Recent advances in unsupervised domain adaptation (UDA) by adapting the model from one domain to another unseen domain have shown considerable promise in improving surgical instrument segmentation performance across domains. However, existing UDA methods primarily rely on pixel-wise labels, which are always difficult to collect due to the labor-intensive annotation process. In this work, we aim to relax the dependence on pixel-level supervision and investigate a challenging UDA setting - source box annotations, where weak supervision and domain shifts coexist. To achieve this, we introduce a novel unsupervised domain adaptation framework, BL-UDA, which leverages bounding box annotations for surgical instrument segmentation across domains. By utilizing the Segment Anything Model (SAM) for pseudo label generation from box annotations, our method effectively bridges object-level and pixel-level domain adaptation. The proposed BL-UDA framework comprises a teacher-student network with entropy minimization for object detection and an entropy-based label selection strategy for generating box prompts to SAM, facilitating pixel-level domain adaptation. Extensive experiments on the EndoVis 2017 and 2018 datasets demonstrate the superiority of BL-UDA over existing UDA methods, significantly mitigating domain shifts and addressing weak supervision challenges with minimal annotation requirements.

Task assignment is a fundamental challenge in Spatial Crowdsourcing which aims to assign location-based tasks to workers under spatial-temporal constraints. Recently, some exciting research has introduced the preference of workers and tasks to improve assignment quality. However, they either primarily focus on the current preferences of both workers and tasks or only consider the unilateral prediction-based preference of workers, overlooking the impact of workers' interconnection and tasks' completed sequences. As a result, they gain suboptimal assignment results in most cases. Inspired by this, we propose a novel problem, named the Predictive Bi-preference Stable Match problem (PBSM), with the goal of maximizing the preferences of both workers and tasks by taking into account the social network of workers and task completion sequence. The PBSM problem is proven to be NP-hard. To tackle this challenging problem, we develop a GCN-enhanced Transformer-based Prediction and Bi-preference Stable Matching (GETBM) framework with two stages: the bi-preference prediction stage and the bilateral assignment stage. In the prediction stage, the Worker Preference Model (WPM) and Task Preference Model (TPM) models are presented to predict the worker-to-task (Worker2Task) and task-to-worker (Task2Worker) preference lists, respectively. Then, we design a bilateral preference-aware stable matching (BPM) algorithm and prove it can gain stable results. To generalize to multiple scenarios, three optimization strategies are devised based on spatial-temporal constraints and priority consideration to gain better assignment performance. Extensive experiments are conducted to prove the superiority of the GETBM framework on two real datasets.

Spatio-temporal graph neural networks have proven efficacy in capturing complex dependencies for urban computing tasks such as forecasting and kriging. Yet, their performance is constrained by the reliance on extensive data for training on a specific task, thereby limiting their adaptability to new urban domains with varied task demands. Although transfer learning has been proposed to remedy this problem by leveraging knowledge across domains, the cross-task generalization still remains under-explored in spatio-temporal graph transfer learning due to the lack of a unified framework. To bridge the gap, we propose Spatio-Temporal Graph Prompting (STGP), a prompt-based framework capable of adapting to multi-diverse tasks in a data-scarce domain. Specifically, we first unify different tasks into a single template and introduce a task-agnostic network architecture that aligns with this template. This approach enables capturing dependencies shared across tasks. Furthermore, we employ learnable prompts to achieve domain and task transfer in a two-stage prompting pipeline, facilitating the prompts to effectively capture domain knowledge and task-specific properties. Our extensive experiments demonstrate that STGP outperforms state-of-the-art baselines in three tasks-forecasting, kriging, and extrapolation-achieving an improvement of up to 10.7%.

Spatio-temporal graph learning is a fundamental problem in modern urban systems. Existing approaches tackle different tasks independently, tailoring their models to unique task characteristics. These methods, however, fall short of modeling intrinsic uncertainties in the spatio-temporal data. Meanwhile, their specialized designs misalign with the current research efforts toward unifying spatio-temporal graph learning solutions. In this paper, we propose to model these tasks in a unified probabilistic perspective, viewing them as predictions based on conditional information with shared dependencies. Based on this proposal, we introduce Unified Spatio-Temporal Diffusion Models (USTD) to address the tasks uniformly under the uncertainty-aware diffusion framework. USTD is holistically designed, comprising a shared spatio-temporal encoder and attention-based denoising decoders that are task-specific. The encoder, optimized by pre-training strategies, effectively captures conditional spatio-temporal patterns. The decoders, utilizing attention mechanisms, generate predictions by leveraging learned patterns. Opting for forecasting and kriging, the decoders are designed as Spatial Gated Attention (SGA) and Temporal Gated Attention (TGA) for each task, with different emphases on the spatial and temporal dimensions. Combining the advantages of deterministic encoders and probabilistic decoders, USTD achieves state-of-the-art performances compared to both deterministic and probabilistic baselines, while also providing valuable uncertainty estimates.

With the popularity of GPS-equipped smart devices, spatial crowdsourcing (SC) techniques have attracted growing attention in both academia and industry. In existing trajectory-aware task assignment approaches, tasks assigned to a worker may be far apart from each other, resulting in a higher detour cost as the worker needs to deviate from the original trajectory more often than necessary. Motivated by the above observations, we investigate a trajectory-aware task coalition assignment (TCA) problem and prove it to be NP-hard. The goal is to maximize the number of assigned tasks by assigning task coalitions to workers based on their preferred trajectories. To tackle the TCA problem, we develop a batch-based three-stage framework consisting of task grouping, planning, and assignment. Extensive experiments on real and synthetic datasets demonstrate the effectiveness and efficiency of the proposed algorithms.

Real-world last-mile express datasets are crucial for research in logistics, supply chain management, and spatio-temporal data mining. Despite a plethora of algorithms developed to date, no widely accepted, publicly available last-mile express dataset exists to support research in this field. In this paper, we introduce LaDe, the first publicly available last-mile express dataset with millions of packages from the industry. LaDe has three unique characteristics: (1)Large-scale. It involves 10,677k packages of 21k couriers over 6 months of real-world operation. (2)Comprehensive information. It offers original package information, task-event information, as well as couriers' detailed trajecotries and road networks. (3)Diversity. The dataset includes data from various scenarios, including package pick-up and delivery, and from multiple cities, each with its unique spatio-temporal patterns due to their distinct characteristics such as populations. We verify LaDe on three tasks by running several classical baseline models per task. We believe that the large-scale, comprehensive, diverse feature of LaDe can offer unparalleled opportunities to researchers in the supply chain community, data mining community, and beyond. The dataset and code is publicly available at https://huggingface.co/datasets/Cainiao-AI/LaDe.

Multivariate time series forecasting plays a pivotal role in contemporary web technologies. In contrast to conventional methods that involve creating dedicated models for specific time series application domains, this research advocates for a unified model paradigm that transcends domain boundaries. However, learning an effective cross-domain model presents the following challenges. First, various domains exhibit disparities in data characteristics, e.g., the number of variables, posing hurdles for existing models that impose inflexible constraints on these factors. Second, the model may encounter difficulties in distinguishing data from various domains, leading to suboptimal performance in our assessments. Third, the diverse convergence rates of time series domains can also result in compromised empirical performance. To address these issues, we propose UniTime for effective cross-domain time series learning. Concretely, UniTime can flexibly adapt to data with varying characteristics. It also uses domain instructions and a Language-TS Transformer to offer identification information and align two modalities. In addition, UniTime employs masking to alleviate domain convergence speed imbalance issues. Our extensive experiments demonstrate the effectiveness of UniTime in advancing state-of-the-art forecasting performance and zero-shot transferability.

Urban region profiling from web-sourced data is of utmost importance for urban computing. We are witnessing a blossom of LLMs for various fields, especially in multi-modal data research such as vision-language learning, where text modality serves as a supplement for images. As textual modality has rarely been introduced into modality combinations in urban region profiling, we aim to answer two fundamental questions: i) Can text modality enhance urban region profiling? ii) and if so, in what ways and which aspects? To answer the questions, we leverage the power of Large Language Models (LLMs) and introduce the first-ever LLM-enhanced framework that integrates the knowledge of text modality into urban imagery, named LLM-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining (UrbanCLIP ). Specifically, it first generates a detailed textual description for each satellite image by Image-to-Text LLMs. Then, the model is trained on image-text pairs, seamlessly unifying language supervision for urban visual representation learning, jointly with contrastive loss and language modeling loss. Results on urban indicator prediction in four major metropolises show its superior performance, with an average improvement of 6.1% on R2 compared to the state-of-the-art methods. Our code and dataset are available at https://github.com/StupidBuluchacha/UrbanCLIP.

Street view imagery (SVI), an emerging geospatial dataset, is useful for evaluating active transportation infrastructure, but it faces potential biases from its vehicle-based capture method, diverging from pedestrians’ and cyclists’ perspectives. Existing literature lacks both an examination of these biases and a solution. This study identifies and quantifies these biases by comparing conventional SVI with views from the road shoulder/sidewalk. To mitigate such perspective biases, we introduce a novel framework with generative adversarial network (GAN)-based image generation models (Pix2Pix and CycleGAN), an image regression model (ResNet-50), and a tabular model (LightGBM). Experiments assessed model effectiveness in translating car-centric views to those from pedestrian and cyclist perspectives. Results show significant differences in semantic indicators (e.g. green view index) between road center and road shoulder/sidewalk SVI, with low Pearson’s correlation coefficients r (0.35–0.55 for road shoulders and 0.45–0.47 for sidewalks) indicating bias. The framework succeeded in creating realistic images and aligning pixel ratios between perspectives, achieving strong correlation coefficients (0.81 for road shoulders and 0.83 for sidewalks), thus reducing bias. This work contributes by providing a scalable and model-agnostic approach to produce accurate SVIs for urban planning and sustainability, setting a foundation for improving bikeability and walkability assessments and promoting active transportation.

In this paper, we address the issue of modeling and estimating changes in the state of the spatio-temporal dynamical systems based on a sequence of observations like video frames. Traditional numerical simulation systems depend largely on the initial settings and correctness of the constructed partial differential equations (PDEs). Despite recent efforts yielding significant success in discovering data-driven PDEs with neural networks, the limitations posed by singular scenarios and the absence of local insights prevent them from performing effectively in a broader real-world context. To this end, this paper propose the universal expert module – that is, optical flow estimation component, to capture the evolution laws of general physical processes in a data-driven fashion. To enhance local insight, we painstakingly design a finer-grained physical pipeline, since local characteristics may be influenced by various internal contextual information, which may contradict the macroscopic properties of the whole system. Further, we harness currently popular neural discrete learning to unveil the underlying important features in its latent space, this process better injects interpretability, which can help us obtain a powerful prior over these discrete random variables. We conduct extensive experiments and ablations to demonstrate that the proposed framework achieves large performance margins, compared with the existing SOTA baselines.

Instant delivery services, such as food delivery and package delivery, have achieved explosive growth in recent years by providing customers with daily-life convenience. An emerging research area within these services is service Route&Time Prediction (RTP), which aims to estimate the future service route as well as the arrival time of a given worker. As one of the most crucial tasks in those service platforms, RTP stands central to enhancing user satisfaction and trimming operational expenditures on these platforms. Despite a plethora of algorithms developed to date, there is no systematic, comprehensive survey to guide researchers in this domain. To fill this gap, our work presents the first comprehensive survey that methodically categorizes recent advances in service route and time prediction. We start by defining the RTP challenge and then delve into the metrics that are often employed. Following that, we scrutinize the existing RTP methodologies, presenting a novel taxonomy of them. We categorize these methods based on three criteria: (i) type of task, subdivided into only-route prediction, only-time prediction, and joint route&time prediction; (ii) model architecture, which encompasses sequence-based and graph-based models; and (iii) learning paradigm, including Supervised Learning (SL) and Deep Reinforcement Learning (DRL). Conclusively, we highlight the limitations of current research and suggest prospective avenues. We believe that the taxonomy, progress, and prospects introduced in this paper can significantly promote the development of this field.

With the popularity of GPS-equipped smart devices, spatial crowdsourcing (SC) techniques have attracted growing attention in both academia and industry. A fundamental problem in SC is assigning location-based tasks to workers under spatial-temporal constraints. In many real-life applications, workers choose tasks on the basis of their preferred trajectories. However, by existing trajectory-aware task assignment approaches, tasks assigned to a worker may be far apart from each other, resulting in a higher detour cost as the worker needs to deviate from the original trajectory more often than necessary. Motivated by the above observations, we investigate a trajectory-aware task coalition assignment (TCA) problem and prove it to be NP-hard. The goal is to maximize the number of assigned tasks by assigning task coalitions to workers based on their preferred trajectories. For tackling the TCA problem, we develop a batch-based three-stage framework consisting of task grouping, planning, and assignment. First, we design greedy and spanning grouping approaches to generate task coalitions. Second, to gain candidate task coalitions for each worker efficiently, we design task-based and trajectory-based pruning strategies to reduce the search space. Furthermore, a 2-approximate algorithm, termed MST-Euler, is proposed to obtain a route among each worker and task coalition with a minimal detour cost. Third, the MST-Euler Greedy (MEG) algorithm is presented to compute an assignment that results in the maximal number of tasks assigned and a parallel strategy is introduced to boost its efficiency. Extensive experiments on real and synthetic datasets demonstrate the effectiveness and efficiency of the proposed algorithms.

Spatio-temporal graph neural networks (STGNN) have emerged as the dominant model for spatio-temporal graph (STG) forecasting. Despite their success, they fail to model intrinsic uncertainties within STG data, which cripples their practicality in downstream tasks for decision-making. To this end, this paper focuses on probabilistic STG forecasting, which is challenging due to the difficulty in modeling uncertainties and complex ST dependencies. In this study, we present the first attempt to generalize the popular de-noising diffusion probabilistic models to STGs, leading to a novel non-autoregressive framework called DiffSTG, along with the first denoising network UGnet for STG in the framework. Our approach combines the spatio-temporal learning capabilities of STGNNs with the uncertainty measurements of diffusion models. Extensive experiments validate that DiffSTG reduces the Continuous Ranked Probability Score (CRPS) by 4%-14%, and Root Mean Squared Error (RMSE) by 2%-7% over existing methods on three real-world datasets.

We study the task of spatio-temporal extrapolation that generates data at target locations from surrounding contexts in a graph. This task is crucial as sensors that collect data are sparsely deployed, resulting in a lack of fine-grained information due to high deployment and maintenance costs. Existing methods either use learning-based models like Neural Networks or statistical approaches like Gaussian Processes for this task. However, the former lacks uncertainty estimates and the latter fails to capture complex spatial and temporal correlations effectively. To address these issues, we propose Spatio-Temporal Graph Neural Processes (STGNP), a neural latent variable model which commands these capabilities simultaneously. Specifically, we first learn deterministic spatio-temporal representations by stacking layers of causal convolutions and cross-set graph neural networks. Then, we learn latent variables for target locations through vertical latent state transitions along layers and obtain extrapolations. Importantly during the transitions, we propose Graph Bayesian Aggregation (GBA), a Bayesian graph aggregator that aggregates contexts considering uncertainties in context data and graph structure. Extensive experiments show that STGNP has desirable properties such as uncertainty estimates and strong learning capabilities, and achieves state-of-the-art results by a clear margin.

Recent deep-learning-based face recognition systems have achieved significant success. However, most existing face recognition systems are vulnerable to spoofing attacks where a copy of the face image is used to deceive the authentication. A number of solutions are developed to overcome this problem by building a separate face anti-spoofing model, which however brings in additional storage and computation requirements. Since both recognition and face anti-spoofing tasks stem from the analysis of the same face image, this paper explores a unified approach to reduce the original dual-model redundancy. To this end, we introduce a compressed multi-task model to simultaneously perform both tasks in a lightweight manner, which has the potential to benefit lightweight IoT applications. Concretely, we regard the original two single-task deep models as teacher networks and propose a novel multi-teacher-assisted knowledge distillation method to guide our lightweight multi-task model to achieve satisfying performance on both tasks. Additionally, to reduce the large gap between the deep teachers and the light student, a comprehensive feature alignment is further integrated by distilling multi-layer features. Extensive experiments are carried out on two benchmark datasets, where we achieve the task accuracy of 93% meanwhile reducing the model size by 97% and reducing the inference time by 56% compared to the original dual-model.

Face verification is a trending way to verify someone’s identity in broad applications. But such systems are vulnerable to face spoofing attacks via, for example, a fraudulent copy of a photo, making it necessary to include face liveness detection as an additional safeguard. Among most existing studies, the face liveness detection is realized in a separate machine learning model in addition to the model for face verification. Such a two-model configuration may face challenges when deployed onto platforms with limited computation power and storage (e.g. mobile phone, IoT devices), especially considering each model may have millions of parameters. Inspired by the fact that humans can verify a person’s identity and liveness at a single glance from a face, we develop a novel system, named FaceLivePlus, to learn a single and universal face descriptor for the two tasks (face verification and liveness detection) so that the computational workload and storage space can be halved. To achieve this, we formulate the underlying relationship between the two tasks, and seamlessly embed this relationship in a distance ranking deep model. The model directly works on features rather than classification labels, which makes the system well generalized on unseen data. Extensive experiments show that our average half total error rate (HTER) has at least 15% and 8% improvement from the state-of-the-arts on two benchmark datasets. We anticipate this approach could become a new direction for face authentication.

Spatio-temporal forecasting has a wide range of applications in smart city efforts, such as traffic forecasting and air quality prediction. Graph Convolutional Recurrent Neural Networks (GCRNN) are the state-of-the-art methods for this problem, which learn temporal dependencies by RNNs and exploit pairwise node proximity to model spatial dependencies. However, the spatial relations in real data are not simply pairwise but sometimes in a higher order among multiple nodes. Moreover, spatio-temporal sequences deriving from nature are often regulated by known or unknown physical laws. GCRNNs rarely take into account the underlying physics in real-world systems, which may result in degenerated performance. To address these issues, we devise a general model called Mixed-Order Relation-Aware RNN (MixRNN+) for spatio-temporal forecasting. Specifically, our MixRNN+ captures the complex mixed-order spatial relations of nodes through a newly proposed building block called Mixer, and simultaneously addressing the underlying physics by the integration of a new residual update strategy. Experimental results on three forecasting tasks in smart city applications (including traffic speed, taxi flow, and air quality prediction) demonstrate the superiority of our model against the state-of-the-art methods. We have also deployed a cloud-based system using our method as the bedrock model to show its practicality.

Transformers have been an efficient alternative to recurrent neural networks in many sequential learning tasks. When adapting transformers to modeling trajectories, we encounter two major issues. First, being originally designed for language modeling, transformers assume regular intervals between input tokens, which contradicts the irregularity of trajectories. Second, transformers often suffer high computational costs, especially for long trajectories. In this paper, we address these challenges by presenting a novel transformer architecture entitled TrajFormer. Our model first generates continuous point embeddings by jointly considering the input features and the information of spatio-temporal intervals, and then adopts a squeeze function to speed up the representation learning. Moreover, we introduce an auxiliary loss to ease the training of transformers using the supervision signals provided by all output tokens. Extensive experiments verify that our TrajFormer achieves a preferable speed-accuracy balance compared to existing approaches.

Deep learning models are modern tools for spatio-temporal graph (STG) forecasting. Though successful, we argue that data scarcity is a key factor limiting their recent improvements. Meanwhile, contrastive learning has been an effective method for providing self-supervision signals and addressing data scarcity in various domains. In view of this, one may ask: can we leverage the additional signals from contrastive learning to alleviate data scarcity, so as to benefit STG forecasting? To answer this question, we present the first systematic exploration on incorporating contrastive learning into STG forecasting. Specifically, we first elaborate two potential schemes for integrating contrastive learning. We then propose two feasible and efficient designs of contrastive tasks that are performed on the node or graph level. The empirical study on STG benchmarks demonstrates that integrating graph-level contrast with the joint learning scheme achieves the best performance. In addition, we introduce four augmentations for STG data, which perturb the data in terms of graph structure, time domain, and frequency domain. Experimental results reveal that the model is not sensitive to the proposed augmentations' semantics. Lastly, we extend the classic contrastive loss via a rule-based strategy that filters out the most semantically similar negatives, yielding performance gains. We also provide explanations and insights based on the above experimental findings. Code is available at https://github.com/liuxu77/STGCL.

Estimating human poses from a video is at the foundation of many visual intelligent systems. Various convolutional neural networks have been proposed, achieving state-of-the-art performance on different image datasets. However, most existing approaches are image based, which deliver unreliable estimations on videos since they fail to model temporal consistency across video frames. Recently, another line of work leverages temporal cues for multi-frame person pose estimation, yet still in an instance-unaware fashion, disregarding the specific traits of different instances (persons) or different joints. In this paper, we propose a novel approach to learn specific keypoint motion representations for each person, termed Personalized Motion-Aware Network (PMAN). In the PMAN, we devise three components: (i) an Instance-Sensitive Extractor that adaptively computes the spatial features according to human physical characteristics; (ii) a Keypoint Motion Encoder that separately generates convolution kernels with fine-grained keypoint motion encoding; (iii) a Motion Driven Decoder that parses multi-frame spatial features of the same person to provide precise human pose estimations. Extensive experiments on PoseTrack2017 and PoseTrack2018 datasets demonstrate that our approach greatly improves the performance of multi-frame human pose estimation. It is worth mentioning that our approach surpasses the state-of-the-art method by +1.7 mAP and achieves 82.9 mAP on PoseTrack2017 dataset.

In recent years, Geo-information extraction from high-resolution satellite imagery has attracted a lot of attention. However, because of the high cost of image acquisition and annotation, there are limited datasets available. Compared to close-range imagery datasets, existing satellite datasets have a much lower number of images and cover only a few scenarios (cities, background environments, etc.). They may not be sufficient for training robust learning models that fit all environmental conditions or be representative enough for training regional models that optimize for local scenarios. In this study, we propose GeoPalette, a Generative Adversarial Network (GAN) based tool to generate additional synthetic training samples for boosting model performance when the training dataset is limited. Our experiments on road segmentation show that using additional synthetic data can improves the model performance mean Intersection over Union (mIoU) from 60.92% to 64.44%, when 1,000 real training pairs are available for learning, which reaches a similar level of performance as a model is standard-trained on 4,000 real pairs (64.59%), i.e., a 4-fold reduction in real dataset size.

Automatic inference of missing road attributes (e.g., road type and speed limit) for enriching digital maps has attracted significant research attention in recent years. A number of machine learning based approaches have been proposed to detect road attributes from GPS traces, dash-cam videos, or satellite images. However, existing solutions mostly focus on a single modality without modeling the correlations among multiple data sources. To bridge the gap, we present a multimodal road attribute detection method, which improves the robustness by performing pixel-level fusion of crowdsourced GPS traces and satellite images. A GPS trace is usually given by a sequence of location, bearing, and speed. To align it with satellite imagery in the spatial domain, we render GPS traces into a sequence of multi-channel images that simultaneously capture the global distribution of the GPS points, the local distribution of vehicles' moving directions and speeds, and their temporal changes over time, at each pixel. Unlike previous GPS based road feature extraction methods, our proposed GPS rendering does not require map matching in the data preprocessing step. Moreover, our multimodal solution addresses single-modal challenges such as occlusions in satellite images and data sparsity in GPS traces by learning the pixel-wise correspondences among different data sources. Extensive experiments have been conducted on two real-world datasets in Singapore and Jakarta. Compared with previous work, our method is able to improve the detection accuracy on road attributes by a large margin.

Urban flow prediction benefits smart cities in many aspects, such as traffic management and risk assessment. However, a critical prerequisite for these benefits is having fine-grained knowledge of the city. Thus, unlike previous works that are limited to coarse-grained data, we extend the horizon of urban flow prediction to fine granularity which raises specific challenges: 1) the predominance of inter-grid transitions observed in fine-grained data makes it more complicated to capture the spatial dependencies among grid cells at a global scale; 2) it is very challenging to learn the impact of external factors (e.g., weather) on a large number of grid cells separately. To address these two challenges, we present a Spatio-Temporal Relation Network (STRN) to predict fine-grained urban flows. First, a backbone network is used to learn high-level representations for each cell. Second, we present a Global Relation Module (GloNet) that captures global spatial dependencies much more efficiently compared to existing methods. Third, we design a Meta Learner that takes external factors and land functions (e.g., POI density) as inputs to produce meta knowledge and boost model performances. We conduct extensive experiments on two real-world datasets. The results show that STRN reduces the errors by 7.1% to 11.5% compared to the state-of-the-art method while using much fewer parameters. Moreover, a cloud-based system called UrbanFlow 3.0 has been deployed to show the practicality of our approach.

Map matching has long been a fundamental yet challenging problem. However, there are currently only a few public small-scale map matching benchmark datasets. Both the GPS trajectories and the road network in the existing map matching datasets are represented by location only, which cannot support the development of data-driven and semantic-enriched map matching algorithms that have increasingly emerged in recent years. To bridge the gap, we present the first large-scale attribute-rich map matching benchmark dataset covering two cities in Southeast Asia (i.e., Singapore and Jakarta). Our GPS trajectories contain rich contextual information including the accuracy level, bearing, speed, and transport mode in addition to the latitude and longitude geo-coordinates. The underlying road network is a snapshot of the OpenStreetMap where roads are associated with rich attributes such as road type, speed limit, etc. To ensure the quality of our dataset, the annotation of the map-matched routes has been conducted by a team of professional map operators. Analysis on our dataset provides new insights into the challenges and opportunities in map matching algorithms.

The quality of a digital map is of utmost importance for geo-aware services. However, maintaining an accurate and up-to-date map is a highly challenging task that usually involves a substantial amount of manual work. To reduce the manual efforts, methods have been proposed to automatically derive road attributes by mining GPS traces. However, previous methods always modeled each road attribute separately based on intuitive hand-crafted features extracted from GPS traces. This observation motivates us to propose a machine learning based method to learn joint features not only from GPS traces but also from map data. To model the relations among the target road attributes, we extract low-level shared feature embeddings via multi-task learning, while still being able to generate task-specific fused representations by applying attention-based feature fusion. To model the relations between the target road attributes and other contextual information that is available from a digital map, we propose to leverage map tiles at road centers as visual features that capture the information of the surrounding geographic objects around the roads. We perform extensive experiments on the OpenStreetMap where state-of-the-art classification accuracy has been obtained compared to existing road attribute detection approaches.

GPS coordinates are fine-grained location indicators that are difficult to be effectively utilized by classifiers in geo-aware applications. Previous GPS embedding methods are mostly tailored for specific problems that are taken place within areas of interest. When it comes to the scale of the entire planet, existing approaches always suffer from extensive computational cost and significant information loss. To solve these issues, we present a novel two-level grid based framework to learn semantic embeddings for geo-coordinates worldwide. The Earth's surface is first discretized by the Universal Transverse Mercator (UTM) coordinate system. Each UTM zone is next processed as a local area of interest that is further divided into fine-grained cells to perform the initial GPS encoding. We train a neural network in each UTM zone to learn the semantic embeddings from the initial GPS encoding. The training labels can be automatically derived from large-scale geotagged documents such as tweets, check-ins, and images that are available from social sharing platforms. We evaluate the effectiveness of our proposed GPS embeddings in geotagged image classification. Improved classification results have been obtained based on a simple early feature fusion technique.

Locating nearest moving objects in real-time is a vital problem that the ride-hailing industry needs to address. For instance, when a passenger makes a booking, the service provider, such as Grab or Uber, needs to locate the K nearest drivers for the given pickup location in case the closest driver is not optimal for this booking request. This poses two main challenges: firstly, massive frequent write operations are needed to track the objects' current locations. As drivers can move as fast as 25 meters per second in developed countries like Singapore, it is therefore important to update drivers' locations at a second, if not millisecond, granularity. Secondly, a K-nearest neighbour (kNN) query poses tremendous challenges, compared to a simple Get query, in a key-value data store such as Redis. This paper presents Sextant, a scalable in-memory spatial data store tailored for kNN searches. Sextant is decentralized, scalable, reliable, efficient and highly available. It has been supporting Grab's daily flow with no downtime for more than one year, with write QPS (query per second) and kNN query QPS approaching millions.

A major drawback of cross-network recommender solutions is that they can only be applied to users that are overlapped across networks. Thus, the non-overlapped users, which form the majority of users are ignored. As a solution, we propose CnGAN, a novel multi-task learning based, encoder-GAN-recommender architecture. The proposed model synthetically generates source network user preferences for non-overlapped users by learning the mapping from target to source network preference manifolds. The resultant user preferences are used in a Siamese network based neural recommender architecture. Furthermore, we propose a novel user-based pairwise loss function for recommendations using implicit interactions to better guide the generation process in the multi-task learning environment. We illustrate our solution by generating user preferences on the Twitter source network for recommendations on the YouTube target network. Extensive experiments show that the generated preferences can be used to improve recommendations for non-overlapped users. The resultant recommendations achieve superior performance compared to the state-of-the-art cross-network recommender solutions in terms of accuracy, novelty and diversity.

Videos recorded with current mobile devices are increasingly geotagged at fine granularity and used in various location- based applications and services. However, raw sensor data collected is often noisy, resulting in subsequent inaccurate geospatial analysis. In this study, we focus on the challenging correction of compass readings and present an automatic approach to reduce these metadata errors. Given the small geo-distance between consecutive video frames, image-based localization does not work due to the high ambiguity in the depth reconstruction of the scene. As an alternative, we collect geographic context from OpenStreetMap and estimate the absolute viewing direction by comparing the image scene to world projections obtained with different external camera parameters. To design a comprehensive model, we further incorporate smooth approximation and feature-based rotation estimation when formulating the error terms. Experimental results show that our proposed pyramid-based method outperforms its competitors and reduces orientation errors by an average of 58.8%. Hence, for downstream applications, improved results can be obtained with these more accurate geo-metadata. To illustrate, we present the performance gain in landmark retrieval and tag suggestion by utilizing the accuracy-enhanced geo-metadata.

A representative skylinecontains$k$skyline points that can represent its corresponding full skyline. The existing measuring criteria of$k$representative skylines are specifically designed for static data, and they cannot effectively handle streaming data. In this paper, we focus on the problem of calculating the$k$representative skyline over data streams. First, we propose a new criterion to choose$k$skyline points as the$k$representative skyline for data stream environments, termed the$k$largest dominance skyline ($k$-LDS), which is representative to the entire data set and is highly stable over the streaming data. Second, we propose an efficient exact algorithm, called Prefix-based Algorithm (PBA), to solve the$k$-LDS problem in a 2-dimensional space. The time complexity of PBA is only$\mathcal {O}((M-k)\times k)$where$M$is the size of the full skyline set. Third, the$k$-LDS problem for a$d$-dimensional ($d\ge 3$) space turns out to be very complex. Therefore, a greedy algorithm is designed to answer$k$-LDS queries. To further accelerate the calculation, we propose a$\epsilon$-greedy algorithm which can achieve an approximate factor of$\frac{1}{(1+\epsilon)}(1-\frac{1}{\sqrt{e}})$. Experimental results on both synthetic and real-world data show that our$k$-LDS significantly outperforms its competitors in data stream environments. Furthermore, we demonstrate that the proposed$\epsilon$-greedy algorithm can solve$k$-LDS efficiently and with a competitive accuracy.

Predicting the location of a video based on its content is a very meaningful, yet very challenging problem. Most existing work has focused on developing representative visual features and then searching for visually nearest neighbors in the development set to achieve a prediction. Interestingly, the relationship between scenes has been overlooked in prior work. Two scenes that are visually different, but frequently co-occur in same location, should naturally be considered similar for the geotagging problem. To build upon the above ideas, we propose to model the geo-spatial distributions of scenes by Gaussian Mixture Models (GMMs) and measure the distribution similarity by the Jensen-Shannon divergence (JSD). Subsequently, we present the Spatial Relationship Model (SRM) for geotagging which integrates the geo-spatial relationship of scenes into a hierarchical framework. We segment the Earth's surface into multiple levels of grids and measure the likelihood of input videos with an adaptation to region granularities. We have evaluated our approach using the YFCC100M dataset in the context of the MediaEval 2014 placing task. The total set of 35,000 geotagged videos is further divided into a training set of 25,000 videos and a test set of 10,000 videos. Our experimental results demonstrate the effectiveness of our proposed framework, as our solution achieves good accuracy and outperforms existing visual approaches for video geotagging.

This paper proposes a novel fine-grained image categorization model where no object annotation is required in the training/testing stage. The key technique is a dense graph mining algorithm that localizes multi-scale discriminative object parts in each image. In particular, to mimick human hierarchical perception mechanism, a super-pixel pyramid is generated for each image, based on which graphlets from each layer are constructed to seamlessly describe object parts. We observe that graphlets representative to each category are densely distributed in the feature space. Therefore a dense graph mining algorithm is developed to discover graphlets representative to each sub- super-category. Finally, the discovered graphlets from pairwise images are encoded into an image kernel for fine-grained recognition. Experiments on the UCB-200 [32] shown that our method performs competitively to many models relying on the annotated bird parts.

Real-time map matching is a fundamental but challenging problem with various applications in Geographic Information Systems (GIS), Intelligent Transportation Systems (ITS) and beyond. It aims to align a sequence of measured latitude/longitude positions with the road network on a digital map in real-time. There exist a number of statistical matching approaches that unfortunately either process trajectory data offline or provide an online solution without an infimum analysis. Here we propose a novel statistics-based online map matching algorithm called Eddy with a solid error-and delay-bound analysis. More specifically, Eddy employs a Hidden Markov Model (HMM) to represent the spatio-temporal data as state chains, which elucidates the road network's topology, observation noises and their underlying relations. After modeling, we shape the decoding phase as a ski-rental problem, and an improved online-version Viterbi decoding algorithm is proposed to find the most likely sequence of hidden states (road routes) in real-time. We reduce the candidate routes search range during the decoding for efficiency reasons. Moreover, our deterministic decoder trades off latency for expected accuracy dynamically, without having to choose a fixed window size beforehand. We also provide the competitive analysis and the proof that our online algorithm is error-bounded (with a competitive ratio of 2) and latency-bounded. Our experimental results show that the proposed algorithm outperforms widely used existing approaches on both accuracy and latency.

Fine-grained image categories recognition is a challenging task aiming at distinguishing objects belonging to the same basic-level category, such as leaf or mushroom. It is a useful technique that can be applied for species recognition, face verification, and etc. Most of the existing methods have difficulties to automatically detect discriminative object components. In this paper, we propose a new fine-grained image categorization model that can be deemed as an improved version spatial pyramid matching (SPM). Instead of the conventional SPM that enumeratively conducts cell-to-cell matching between images, the proposed model combines multiple cells into cellets that are highly responsive to object fine-grained categories. In particular, we describe object components by cellets that connect spatially adjacent cells from the same pyramid level. Straightforwardly, image categorization can be casted as the matching between cellets extracted from pairwise images. Toward an effective matching process, a hierarchical sparse coding algorithm is derived that represents each cellet by a linear combination of the basis cellets. Further, a linear discriminant analysis (LDA)-like scheme is employed to select the cellets with high discrimination. On the basis of the feature vector built from the selected cellets, fine-grained image categorization is conducted by training a linear SVM. Experimental results on the Caltech-UCSD birds, the Leeds butterflies, and the COSMIC insects data sets demonstrate our model outperforms the state-of-the-art. Besides, the visualized cellets show discriminative object parts are localized accurately.

Similar to positioning data, camera orientation information has become a powerful contextual feature utilized by a number of GIS and social media applications. Such auxiliary information facilitates higher-level semantic analysis and management of video assets in such applications, e.g., video summarization and video indexing systems. However, it is problematic that raw sensor data collected from current mobile devices is often not accurate enough for subsequent geospatial analysis. To date, an effective orientation data correction system for mobile video content has been lacking. Here we present a content-based approach that improves the accuracy of noisy orientation sensor measurements generated by mobile devices in conjunction with video acquisition. Our preliminary experimental results demonstrate significant accuracy enhancements which benefit upstream sensor-aided GIS applications to access video content more precisely.

Geo-fencing is a promising technique for emerging location-based services. Its two basic spatial predicates, INSIDE and WITHIN pairings between points and polygons, can be addressed by state-of-the-art methods such as the crossing number algorithm. In the era of big-data, however, geo-fencing has to process millions of points and hundreds of polygons or even more in real-time. In this paper, we propose an efficient algorithm to improve the scalability of geo-fencing, which consists of two main stages. At the first stage, an R-tree is used to quickly detect whether a point is inside the minimum bounding rectangle of a polygon. In the second stage, instead of an exhaustive search, we design an edge-based locality sensitive hashing scheme adapted to the crossing number algorithm. As for the case of WITHIN detection, a probing scheme is suggested to locate adjacent buckets so as to check all edges near to a target point. By further exploiting batch processing and multi-threading programming, our algorithm can achieve a fast speed while retaining 100% accuracy over all training datasets provided by the GIS Cup 2013 organizers.

Given a set of spatial objects, facilities can influence the objects located within their influence regions that are represented by circular disks with the same radius $(r)$. Our task is to select the minimum number of locations such that establishing a temporary facility at each selected location would ensure that all the objects are influenced. Aiming to solve this location selection problem, we propose a novel kind of location selection query, called group location selection (GLS) queries. In many real-world applications, every object is usually located within an uncertainty region instead of at an exact point. Due to the uncertainty of the data, GLS processing needs to ensure that the probability of each uncertain object being influenced by one facility is not less than a given threshold $(\tau)$. An analysis of the time cost reveals that it is infeasible to exactly answer GLS queries over uncertain objects in polynomial time. Hence, this paper proposes an approximate query framework for answering queries efficiently while guaranteeing that the results of GLS queries are correct with a bounded probability. The performance of the proposed methods of the framework is demonstrated by theoretical analysis and extensive experiments with both real and synthetic data sets.

The results of skyline queries performed on data sets with partially-ordered domains vary depending on users' preference profiles specified for the partially-ordered domains. Existing work has addressed the issue of handling each individual query with some efficiency. However, processing large volumes of such queries for online applications with low response time is still very challenging. In this paper, we introduce a novel approach, termed CSS, to reduce the latency by caching query results with their unique user preferences. Of paramount importance in this case is that cached queries with compatible preference profiles need to be utilized. For this purpose, we introduce a similarity measure that establishes the level of a relation of a new query to each of the previously cached queries and profiles. The similarity measure allows the cached entries to be effectively ordered according to descending values; hence, query processing can start with the most promising candidates. If a new query is only partially answerable from the cache, the proposed method pursues a second optimization step. The query processor utilizes the partial result sets and augments them by performing less expensive constraint skyline queries guided by constraint violations between different query preference profiles. Extensive experiments are presented to demonstrate the performance and utility of our novel approach.

GIS applications now increasingly make use of geo-located multimedia data such as images and videos. Furthermore, the wide-spread availablity of smartphones allows the acquisition of user-generated videos that are annotated with geo-properties. The sensor meta-data, e.g., GPS and digital compass values, are considerably smaller in size than the visual content and are helpful in effectively and efficiently manage and search through large repositories of videos. However, a major practical issue is the noisy nature of such sensor data. For example, due to sensor data inaccuracies the visual coverage described by the meta-data may not exactly match the actual video scene, which leads to imprecise search results and positional disagreements on map overlays. Obstructions between the camera and its captured objects make these situations worse. Therefore, robust error-tolerance is an essential feature of any geo-tagged video search application.

Video associated positioning data has become a useful contextual feature to facilitate analysis and management of media assets in GIS and social media applications. Moreover, with today's sensor-equipped mobile devices, the location of a camera can be continuously acquired in conjunction with the captured video stream without much difficulty. However, most sensor information collected from mobile devices is not highly accurate due to two main reasons: (a) the varying surrounding environmental conditions during data acquisition, and (b) the use of low-cost, consumer-grade sensors in current mobile devices. In this paper, we enhance the noisy positioning data generated by smartphones during video recording by analyzing typical error patterns for real collected data and introducing two robust algorithms, based on Kalman filtering and weighted linear least square regression, respectively. Our experimental results demonstrate significant benefits of our methods, which help upstream sensor-aided applications to access media content precisely.

Todays versatile mobile devices such as smartphones are increasingly popular platforms for trajectory-based applications such as vehicle tracking, route navigation and geotagged video acquisition. On these battery-powered devices employing a trajectory data acquisition approach that reduces the amount of energy spent but still provides accurate location information is essential for these applications' usability. This paper presents EnAcq, a novel energy-efficient GPS trajectory data acquisition scheme based on improved map matching that addresses two key challenges: providing highly accurate trajectory data and reducing energy consumption. To improve the precision of trajectory data, EnAcq utilizes an improved Hidden Markov Model (HMM)-based map matching algorithm which can find candidate matches for each GPS location sample point without using the traditionally necessary range query and determine the most likely route the mobile device (e.g., in a vehicle) has travelled. To avoid unnecessary energy consumption, EnAcq adopts an adaptive GPS sampling method which adjusts the sampling period based on the device's current motion state. On a public real-world dataset, we demonstrate via experimental results that EnAcq is able to yield accurate trajectory data while avoiding unnecessary energy consumption.

Skyline query processing has become an important feature in multi-dimensional, data-intensive applications. Such computations are especially challenging under dynamic conditions, when either snapshot queries need to be answered with short user response times or when continuous skyline queries need to be maintained efficiently over a set of objects that are frequently updated. To achieve high performance, we have recently designed the ESC algorithm, an Efficient update approach for Skyline Computations. ESC creates a pre-computed candidate skyline set behind the first skyline (a “second line of defense,” so to speak) that facilitates an incremental, two-stage skyline update strategy which results in a quicker query response time for the user. Our demonstration presents the two-threaded SkyEngine system that builds upon and extends the base-features of the ESC algorithm with innovative, user-oriented functionalities that are termed SkyAlert and AutoAdjust. These functions enable a data or service provider to be informed about and gain the opportunity of automatically promoting its data records to remain part of the skyline, if so desired. The SkyEngine demonstration includes both a server and a web browser based client. Finally, the SkyEngine system also provides visualizations that reveal its internal performance statistics.

With the proliferation of mobile devices, an increasing number of urban users subscribe to location-based services. This trend has led to significant research interest in techniques that address two fundamental requirements: road network-based distance computation and the capability to process moving objects as points of interests. However, there exist few techniques that support both requirements simultaneously. To address these challenges, we propose a novel approach to process continuous range queries. We build on our previous work of an infrastructure that supports location-based snapshot queries on MOVing objects in road Networks (MOVNet). We introduce several significant features to enable continuous queries. The dual index structure that we proposed for MOVNet has been appropriately modified. We further appoint a number of connecting vertices in each cell and precompute the distances among them to expedite query processing. Most importantly, to alleviate the effects of frequent object updates, we introduce a Shortest-Distance-based Tree (SD-Tree). We illustrate that the network connectivity and distance information can be preserved and reused by the SD-Tree when the query point location is updated; hence, reducing the continuous query update cost. Our experimental results demonstrate that our method yields excellent performance with a very large number of moving objects.

Recently various sensors, such as GPS and compass devices, can be cost-effectively manufactured and this allows their deployment in conjunction with mobile video cameras. Hence, recorded clips can automatically be annotated with geospatial information and the resulting georeferenced videos may be used in various Geographic Information System (GIS) applications. However, the research community is lacking large-scale and realistic test datasets of such sensor-fused information to evaluate their techniques since collecting real-world test data requires considerable time and effort. To fill this void, we propose an approach for generating synthetic video meta-data with realistic geospatial properties for mobile video management research. We highlight the essential aspects of the georeferenced video meta-data and present an approach to simulate the behavioral patterns of mobile cameras in the synthetic data. The data generation process can be customized through user parameters for a variety of GIS applications that use mobile videos. We demonstrate the feasibility and applicability of the proposed approach by providing comparisons with real-world data.

The PLUS system is designed to efficiently track moving object locations on a road network and execute continuous spatial queries in support of location-based services. PLUS implements a novel lazy position update mechanism that significantly reduces the communication overhead and server indexing load related to frequent location updates in moving object and moving query scenarios. The contribution of this demo is to present how the lazy position update scheme can achieve message-efficiency under various conditions which can be interactively set via user-selectable parameters in a graphical user interface.

Trip planning search (TPS) represents an important class of queries in Geographic Information Systems (GIS). In many real-world applications, TPS requests are issued with a number of constraints. Unfortunately, most of these constrained TPS cannot be directly answered by any of the existing algorithms. By formulating each restriction into rules, we propose a novel form of route query, namely the multi-rule partial sequenced route (MRPSR) query. Our work provides a unified framework that also subsumes the well-known trip planning query (TPQ) and the optimal sequenced route (OSR) query. In this paper, we first prove that MRPSR is NP-hard and then present three heuristic algorithms to search for near-optimal solutions for the MRPSR query. Our extensive simulations show that all of the proposed algorithms can answer the MRPSR query effectively and efficiently. Using both real and synthetic datasets, we investigate the performance of our algorithms with the metrics of the route distance and the response time in terms of the percentage of the constrained points of interest (POI) categories. Compared to the LORD-based brute-force solution, the response times of our algorithms are remarkably reduced while the resulting route length is only slightly longer than the shortest route.

Location-based services are increasingly popular and it is a key challenge to efficiently support query processing. We present a novel design to process large numbers of location-based snapshot queries on MOVing objects in road Networks (MOVNet, for short). MOVNet's dual-index design utilizes an on-disk R-tree to store the network connectivities and an in-memory grid structure to maintain moving object position updates. A method to speedily compute the overlapping grid cells in the network relates these two indices. Based on the above features we propose algorithms to support mobile network distance range queries. We demonstrate via experimental results that MOVNet yields excellent performance while scaling to a very large number of moving objects.

Continuous spatial queries posted within an environment of moving objects produce as their results a time-varying set of objects. In the most ambitious case both queries and data objects are dynamic, making it very challenging to find an efficient query evaluation strategy. The significant overhead related to frequent location updates from moving objects often results in poor performance. The most advanced existing techniques use the concept of simple geometric safe regions to delay or avoid location updates. We introduce a Partition-based Lazy Update (PLU) algorithm that elevates this idea further by adopting Location Information Tables (LIT) which (a) allow each moving object to estimate possible query movements and issue a location update only when it may affect any query results and (b) enable smart server probing that results in fewer messages. Among the significant advantages, our technique performs well even in very highly dynamic environments (with up to 100% mobility) where many other techniques deteriorate. PLU can be efficiently implemented and we demonstrate its query performance improvement of up to 28% over the current state-of-the-art.

Location-based spatial queries (LBSQs) refer to spatial queries whose answers rely on the location of the inquirer. Efficient processing of LBSQs is of critical importance with the ever-increasing deployment and use of mobile technologies. We show that LBSQs have certain unique characteristics that traditional spatial query processing in centralized databases does not address. For example, a significant challenge is presented by wireless broadcasting environments, which often exhibit high-latency database access. In this paper, we present a novel query processing technique that, while maintaining high scalability and accuracy, manages to reduce the latency considerably in answering location-based spatial queries. Our approach is based on peer-to-peer sharing, which enables us to process queries without delay at a mobile host by using query results cached in its neighboring mobile peers. We illustrate the appeal of our technique through extensive simulation results.

In this demonstration we present MAPLE, a scalable peer-to-peer nearest neighbor (NN) query system for mobile environments. MAPLE is designed for the efficient sharing of query results cached in the local storage of mobile peers. The MAPLE system is innovative in its ability to either fully or partially compute location-dependent nearest neighbor objects on each host. The demonstration illustrates how cooperative data sharing and distributed processing among mobile peers results in a considerable reduction of the load on remote spatial databases.

Nearest neighbor (NN) searches represent an important class of queries in geographic information systems (GIS). Most nearest neighbor algorithms rely on static distance information to compute NN queries (e.g., Euclidean distance or spatial network distance). However, the final goal of a user when performing an NN search is often to travel to one of the search results. Based on this observation, finding the nearest neighbors in terms of travel time is more realistic than the actual distance. In the existing NN algorithms dynamic real-time events (e.g., traffic congestions, detours, etc.) are usually not considered and hence the pre-computed nearest neighbor objects may not accurately reflect the shortest travel time. In this demonstration we present ANNATTO, a novel adaptive nearest neighbor query model for travel time networks which integrates both spatial networks and real-time traffic event information. The ANNATTO system includes the implementation of a globalbased adaptive nearest neighbor algorithm and a localbased greedy nearest neighbor algorithm that both utilize real-time traffic information to provide adaptive nearest neighbor search results.

Scalable storage architectures allow for the addition of disks to increase storage capacity and/or bandwidth. In its general form, disk scaling also refers to disk removals when either capacity needs to be conserved or old disk drives are retired. Assuming random placement of blocks on multiple nodes of a continuous media server, our optimization objective is to redistribute a minimum number of media blocks after disk scaling. This objective should be met under two restrictions. First, uniform distribution and hence a balanced load should be ensured after redistribution. Second, the redistributed blocks should be retrieved at the normal mode of operation in one disk access and through low complexity computation. We propose a technique that meets the objective, while we prove that it also satisfies both restrictions. The SCADDAR approach is based on using a series of REMAP functions which can derive the location of a new block using only its original location as a basis.

Moving sensors refers to an emerging class of data intensive applications that inpacts disciplines such as communication, health-care, scientific applications, etc. These applications consist of a fixed number of sensors that move and produce streams of data as a function of time. They may require the system to match these streams against stored streams to retrieve relevant data (patterns). With communication, for example, a speaking impaired individual might utilize a haptic glove that translates hand signs into written (spoken) words. The glove consists of sensors for different finger joints. These sensors report their location and values as a function of time, producing streams of data. These streams are matched against a repository of spatio-temporal streams to retrieve the corresponding English character or word.The contributions of this study are two fold. First, it introduces a framework to store and retrieve "moving sensors" data. The framework advocates physical data independence and software-reuse. Second, we investigate alternative representations for storage and retrieve of data in support of query processing. We quantify the tradeoff associated with these alternatives using empirical data RoboCup soccer matches.