中文
相关论文

相关论文: Exploring Over-stationarization in Deep Learning-b…

200 篇论文

Forecasting vehicle behavior within complex traffic environments is pivotal within Intelligent Transportation Systems (ITS). Though this technology plays a significant role in alleviating the prevalent operational difficulties in logistics…

机器人学 · 计算机科学 2025-01-03 Ouhan Huang , Huanle Rao , Xiaowen Cai , Tianyun Wang , Aolong Sun , Sizhe Xing , Yifan Sun , Gangyong Jia

Dataset Distillation is used to create a concise, yet informative, synthetic dataset that can replace the original dataset for training purposes. Some leading methods in this domain prioritize long-range matching, involving the unrolling of…

计算机视觉与模式识别 · 计算机科学 2024-07-22 Dai Liu , Jindong Gu , Hu Cao , Carsten Trinitis , Martin Schulz

Traditional automated crash analysis systems heavily rely on static statistical models and historical data, requiring significant manual interpretation and lacking real-time predictive capabilities. This research presents an innovative…

机器学习 · 计算机科学 2025-02-11 Karthik Sivakoti

Traffic state data, such as speed, volume and travel time collected from ubiquitous traffic monitoring sensors require advanced network level analytics for forecasting and identifying significant traffic patterns. This paper leverages…

机器学习 · 计算机科学 2025-02-18 Tianya Zhang

Operator learning for time-dependent partial differential equations (PDEs) has seen rapid progress in recent years, enabling efficient approximation of complex spatiotemporal dynamics. However, most existing methods rely on fixed time step…

机器学习 · 计算机科学 2025-10-07 Zhikai Wu , Sifan Wang , Shiyang Zhang , Sizhuang He , Min Zhu , Anran Jiao , Lu Lu , David van Dijk

The self-attention mechanism (SAM) is widely used in various fields of artificial intelligence and has successfully boosted the performance of different models. However, current explanations of this mechanism are mainly based on intuitions…

计算机视觉与模式识别 · 计算机科学 2023-08-22 Zhongzhan Huang , Mingfu Liang , Jinghui Qin , Shanshan Zhong , Liang Lin

Tensor train (TT) decomposition, a powerful tool for analyzing multidimensional data, exhibits superior performance in many machine learning tasks. However, existing methods for TT decomposition either suffer from noise overfitting, or…

信号处理 · 电气工程与系统科学 2023-06-27 Le Xu , Lei Cheng , Ngai Wong , Yik-Chung Wu

Travel Time Estimation (TTE) is indispensable in intelligent transportation system (ITS). It is significant to achieve the fine-grained Trajectory-based Travel Time Estimation (TTTE) for multi-city scenarios, namely to accurately estimate…

人工智能 · 计算机科学 2022-01-21 Chenxing Wang , Fang Zhao , Haichao Zhang , Haiyong Luo , Yanjun Qin , Yuchen Fang

We present PAT, a transformer-based network that learns complex temporal co-occurrence action dependencies in a video by exploiting multi-scale temporal features. In existing methods, the self-attention mechanism in transformers loses the…

计算机视觉与模式识别 · 计算机科学 2023-08-10 Faegheh Sardari , Armin Mustafa , Philip J. B. Jackson , Adrian Hilton

To compare alternative taxi schedules and to compute them, as well as to provide insights into an upcoming taxi trip to drivers and passengers, the duration of a trip or its Estimated Time of Arrival (ETA) is predicted. To reach a high…

机器学习 · 计算机科学 2024-01-12 Sören Schleibaum , Jörg P. Müller , Monika Sester

Non-stationarity can arise in Reinforcement Learning (RL) even in stationary environments. For example, most RL algorithms collect new data throughout training, using a non-stationary behaviour policy. Due to the transience of this…

机器学习 · 计算机科学 2021-09-23 Maximilian Igl , Gregory Farquhar , Jelena Luketina , Wendelin Boehmer , Shimon Whiteson

In nonlinear dynamical systems, tipping refers to a critical transition from one steady state to another, typically catastrophic, steady state, often resulting from a saddle-node bifurcation. Recently, the machine-learning framework of…

混沌动力学 · 物理学 2026-04-09 Smita Deb , Zheng-Meng Zhai , Mulugeta Haile , Ying-Cheng Lai

In recent years, RAPTOR based algorithms have been considered the state-of-the-art for path-finding with unlimited transfers without preprocessing. However, this status largely stems from the evolution of routing research, where…

数据结构与算法 · 计算机科学 2026-05-27 Denys Katkalo , Andrii Rohovyi , Toby Walsh

In this study, we introduce a novel framework called Toast for learning general-purpose representations of road networks, along with its advanced counterpart DyToast, designed to enhance the integration of temporal dynamics to boost the…

机器学习 · 计算机科学 2024-03-19 Yile Chen , Xiucheng Li , Gao Cong , Zhifeng Bao , Cheng Long

Predicting individual mobility patterns is crucial across various applications. While current methods mainly focus on predicting the next location for personalized services like recommendations, they often fall short in supporting broader…

人工智能 · 计算机科学 2025-08-20 Zongyuan Huang , Weipeng Wang , Shaoyu Huang , Marta C. Gonzalez , Yaohui Jin , Yanyan Xu

Drivers in ridesharing platforms exhibit cognitive atrophy and fatigue as they accept ride offers along the day, which can have a significant impact on the overall efficiency of the ridesharing platform. In contrast to the current…

机器学习 · 计算机科学 2024-04-17 Sree Pooja Akula , Mukund Telukunta , Venkata Sriram Siddhardh Nadendla

Estimating the travel time for a given path is a fundamental problem in many urban transportation systems. However, prior works fail to well capture moving behaviors embedded in paths and thus do not estimate the travel time accurately. To…

计算机视觉与模式识别 · 计算机科学 2019-09-13 Tao-yang Fu , Wang-Chien Lee

We study the problem of planning Pareto-optimal journeys in public transit networks. Most existing algorithms and speed-up techniques work by computing subjourneys to intermediary stops until the destination is reached. In contrast, the…

数据结构与算法 · 计算机科学 2016-09-16 Sascha Witt

In bus arrival time prediction, the process of organizing road infrastructure network data into homogeneous entities is known as segmentation. Segmenting a road network is widely recognized as the first and most critical step in developing…

机器学习 · 计算机科学 2025-12-09 Zhen Huang , Jiaxin Deng , Jiayu Xu , Junbiao Pang , Haitao Yu

Without relevant human priors, neural networks may learn uninterpretable features. We propose Dynamics of Attention for Focus Transition (DAFT) as a human prior for machine reasoning. DAFT is a novel method that regularizes attention-based…

机器学习 · 统计学 2019-12-24 Wonjae Kim , Yoonho Lee