检索结果-内蒙古大学图书馆

spatial-temporal modeling for prediction of stylized human motion

NEUROCOMPUTING 2022年 511卷 34-42页

作者： Zhong, Chongyang Hu, Lei Xia, Shihong Chinese Acad Sci Inst Comp Technol Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

Human motion prediction refers to forecasting human motion in the future given a past motion sequence, which has significant applications in human tracking, automatic motion generation, autonomous driving, human-robotics interaction, etc. Previous works usually used RNN-based methods, focusing on modeling the temporal dynamics of human motion, which have made great effort on content motions. However, it is unclear for their performance on stylized motion, which is with more expressive emotions and states of the human motion. Different styles within the same motion type have similar motion patterns but also subtle variances. This makes it difficult to be predicted. The main idea of this paper is to learn the spatial characteristic of stylized motion and combine it with the temporal dynamics to achieve accurate prediction. We adopt a transformer-based style encoder to learn the motion representation in the pose space and then maps it to the latent space modeled by the constant variance Gaussian mixture model;meanwhile, we use the hierarchical multi-scale RNN as a temporal encoder to capture the temporal dynamics of human motion;finally, we feed the spatial and temporal features into the prediction decoder to predict the next frame. Our experiments on the Human 3.6 M and Stylized MotionDatasets demonstrate that our model has comparable prediction performance with the state-of-the-art motion prediction works on Human 3.6 M and outperforms previous works on stylized human motion prediction. (C) 2022 Elsevier B.V. All rights reserved.

关键词： stylized motion transformer human motion prediction spatial-temporal modeling constant variance GMM

来源：评论

学校读者我要写书评

暂无评论

spatial-temporal modeling of Neighborhood Sociodemographic Characteristics and Food Stores

引用

AMERICAN JOURNAL OF EPIDEMIOLOGY 2015年第2期181卷 137-150页

作者： Lamichhane, Archana P. Warren, Joshua L. Peterson, Marc Rummo, Pasquale Gordon-Larsen, Penny Univ N Carolina Gillings Sch Global Publ Hlth Dept Nutr Chapel Hill NC 27514 USA Univ N Carolina Gillings Sch Global Publ Hlth Dept Biostat Chapel Hill NC 27514 USA Yale Univ Sch Publ Hlth Dept Biostat New Haven CT USA Univ N Carolina Carolina Populat Ctr Chapel Hill NC 27514 USA

The literature on food stores, neighborhood poverty, and race/ethnicity is mixed and lacks methods of accounting for complex spatial and temporal clustering of food resources. We used quarterly data on supermarket and convenience store locations from Nielsen TDLinx (Nielsen Holdings N.V., New York, New York) spanning 7 years (2006-2012) and census tract-based neighborhood sociodemographic data from the American Community Survey (2006-2010) to assess associations between neighborhood sociodemographic characteristics and food store distributions in the Metropolitan Statistical Areas (MSAs) of 4 US cities (Birmingham, Alabama;Chicago, Illinois;Minneapolis, Minnesota;and San Francisco, California). We fitted a space-time Poisson regression model that accounted for the complex spatial-temporal correlation structure of store locations by introducing space-time random effects in an intrinsic conditionally autoregressive model within a Bayesian framework. After accounting for census tract-level area, population, their interaction, and spatial and temporal variability, census tract poverty was significantly and positively associated with increasing expected numbers of supermarkets among tracts in all 4 MSAs. A similar positive association was observed for convenience stores in Birmingham, Minneapolis, and San Francisco;in Chicago, a positive association was observed only for predominantly white and predominantly black tracts. Our findings suggest a positive association between greater numbers of food stores and higher neighborhood poverty, with implications for policy approaches related to food store access by neighborhood poverty.

关键词： food availability food stores intrinsic conditionally autoregressive model neighborhood characteristics poverty sociodemographic factors spatial-temporal modeling supermarkets

来源：评论

学校读者我要写书评

暂无评论

spatial-temporal modeling USING DEEP LEARNING FOR REAL-TIME MONITORING OF ADDITIVE MANUFACTURING

SPATIAL-TEMPORAL MODELING USING DEEP LEARNING FOR REAL-TIME ...

引用

ASME International Design Engineering Technical Conferences / 42nd Annual Computers and Information in Engineering Conference (IDETC-CIE)

作者： Ko, Hyunwoong Kim, Jaehyuk Lu, Yan Shin, Dongmin Yang, Zhuo Oh, Yosep Arizona State Univ Tempe AZ 85287 USA NIST Bethesda MD USA Pohang Univ Sci & Technol Pohang South Korea Hanyang Univ Seoul South Korea Univ Massachusetts Amherst MA 01003 USA Kyonggi Univ Suwon South Korea

ISBN: (纸本)9780791886212

Real-time monitoring for Additive Manufacturing (AM) processes can greatly benefit from spatial-temporal modeling using deep learning. However, existing, deep-learning approaches in AM are case-dependent, and therefore not robust to changes of control inputs and data types. As AM is dynamic and complex, this limitation leads to a lack of systematic, DL approaches for real-time monitoring of AM, which involves a large number of varying control parameters and monitoring data. To address the challenge, this paper introduces a novel approach for developing spatial-temporal models to monitor Laser Powder Bed Fusion (LPBF) processes using deep learning on real-time, monitoring data. First, we present a novel model for representing in-situ-monitoring and control data of LPBF at multiple scales. Second, from the model, we extract spatial-temporal relationships for in-situ monitoring of LPBF processes. Third, we present a spatial-temporal, modeling approach using the architecture of convolutional long short-term memory (LSTM) to monitor the spatial-temporal relationships and detect anomalies. A case study used convolutional LSTM Autoencoder on optical, melt- pool-monitoring data, one of the most widely adopted data types in in-situ monitoring of LPBF. The data was generated from an LPBF testbed called the Additive Manufacturing Metrology Testbed. The novel, learning approach enables spatial-temporal modeling of AM dynamics directly from real-time data for the monitoring of varying AM environments. This methodical approach provides the potential to fuse realtime data at multiple, spatial-temporal scales.

关键词： Deep Learning Laser Powder Bed Fusion spatial-temporal modeling Real-time

来源：评论

学校读者我要写书评

暂无评论

Fragment and Integrate Network (FIN): A Novel spatial-temporal modeling Based on Long Sequential Behavior for Online Food Ordering Click-Through Rate Prediction 23

Fragment and Integrate Network (FIN): A Novel Spatial-Tempor...

引用

32nd ACM International Conference on Information and Knowledge Management (CIKM)

作者： Li, Jun Zhang, Ge Alibaba Grp Beijing Peoples R China

ISBN: (纸本)9798400701245

spatial-temporal information has been proven to be of great significance for click-through rate prediction tasks in online Location-Based Services (LBS), especially in mainstream food ordering platforms such as DoorDash, Uber Eats, Meituan, and ***. modeling user spatial-temporal preferences with sequential behavior data has become a hot topic in recommendation systems and online advertising. However, most of existing methods either lack the representation of rich spatial-temporal information or only handle user behaviors with limited length, e.g. 100. In this paper, we tackle these problems by designing a new spatial-temporal modeling paradigm named Fragment and Integrate Network (FIN). FIN consists of two networks: (i) Fragment Network (FN) extracts Multiple Sub-Sequences (MSS) from lifelong sequential behavior data, and captures the specific spatial-temporal representation by modeling each MSS respectively. Here both a simplified attention and a complicated attention are adopted to balance the performance gain and resource consumption. (ii) Integrate Network (IN) builds a new integrated sequence by utilizing spatial-temporal interaction on MSS and captures the comprehensive spatial-temporal representation by modeling the integrated sequence with a complicated attention. Both public datasets and production datasets have demonstrated the accuracy and scalability of FIN. Since 2022, FIN has been fully deployed in the recommendation advertising system of ***, one of the most popular online food ordering platforms in China, obtaining 5.7% improvement on Click-Through Rate (CTR) and 7.3% increase on Revenue Per Mille (RPM).

关键词： Click-Through Rate Prediction Long Sequential Behavior spatial-temporal modeling Online Food Ordering

来源：评论

学校读者我要写书评

暂无评论

Joint spatial-temporal modeling and Contrastive Learning for Self-supervised Heart Rate Measurement 3

Joint Spatial-Temporal Modeling and Contrastive Learning for...

引用

3rd Vision-Based Remote Physiological Signal Sensing Challenge and Workshop, RePSS 2024

作者： Qian, Wei Li, Qi Li, Kun Wang, Xinke Sun, Xiao Wang, Meng Guo, Dan China Ministry of Education China Institute of Artificial Intelligence Hefei Comprehensive National Science Center China Anhui University China Zhejiang University China Anhui Zhonghuitong Technology Co. Ltd. China

This paper briefly introduces the solutions developed by our team, HFUT-VUT, for Track 1 of selfsupervised heart rate measurement in the 3rd Vision-based Remote Physiological Signal Sensing (RePSS) Challenge hosted at IJCAI 2024. The goal is to develop a self-supervised learning algorithm for heart rate (HR) estimation using unlabeled facial videos. To tackle this task, we present two self-supervised HR estimation solutions that integrate spatial-temporal modeling and contrastive learning, respectively. Specifically, we first propose a non-end-to-end self-supervised HR measurement framework based on spatial-temporal modeling, which can effectively capture subtle rPPG clues and leverage the inherent bandwidth and periodicity characteristics of rPPG to constrain the model. Meanwhile, we employ an excellent end-to-end solution based on contrastive learning, aiming to generalize across different scenarios from complementary perspectives. Finally, we combine the strengths of the above solutions through an ensemble strategy to generate the final predictions, leading to a more accurate HR estimation. As a result, our solutions achieved a remarkable RMSE score of 8.85277 on the test dataset, securing 2nd place in Track 1 of the challenge. © 2024 Copyright for this paper by its authors.

关键词： contrastive learning heart rate rPPG Self-supervised spatial-temporal modeling

来源：评论

学校读者我要写书评

暂无评论

Multi-Building Energy Forecasting Through Weather-Integrated temporal Graph Neural Networks

引用

BUILDINGS 2025年第5期15卷 808-808页

作者： Moveh, Samuel Merchan-Cruz, Emmanuel Alejandro Abuhussain, Maher Alhumaid, Saleh Almazam, Khaled Dodo, Yakubu Aminu Transport & Telecommun Inst Engn Fac LV-1019 Riga Latvia Umm Al Qura Univ Coll Engn & Comp Al Qunfudhah Dept Civil & Environm Engn Mecca 24221 Saudi Arabia Univ Hail Dept Mech Engn Hail 81481 Saudi Arabia Najran Univ Architectural Engn Dept Najran 66426 Saudi Arabia

While existing building energy prediction methods have advanced significantly, they face fundamental challenges in simultaneously modeling complex spatial-temporal relationships between buildings and integrating dynamic weather patterns, particularly in dense urban environments where building interactions significantly impact energy consumption patterns. This study presents an advanced deep learning system combining temporal graph neural networks with weather data parameters to enhance prediction accuracy across diverse building types through innovative spatial-temporal modeling. This approach integrates LSTM layers with graph convolutional networks, trained using energy consumption data from 150 commercial buildings over three years. The system incorporates spatial relationships through a weighted adjacency matrix considering building proximity and operational similarities, while weather parameters are integrated via a specialized neural network component. Performance evaluation examined normal operations, data gaps, and seasonal variations. The results demonstrated a 3.2% mean absolute percentage error (MAPE) for 15 min predictions and a 4.2% MAPE for 24 h forecasts. The system showed robust data recovery, maintaining 95.8% effectiveness even with 30% missing values. Seasonal analysis revealed consistent performance across weather conditions (MAPE: 3.1-3.4%). The approach achieved 33.3% better prediction accuracy compared to conventional methods, with 75% efficiency across four GPUs. These findings demonstrate the effectiveness of combining spatial relationships and weather parameters for building energy prediction, providing valuable insights for energy management systems and urban planning. The system's performance and scalability make it particularly suitable for practical applications in smart building management and urban sustainability.

关键词： building energy prediction temporal graph neural networks spatial-temporal modeling multi-building systems weather integration

来源：评论

学校读者我要写书评

暂无评论

RESTHT: relation-enhanced spatial-temporal hierarchical transformer for video captioning

引用

VISUAL COMPUTER 2025年第1期41卷 591-604页

作者： Zheng, Lihuan Xu, Wanru Miao, Zhenjiang Qiu, Xinxiu Gong, Shanshan Beijing Jiaotong Univ Inst Informat Sci 3 Shangyuancun Beijing 100044 Peoples R China

The video captioning task is generating description sentences by learning semantic information. It has a wide range of applications in areas such as video retrieval, automatic generation of subtitles and blind assistance. Visual semantic information plays a decisive role in video captioning. However, traditional methods are relatively rough for video feature modeling, failing to harness local and global features to understand temporal and spatial relationships. In this paper, we propose a video captioning model based on the Transformer and GCN network called "Relation-Enhanced spatial-temporal Hierarchical Transformer" (RESTHT). To address the above issues, we present a spatial-temporal hierarchical network framework to jointly model local and global features in terms of both time and space. For temporal modeling, our model learns the direct interactions between diverse video features and sentence features in the temporal sequence via the pre-trained GPT2, and the global feature construction encourages it to capture essential and relevant information. For spatial modeling, we use self-attention and GCN networks to learn the spatial relationship from appearance and motion perspectives jointly. Through spatial-temporal modeling, our method can comprehend the global time-space relationships of complex events in videos and catch the interaction between different objects to generate more accurate descriptions applicable to universal video captioning tasks. We conducted experiments on two widely used datasets, and especially in the MSVD dataset, our model improves the score of CIDEr by 6.1 compared to the baseline and excels present methods by 13. The results verify that our model can fully model the temporal and spatial relationship and outperforms other related models.

关键词： Video captioning spatial-temporal modeling Transformer GCN

来源：评论

学校读者我要写书评

暂无评论

Memory-MambaNav: Enhancing object-goal navigation through integration of spatial-temporal scanning with state space models

引用

IMAGE AND VISION COMPUTING 2025年 158卷

作者： Sun, Leyuan Yoshiyasu, Yusuke Natl Inst Adv Ind Sci & Technol Artificial Intelligence Res Ctr AIRC Comp Vis Res Team Tsukuba Ibaraki 3058560 Japan Natl Inst Adv Ind Sci & Technol CNRS AIST Joint Robot Lab JRL IRL Tsukuba Ibaraki 3058560 Japan

Object-goal Navigation (ObjectNav) involves locating a specified target object using a textual command combined with semantic understanding in an unknown environment. This requires the embodied agent to have advanced spatial and temporal comprehension about environment during navigation. While earlier approaches focus on spatial modeling, they either do not utilize episodic temporal memory (e.g., keeping track of explored and unexplored spaces) or are computationally prohibitive, as long-horizon memory knowledge is resource-intensive in both storage and training. To address this issue, this paper introduces the MemoryMambaNav model, which employs multiple Mamba-based layers for refined spatial-temporal modeling. Leveraging the Mamba architecture, known for its global receptive field and linear complexity, MemoryMambaNav can efficiently extract and process memory knowledge from accumulated historical observations. To enhance spatial modeling, we introduce the Memory spatial Difference State Space Model (MSD-SSM) to address the limitations of previous CNN and Transformer-based models in terms of receptive field and computational demand. For temporal modeling, the proposed Memory temporal Serialization SSM (MTSSSM) leverages Mamba's selective scanning capabilities in a cross-temporal manner, enhancing the model's temporal understanding and interaction with bi-temporal features. We also integrate memory-aggregated egocentric obstacle-awareness embeddings (MEOE) and memory-based fine-grained rewards into our end-to-end policy training, which improve obstacle understanding and accelerate convergence by fully utilizing memory knowledge. Our experiments on the AI2-Thor dataset confirm the benefits and superior performance of proposed Memory-MambaNav, demonstrating Mamba's potential in ObjectNav, particularly in long-horizon trajectories. All demonstration videos referenced in this paper can be viewed on the webpage (https:// ***/Memory-MambaNav).

关键词： Embodied artificial intelligence Robotic vision Object-goal navigation State space models spatial-temporal modeling Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

High and Low Frequency Attention Network for Long-Term Traffic Flow Prediction

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年

作者： Hu, Jia Baldi, Simone Southeast Univ Sch Cyber Sci & Engn Nanjing 210096 Peoples R China Southeast Univ Sch Cyber Sci & Engn Nanjing 210096 Peoples R China Southeast Univ Sch Math Nanjing 210096 Peoples R China

While several methods for short-term traffic prediction have been proposed in the literature, modeling the interaction between short-term and long-term traffic dynamics remains a major challenge. To address this problem, we propose a deep learning architecture named High and Low Frequency Attention Network (HLFNet) with the capability to capture multi-scale spatio-temporal dynamics. HLFNet takes inspiration from the frequency domain analysis in signal processing, where short-term (fast) and long-term (slow) dynamics are characterized in terms of high and low frequency, respectively. Specifically, we design a multi-scale attention block considering multi-grained feature information at different frequencies. The attention block comprises: a high-frequency attention operation for extracting fine-grained information within a local window;a low-frequency attention operation for extracting coarse-grained information within average pooled features. To capture the spatial interactions within the traffic network, HLFNet further considers three spatial embeddings: distance-based, attribute-based and potential-based. Experimental results with real-world traffic datasets using different prediction horizons and granularities show that, no matter how state-of-the-art methods are good at predicting in the short term, they fail to capture long-term trends. On the other hand, HLFNet retains a consistent prediction performance in both the short and the long term, outperforming all tested state-of-the-art methods in long-term traffic prediction.

关键词： Feature extraction Predictive models Attention mechanisms Data mining Correlation Computational modeling Transformers Graph neural networks Deep learning Accuracy Traffic prediction spatial-temporal modeling multi-scale modeling attention network

来源：评论

学校读者我要写书评

暂无评论

HSTI: A Light Hierarchical spatial-temporal Interaction Model for Map-Free Trajectory Prediction

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第6期26卷 9037-9046页

作者： Luo, Xiaoyang Fu, Shuaiqi Gao, Baolin Zhao, Yanan Tan, Huachun Song, Zeye Beijing Inst Technol Sch Mech Engn Beijing 100811 Peoples R China Tsinghua Univ Sch Vehicle & Mobil Beijing 100084 Peoples R China Beijing Inst Technol Sch Mech Engn Beijing 100811 Peoples R China Beijing Inst Technol Zhuhai 519087 Peoples R China Beijing Inst Technol Adv Res Inst Multidisciplinary Sci Beijing 100811 Peoples R China

Trajectory prediction is a crucial task for autonomous driving, but current models' reliance on high-definition (HD) maps limits their broader applicability. To cope with this challenge, we propose a novel map-free trajectory prediction method that leverages spatiotemporal attention mechanisms. The method consists of three key stages: 1) we first encode spatial and temporal features separately using spatial and temporal attention mechanisms, 2) we then model spatial and temporal interactions through Crystal Graph Convolutional Networks (CGCN) and Multi-Head Attention (MHA), 3) finally, an adaptive anchor generation technique is introduced to tackle the multimodal trajectory prediction challenge. This self-adaptive technique generates context-specific anchors, enabling accurate prediction of multiple possible future vehicle trajectories. Extensive experiments on the Argoverse1 and V2X-Seq datasets validate the effectiveness of our approach. On the Argoverse1 dataset, our method outperforms CRAT-Pred by 5.8% in minADE and 6.25% in minFDE. On the V2X-Seq dataset, it achieves improvements of 82.6%, 85.1%, and 44.0% in minADE, minFDE, and MR, respectively, compared to the baseline model.

关键词： Trajectory Predictive models Adaptation models Feature extraction Vectors Computational modeling Silicon Autonomous vehicles Accuracy Spatiotemporal phenomena Autonomous driving trajectory prediction map-free spatial-temporal modeling

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：