of foreground block with the residual reconstruction of the background block to improve the overall reconstruction effect of the video sequence.In addition,most of the existing methods based on predictive residual reconstruction ignore the impact of search windows and reference frames on performance.Therefore,Block-level search window(BSW)is constructed to cover the position of the optimal hypothesis block as much as possible.To maximize the availability of reference frames,Nearby reference frame information(NRFI)is designed to reconstruct the current block.The proposed method effectively suppresses the influence of the fluctuation of the prediction block on reconstruction and improves the reconstruction performance.Experimental results showthat the proposed compressed sensing-based high-quality adaptive video reconstruction optimization method significantly improves the reconstruction performance in both objective and supervisor quality.
基金supported by China Postdoctoral Science Foundation(2015M582355)the Doctor Scientific Research Start Project from Hubei University of Science and Technology(BK1418)National Natural Science Foundation of China(61271256)
文摘One of the challenges of face recognition in surveillance is the low resolution of face region. Therefore many superresolution(SR) face reconstruction methods are proposed to produce a high-resolution face image from one or a set of low-resolution face images. However, existing dictionary learning based algorithms are sensitive to noise and very time-consuming.In this paper, we define and prove the multi-scale linear combination consistency. In order to improve the performance of SR, we propose a novel SR face reconstruction method based on nonlocal similarity and multi-scale linear combination consistency(NLS-MLC). We further proposed a new recognition approach for very low resolution face images based on resolution scale invariant feature(RSIF). A series of experiments are conducted on two public face image databases to test feasibility of our proposed methods. Experimental results show that the proposed SR method is more robust and computationally effective in face hallucination, and the recognition accuracy of RSIF is higher than some state-of-art algorithms.
基金supported by the National Natural Science Foundation of China(61702251,41971424,61701191,U1605254)the Natural Science Basic Research Plan in Shaanxi Province of China(2018JM6030)+4 种基金the Key Technical Project of Fujian Province(2017H6015)the Science and Technology Project of Xiamen(3502Z20183032)the Doctor Scientific Research Starting Foundation of Northwest University(338050050)Youth Academic Talent Support Program of Northwest University(360051900151)the Natural Sciences and Engineering Research Council of Canada,Canada。
文摘This paper presents a novel medical image registration algorithm named total variation constrained graphregularization for non-negative matrix factorization(TV-GNMF).The method utilizes non-negative matrix factorization by total variation constraint and graph regularization.The main contributions of our work are the following.First,total variation is incorporated into NMF to control the diffusion speed.The purpose is to denoise in smooth regions and preserve features or details of the data in edge regions by using a diffusion coefficient based on gradient information.Second,we add graph regularization into NMF to reveal intrinsic geometry and structure information of features to enhance the discrimination power.Third,the multiplicative update rules and proof of convergence of the TV-GNMF algorithm are given.Experiments conducted on datasets show that the proposed TV-GNMF method outperforms other state-of-the-art algorithms.
基金partially supported by the National Key RD Program of China(2020AAA0105200,2018AAA01012600)National Natural Science Foundation of China(61876215)+5 种基金Beijing Academy of Artificial Intelligence(BAAI)in part by the Science and Technology Major Project of Guangzhou(202007030006)Pengcheng laboratorypartially funded by the Ministry of Education,Singapore,under contract RG19/20partly supported by the Future Resilient Systems Project(FRS-Ⅱ)at the Singapore-ETH Centre(SEC)funded by the National Research Foundation of Singapore(NRF)。
文摘The number of available control sources is a limiting factor to many network control tasks.A lack of input sources can result in compromised controllability and/or sub-optimal network performance,as noted in engineering applications such as the smart grids.The mechanism can be explained by a linear timeinvariant model,where structural controllability sets a lower bound on the number of required sources.Inspired by the ubiquity of time-varying topologies in the real world,we propose the strategy of spatiotemporal input control to overcome the source-related limit by exploiting temporal variation of the network topology.We theoretically prove that under this regime,the required number of sources can always be reduced to 2.It is further shown that the cost of control depends on two hyperparameters,the numbers of sources and intervals,in a trade-off fashion.As a demonstration,we achieve controllability over a complex network resembling the nervous system of Caenorhabditis elegans using as few as 6%of the sources predicted by a static control model.This example underlines the potential of utilizing topological variation in complex network control problems.
基金the Natural Science Foundation of China under Grant No.61374090the Program for Scientific Research Innovation Team in Colleges and Universities of Shandong Provincethe Taishan Scholarship Project of Shandong Province。
文摘This paper investigates sampling dependent stability for aperiodic sampled-data systems by employing a Lyapunov-like functional that is time-dependent,and not imposed to be definite positive.Based on the system information on the sampling interval wholly rather than partly,a new Lyapunovlike functional is constructed,which extends existing ones by introducing the integral of the system state and the cross terms among this integral and the sampled state.To take advantage of the integral of the system state,integral equations of the sampled-data system are explored when estimating the derivative of the extended functional.By the Lyapunov-like functional theory,a new sampling dependent stability result is obtained for sampled-data systems without uncertainties.Then,the stability result is applied to sampled-data systems with polytopic uncertainties and a robust stability result is derived.At last,numerical examples are given to illustrate that the stability results improve over some existing ones.
