Ghadir Alselwi, Hao Xue, Shoaib Jameel, Basem Suleiman, Flora D. Salim, Imran Razzak. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Automated simulator construction requires distributional fidelity, distinguishing it from generic code generation.We identify two failure modes in long-horizon LLM agents: contextual drift and optimization instability arising from conflating structural and parametric errors.We propose SOCIA-EVO, a dualanchored evolutionary framework.SOCIA-EVO introduces (1) a static blueprint to enforce empirical constraints; (2) a bi-level optimization to decouple structural refinement from parameter calibration; and (3) a selfcurating Strategy Playbook that manages remedial hypotheses via Bayesian-weighted retrieval.By falsifying ineffective strategies through execution feedback, SOCIA-EVO achieves robust convergence, generating simulators that are statistically consistent with observational data.SOCIA-EVO's code and data are available here: https://github.com/ cruiseresearchgroup/SOCIA/tree/evo.* We set τ as 3% empirically.

Motion sensor time-series are central to Human Activity Recognition (HAR), yet conventional approaches are constrained to fixed activity sets and typically require costly parameter retraining to adapt to new behaviors.While Large Language Models (LLMs) offer promising open-set reasoning capabilities, applying them directly to numerical time-series often leads to hallucinations and weak grounding.To address this challenge, we propose ZARA (Zero-training Activity Reasoning Agents), a knowledge-and retrieval-augmented agentic framework for motion time-series reasoning in a training-free inference setting.Rather than relying on black-box projections, ZARA distills reference data into a statistically grounded textual knowledge base that transforms implicit signal patterns into verifiable naturallanguage priors.Guided by retrieved evidence, ZARA iteratively selects discriminative cues and performs grounded reasoning over candidate activities.Extensive experiments on eight benchmarks show that ZARA generalizes robustly to unseen subjects and across datasets, demonstrating strong transferability across heterogeneous sensor domains.These results mark a step toward trustworthy, plugand-play motion understanding beyond datasetspecific artifacts.Our code is available at https://github.com/zechenli03/ZARA.

Regulatory limits on explicit targeting have not eliminated algorithmic profiling on the Web, as optimisation systems still adapt ad delivery to users' private attributes. The widespread availability of powerful zero-shot multimodal Large Language Models (LLMs) has dramatically lowered the barrier for exploiting these latent signals for adversarial inference. We investigate this emerging societal risk, specifically how adversaries can now exploit these signals to reverse-engineer private attributes from ad exposure alone. We introduce a novel pipeline that leverages LLMs as adversarial inference engines to perform natural language profiling. Applying this method to a longitudinal dataset comprising over 435,000 Facebook ad impressions collected from 891 users, we conducted a large-scale study to assess the feasibility and precision of inferring private attributes from passive online ad observations. Our results demonstrate that off-the-shelf LLMs can accurately reconstruct complex user private attributes, including party preference, employment status, and education level, consistently outperforming strong census-based priors and matching or exceeding human social perception at only a fraction of the cost (223× lower) and time (52× faster) required by humans. Critically, actionable profiling is feasible even within short observation windows, indicating that prolonged tracking is not a prerequisite for a successful attack. These findings provide the first empirical evidence that ad streams serve as a high-fidelity digital footprint, enabling off-platform profiling that inherently bypasses current platform safeguards, highlighting a systemic vulnerability in the ad ecosystem and the urgent need for responsible web AI governance in the generative AI era. The code is available at https://github.com/Breezelled/when-ads-become-profiles.

Retrieval-augmented generation (RAG) has improved large language models (LLMs) on knowledge-intensive tasks, yet most systems assume static facts and struggle when answers depend on serialized and dynamic data, like time--e.g., ordering events, aligning facts to valid intervals, or planning actions under evolving conditions. This paper presents Knowledge-Graph Iterative Retrieval-Augmented Generation (KG-iRAG), a framework specialized for temporal reasoning. KG-iRAG couples a time-aware planner with a knowledge graph (KG) to iteratively fetch and compose evidence along a temporal axis. Concretely, it (i) represents events and facts with explicit timestamps and validity intervals; (ii) propagates temporal constraints through iterative retrieval using operators; and (iii) verifies temporal consistency while refining intermediate hypotheses, enabling step-by-step deduction for queries that mix knowledge retrieval with inference. Across public temporal QA benchmarks, KG-iRAG consistently improves accuracy and calibration over strong RAG baselines while reducing unnecessary retrieval through targeted, constraint-guided steps. To stress-test real-time decision queries, three application-oriented datasets (weatherQA-Irish, ~ weatherQA-Sydney, and~ trafficQA-TFNSW) are additionally constructed and tested alongside existing temporal benchmarks. The results demonstrate that injecting temporal structure into KG-driven RAG yields robust gains on multi-step, time-dependent queries, advancing the state of temporal reasoning with LLMs.

We introduce SensorLLM, a two-stage framework that enables Large Language Models (LLMs) to perform human activity recognition (HAR) from sensor time-series data.Despite their strong reasoning and generalization capabilities, LLMs remain underutilized for motion sensor data due to the lack of semantic context in time-series, computational constraints, and challenges in processing numerical inputs.Sen-sorLLM addresses these limitations through a Sensor-Language Alignment stage, where the model aligns sensor inputs with trend descriptions.Special tokens are introduced to mark channel boundaries.This alignment enables LLMs to capture numerical variations, channelspecific features, and data of varying durations, without requiring human annotations.In the subsequent Task-Aware Tuning stage, we refine the model for HAR classification, achieving performance that matches or surpasses state-ofthe-art methods.Our results demonstrate that SensorLLM evolves into an effective sensor learner, reasoner, and classifier through humanintuitive Sensor-Language Alignment, generalizing across diverse HAR datasets.We believe this work establishes a foundation for future research on time-series and text alignment, paving the way for foundation models in sensor data analysis.Our codes are available at https: //github.com/zechenli03/SensorLLM.

Pathogen genome data offers valuable structure for spatial models, but its utility is limited by incomplete sequencing coverage. We propose a probabilistic framework for inferring genetic distances between unsequenced cases and known sequences within defined transmission chains, using time-aware evolutionary distance modeling. The method estimates pairwise divergence from collection dates and observed genetic distances, enabling biologically plausible imputation grounded in observed divergence patterns, without requiring sequence alignment or known transmission chains. Applied to highly pathogenic avian influenza A/H5 cases in wild birds in the United States, this approach supports scalable, uncertainty-aware augmentation of genomic datasets and enhances the integration of evolutionary information into spatiotemporal modeling workflows.

Traditional Point-of-Interest (POI) recommendation systems often lack transparency, interpretability, and scrutability due to their reliance on dense vector-based user embeddings. Furthermore, the cold-start problem—where systems have insufficient data for new users—limits their ability to generate accurate recommendations. Existing methods often address this by leveraging similar trajectories from other users, but this approach can be computationally expensive and increases the context length for large language model-based methods, making them difficult to scale. To address these limitations, we propose a method that generates natural language (NL) user profiles from large-scale, location-based social network checkins, utilizing robust personality assessments and behavioral theories. These NL profiles capture user preferences, routines, and behaviors, improving POI prediction accuracy while offering enhanced transparency. By incorporating NL profiles as system prompts to large language models, our approach reduces reliance on extensive historical data, while remaining flexible, easily updated, and computationally efficient. Results demonstrate that our approach consistently outperforms baseline methods, offering a more interpretable and resource-efficient solution for POI recommendation systems. Our source code is available at: https://github.com/w11wo/GenUP/.

Spatial-temporal causal time series (STC-TS) involve region-specific temporal observations driven by causally relevant covariates and interconnected across geographic or network-based spaces. Existing methods often model spatial and temporal dynamics independently and overlook causality-driven probabilistic forecasting, limiting their predictive power. To address this, we propose STOAT (Spatial-Temporal Probabilistic Causal Inference Network), a novel framework for probabilistic forecasting in STC-TS. The proposed method extends a causal inference approach by incorporating a spatial relation matrix that encodes interregional dependencies, enabling spatially informed causal effect estimation. The resulting latent series are processed by deep probabilistic models to estimate the parameters of the distributions, enabling calibrated uncertainty modeling. Experiments on COVID-19 data across six countries demonstrate that STOAT outperforms state-of-the-art probabilistic forecasting models in key metrics, particularly in regions with strong spatial dependencies. By bridging causal inference and geospatial probabilistic forecasting, STOAT offers a generalizable framework for complex spatial-temporal tasks, such as epidemic management.

Traffic forecasting is crucial for smart cities and intelligent transportation initiatives, where deep learning has made significant progress in modeling complex spatio-temporal patterns in recent years. However, current public datasets have limitations in reflecting the distribution shift nature of real-world scenarios, characterized by continuously evolving infrastructures, varying temporal distributions, and long temporal gaps due to sensor downtimes or changes in traffic patterns. These limitations inevitably restrict the practical applicability of existing traffic forecasting datasets. To bridge this gap, we present XXLTraffic, the largest available public traffic dataset with the longest timespan collected from Los Angeles, USA, and New South Wales, Australia, curated to support research in extremely long forecasting beyond test adaptation. Our benchmark includes both typical time-series forecasting settings with hourly and daily aggregated data and novel configurations that introduce gaps and down-sample the training size to better simulate practical constraints. We anticipate the new XXL-Traffic will provide a fresh perspective for the time-series and traffic forecasting communities. It would also offer a robust platform for developing and evaluating models designed to tackle the extremely long forecasting problems beyond test adaptation. Our dataset supplements existing spatio-temporal data resources and leads to new research directions in this domain.

Massive datasets related to infectious diseases became available after the COVID-19 pandemic, supporting data-driven approaches in modeling and forecasting infectious diseases. However, these approaches are known to exacerbate data biases present in the training data such as having certain demographic groups being over or underrepresented in the data. Such data collection biases may propagate through the modeling and prediction pipelines to decision-making, and the consequences are relatively unknown. Therefore, efforts are needed to understand how data collection bias affects data-driven infectious disease models. This datasets and benchmarks paper provides a suite of datasets, each corresponding to a simulated disease spread among a population of 5000 simulated agents over 90 days in Atlanta and San Francisco. For each dataset, we provide not only the full (simulated ground truth) of the disease spread in terms of when, where, and by whom the disease spreads, but also information on which cases are observed when different types and degrees of data collection bias are applied. The agents' characteristics, check-ins, and social network data are also available to support downstream tasks. Additionally, we also describe how to use the simulation to re-generate the data and to generate new datasets in different regions and with different parameters. With the provided datasets and the simulation tools, researchers studying the spread of infectious diseases may better understand, account for, and correct the systematic bias caused by the inherent real-world data bias, and hence improve the prediction of infectious diseases.

Frontier vision-language models (VLMs) have made remarkable improvements in video understanding tasks. However, real-world videos typically exist as continuously evolving data streams (e.g., dynamic scenes captured by wearable glasses), necessitating models to continually adapt to shifting data distributions and novel scenarios. Considering the prohibitive computational costs of fine-tuning models on new tasks, usually, a small subset of parameters is updated while the bulk of the model remains frozen. This poses new challenges to existing continual learning frameworks in the context of large multimodal foundation models, i.e., catastrophic forgetting and update conflict. While the foundation models struggle with parameter-efficient continual learning, the hippocampus in the human brain has evolved highly efficient mechanisms for memory formation and consolidation. Inspired by the rapid **Bi**nding and pattern **se**paration mechanisms in the hippocampus, in this work, we propose **Bisecle** for video-language **c**ontinual **le**arning, where a multi-directional supervision module is used to capture more cross-modal relationships and a contrastive prompt learning scheme is designed to isolate task-specific knowledge to facilitate efficient memory storage. Binding and separation processes further strengthen the ability of VLMs to retain complex experiences, enabling robust and efficient continual learning in video understanding tasks. We perform a thorough evaluation of the proposed Bisecle, demonstrating its ability to mitigate forgetting and enhance cross-task generalization on several VideoQA benchmarks.

Vision-based trajectory prediction is an important task that supports safe and intelligent behaviors in autonomous systems. Many advanced approaches have been proposed over the years with improved spatial and temporal feature extraction. However, human behavior is naturally diverse and uncertain. Given the past trajectory and surrounding environment information, an agent can have multiple plausible trajectories in the future. To tackle this problem, an essential task named multi-future trajectory prediction (MTP) has recently been studied. This task aims to generate a diverse, acceptable, and explainable distribution of future predictions for each agent. In this article, we present the first survey for MTP with our unique taxonomies and a comprehensive analysis of frameworks, datasets, and evaluation metrics. We also compare models on existing MTP datasets and conduct experiments on the ForkingPath dataset. Finally, we discuss multiple future directions that can help researchers develop novel MTP systems and other diverse learning tasks similar to MTP.

With the advancement of large language models, language model-based forecasting has recently emerged as an innovative approach for predicting mobility flow patterns. The core idea is to use prompts to transform the raw mobility data given as numerical values into natural language sentences so that the language models can be leveraged to generate the description for future observations. However, previous studies have only employed fixed and manually designed templates to transform numerical values into sentences. Since the forecasting performance of language models heavily relies on prompts, using fixed templates for prompting may limit the forecasting capability of language models. In this paper, we propose a novel framework for prompt mining in language model-based mobility forecasting, aiming to explore diverse prompt design strategies. Specifically, the framework includes a prompt generation stage based on the information entropy of prompts and a prompt refinement stage to integrate mechanisms such as the chain of thought. Experimental results on real-world large-scale data demonstrate the superiority of generated prompts from our prompt mining pipeline. Additionally, the comparison of different prompt variants shows that the proposed prompt refinement process is effective. Our study presents a promising direction for further advancing language model-based mobility forecasting.

Trajectory similarity computation is crucial for analyzing movement patterns in applications like traffic management and wildlife tracking. Recent self-supervised learning methods such as contrastive learning have made advancements in trajectory representation learning but rely on predefined data augmentation schemes, limiting generalized and robust high-level semantic understanding. We introduce T-JEPA, a self-supervised method using Joint-Embedding Predictive Architecture (JEPA) to enhance trajectory representation learning. By sampling and predicting in representation space, T-JEPA infers high-level trajectory semantics without manual intervention. Extensive experiments conducted on three urban and two Foursquare datasets verify the effectiveness of T-JEPA in trajectory similarity computation.

Training models on spatio-temporal (ST) data poses an open problem due to the complicated and diverse nature of the data itself, and it is challenging to ensure the model's performance directly trained on the original ST data. While limiting the variety of training data can make training easier, it can also lead to a lack of knowledge and information for the model, resulting in a decrease in performance. To address this challenge, we presented an innovative paradigm that incorporates three separate forms of curriculum learning specifically targeting from spatial, temporal, and quantile perspectives. Furthermore, our framework incorporates a stacking fusion module to combine diverse information from three types of curriculum learning, resulting in a strong and thorough learning process. We demonstrated the effectiveness of this framework with extensive empirical evaluations, highlighting its better performance in addressing complex ST challenges. We provided thorough ablation studies to investigate the effectiveness of our curriculum and to explain how it contributes to the improvement of learning efficiency on ST data.

Video language continual learning involves continuously adapting to information from video and text inputs, enhancing a model’s ability to handle new tasks while retaining prior knowledge. This field is a relatively under-explored area, and establishing appropriate datasets is crucial for facilitating communication and research in this field. In this study, we present the first dedicated benchmark, ViLCo-Bench, designed to evaluate continual learning models across a range of video-text tasks. The dataset comprises ten-minute-long videos and corresponding language queries collected from publicly available datasets. Additionally, we introduce a novel memory-efficient framework that incorporates self-supervised learning and mimics long-term and short-term memory effects. This framework addresses challenges including memory complexity from long video clips, natural language complexity from open queries, and text-video misalignment. We posit that ViLCo-Bench, with greater complexity compared to existing continual learning benchmarks, would serve as a critical tool for exploring the video-language domain, extending beyond conventional class-incremental tasks, and addressing complex and limited annotation issues. The curated data, evaluations, and our novel method are available at https://github.com/cruiseresearchgroup/ViLCo.

Buildings play a crucial role in human well-being, influencing occupant comfort, health, and safety.Additionally, they contribute significantly to global energy consumption, accounting for one-third of total energy usage, and carbon emissions.Optimizing building performance presents a vital opportunity to combat climate change and promote human flourishing.However, research in building analytics has been hampered by the lack of accessible, available, and comprehensive real-world datasets on multiple building operations.In this paper, we introduce the Building TimeSeries (BTS) dataset.Our dataset covers three buildings over a three-year period, comprising more than ten thousand timeseries data points with hundreds of unique ontologies.Moreover, the metadata is standardized using the Brick schema.To demonstrate the utility of this dataset, we performed benchmarks on two tasks: timeseries ontology classification and zero-shot forecasting.These tasks represent an essential initial step in addressing challenges related to interoperability in building analytics.Access to the dataset and the code used for benchmarking are available here: https://github.com/cruiseresearchgroup/DIEF_BTS

The next Point of Interest (POI) recommendation task is to predict users' immediate next POI visit given their historical data. Location-Based Social Network (LBSN) data, which is often used for the next POI recommendation task, comes with challenges. One frequently disregarded challenge is how to effectively use the abundant contextual information present in LBSN data. Previous methods are limited by their numerical nature and fail to address this challenge. In this paper, we propose a framework that uses pretrained Large Language Models (LLMs) to tackle this challenge. Our framework allows us to preserve heterogeneous LBSN data in its original format, hence avoiding the loss of contextual information. Furthermore, our framework is capable of comprehending the inherent meaning of contextual information due to the inclusion of commonsense knowledge. In experiments, we test our framework on three real-world LBSN datasets. Our results show that the proposed framework outperforms the state-of-the-art models in all three datasets. Our analysis demonstrates the effectiveness of the proposed framework in using contextual information as well as alleviating the commonly encountered cold-start and short trajectory problems.

Knowledge graphs (KGs) have been increasingly employed for link prediction and recommendation using real-world datasets. However, the majority of current methods rely on static data, neglecting the dynamic nature and the hidden spatio-temporal attributes of real-world scenarios. This often results in suboptimal predictions and recommendations. Although there are effective spatio-temporal inference methods, they face challenges such as scalability with large datasets and inadequate semantic understanding, which impede their performance. To address these limitations, this paper introduces a novel framework - Simple Spatio-Temporal Knowledge Graph (SSTKG), for constructing and exploring spatio-temporal KGs. To integrate spatial and temporal data into KGs, our framework exploited through a new 3-step embedding method. Output embeddings can be used for future temporal sequence prediction and spatial information recommendation, providing valuable insights for various applications such as retail sales forecasting and traffic volume prediction. Our framework offers a simple but comprehensive way to understand the underlying patterns and trends in dynamic KG, thereby enhancing the accuracy of predictions and the relevance of recommendations. This work paves the way for more effective utilization of spatio-temporal data in KGs, with potential impacts across a wide range of sectors.

Abstract New roads are being constructed all the time. However, the capabilities of previous deep forecasting models to generalize to new roads not seen in the training data (unseen roads) are rarely explored. In this paper, we introduce a novel setup called a spatio-temporal split to evaluate the models’ capabilities to generalize to unseen roads. In this setup, the models are trained on data from a sample of roads, but tested on roads not seen in the training data. Moreover, we also present a novel framework called Spatial Contrastive Pre-Training (SCPT) where we introduce a spatial encoder module to extract latent features from unseen roads during inference time. This spatial encoder is pre-trained using contrastive learning. During inference, the spatial encoder only requires two days of traffic data on the new roads and does not require any re-training. We also show that the output from the spatial encoder can be used effectively to infer latent node embeddings on unseen roads during inference time. The SCPT framework also incorporates a new layer, named the spatially gated addition layer, to effectively combine the latent features from the output of the spatial encoder to existing backbones. Additionally, since there is limited data on the unseen roads, we argue that it is better to decouple traffic signals to trivial-to-capture periodic signals and difficult-to-capture Markovian signals, and for the spatial encoder to only learn the Markovian signals. Finally, we empirically evaluated SCPT using the ST split setup on four real-world datasets. The results showed that adding SCPT to a backbone consistently improves forecasting performance on unseen roads. More importantly, the improvements are greater when forecasting further into the future. The codes are available on GitHub: https://github.com/cruiseresearchgroup/forecasting-on-new-roads .

This paper presents a new perspective on time series forecasting. In existing time series forecasting methods, the models take a sequence of numerical values as input and yield numerical values as output. The existing SOTA models are largely based on the Transformer architecture, modified with multiple encoding mechanisms to incorporate the context and semantics around the historical data. Inspired by the successes of pre-trained language foundation models, we pose a question about whether these models can also be adapted to solve time-series forecasting. Thus, we propose a new forecasting paradigm: prompt-based time series forecasting (PromptCast). In this novel task, the numerical input and output are transformed into prompts and the forecasting task is framed in a sentence-to-sentence manner, making it possible to directly apply language models for forecasting purposes. To support and facilitate the research of this task, we also present a large-scale dataset (PISA) that includes three real-world forecasting scenarios. We evaluate different SOTA numerical-based forecasting methods and language generation models. The benchmark results with various forecasting settings demonstrate the proposed PromptCast with language generation models is a promising research direction. Additionally, in comparison to conventional numerical-based forecasting, PromptCast shows a much better generalization ability under the zero-shot setting.

This paper presents a visionary perspective on developing Artificial General Intelligence (AGI) in the field of human mobility research. Human mobility profoundly influences our daily lives, impacting transportation systems, urban planning, logistics, and healthcare. While AI methods have made significant advancements in addressing human mobility challenges, they often struggle with the complexity and dynamic nature of this domain. The limitations arise from the narrow focus of existing AI systems, lacking the ability to generalize and adapt to new situations. To overcome these limitations, there is a growing interest in developing AGI systems. This paper explores the potential of AGI to revolutionize human mobility research by enabling systems to understand, learn, reason, and adapt across diverse domains and tasks. To achieve this goal, we propose the Mobility Foundation Model (MFM) and the concept of an intermediate modality is further introduced as a means to bridge the gap between different mobility modalities and scales. The unified representation allows the MFM to effectively learn and integrate information from various modalities. We also present a novel MFM as Administrator paradigm for leveraging MFM in complex mobility tasks. We hope that this paper will provide novel insights and open new directions in human mobility research.

In the context of mobile sensing environments, various sensors on mobile devices continually generate a vast amount of data. Analyzing this ever-increasing data presents several challenges, including limited access to annotated data and a constantly changing environment. Recent advancements in self-supervised learning have been utilized as a pre-training step to enhance the performance of conventional supervised models to address the absence of labelled datasets. This research examines the impact of using a self-supervised representation learning model for time series classification tasks in which data is incrementally available. We proposed and evaluated a workflow in which a model learns to extract informative features using a corpus of unlabeled time series data and then conducts classification on labelled data using features extracted by the model. We analyzed the effect of varying the size, distribution, and source of the unlabeled data on the final classification performance across four public datasets, including various types of sensors in diverse applications.

As a decisive part in the success of Mobility-as-a-Service (MaaS), spatio-temporal predictive modeling for crowd movements is a challenging task particularly considering scenarios where societal events drive mobility behavior deviated from the normality. While tremendous progress has been made to model high-level spatio-temporal regularities with deep learning, most, if not all of the existing methods are neither aware of the dynamic interactions among multiple transport modes nor adaptive to unprecedented volatility brought by potential societal events. In this paper, we are therefore motivated to improve the canonical spatio-temporal network (ST-Net) from two perspectives: (1) design a heterogeneous mobility information network (HMIN) to explicitly represent intermodality in multimodal mobility; (2) propose a memory-augmented dynamic filter generator (MDFG) to generate sequence-specific parameters in an on-the-fly fashion for various scenarios. The enhanced event-aware spatio-temporal network, namely EAST-Net, is evaluated on several real-world datasets with a wide variety and coverage of societal events. Both quantitative and qualitative experimental results verify the superiority of our approach compared with the state-of-the-art baselines. Code and data are published on https://github.com/underdoc-wang/EAST-Net.

In this paper, we propose a novel pipeline that leverages language foundation models for temporal sequential pattern mining, such as for human mobility forecasting tasks. For example, in the task of predicting Place-of-Interest (POI) customer flows, typically the number of visits is extracted from historical logs, and only the numerical data are used to predict visitor flows. In this research, we perform the forecasting task directly on the natural language input that includes all kinds of information such as numerical values and contextual semantic information. Specific prompts are introduced to transform numerical temporal sequences into sentences so that existing language models can be directly applied. We design an AuxMobLCast pipeline for predicting the number of visitors in each POI, integrating an auxiliary POI category classification task with the encoder-decoder architecture. This research provides empirical evidence of the effectiveness of the proposed AuxMobLCast pipeline to discover sequential patterns in mobility forecasting tasks. The results, evaluated on three real-world datasets, demonstrate that pre-trained language foundation models also have good performance in forecasting temporal sequences. This study could provide visionary insights and lead to new research directions for predicting human mobility.

Existing human mobility forecasting models follow the standard design of the time-series prediction model which takes a series of numerical values as input to generate a numerical value as a prediction. Although treating this as a regression problem seems straightforward, incorporating various contextual information such as the semantic category information of each Place-of-Interest (POI) is a necessary step, and often the bottleneck, in designing an effective mobility prediction model. As opposed to the typical approach, we treat forecasting as a translation problem and propose a novel forecasting through a language generation pipeline. The paper aims to address the human mobility forecasting problem as a language translation task in a sequence-to-sequence manner. A mobility-to-language template is first introduced to describe the numerical mobility data as natural language sentences. The core intuition of the human mobility forecasting translation task is to convert the input mobility description sentences into a future mobility description from which the prediction target can be obtained. Under this pipeline, a two-branch network, SHIFT (Translating Human Mobility Forecasting), is designed. Specifically, it consists of one main branch for language generation and one auxiliary branch to directly learn mobility patterns. During the training, we develop a momentum mode for better connecting and training the two branches. Extensive experiments on three real-world datasets demonstrate that the proposed SHIFT is effective and presents a new revolutionary approach to forecasting human mobility.

Generative Adversarial Networks (GANs) have shown remarkable success in producing realistic-looking images in the computer vision area. Recently, GAN-based techniques are shown to be promising for spatio-temporal-based applications such as trajectory prediction, events generation, and time-series data imputation. While several reviews for GANs in computer vision have been presented, no one has considered addressing the practical applications and challenges relevant to spatio-temporal data. In this article, we have conducted a comprehensive review of the recent developments of GANs for spatio-temporal data. We summarise the application of popular GAN architectures for spatio-temporal data and the common practices for evaluating the performance of spatio-temporal applications with GANs. Finally, we point out future research directions to benefit researchers in this area.

Heterogeneity and irregularity of multi-source data sets present a significant challenge to time-series analysis. In the literature, the fusion of multi-source time-series has been achieved either by using ensemble learning models which ignore temporal patterns and correlation within features or by defining a fixed-size window to select specific parts of the data sets. On the other hand, many studies have shown major improvement to handle the irregularity of time-series, yet none of these studies has been applied to multi-source data. In this work, we design a novel architecture, PIETS, to model heterogeneous time-series. PIETS has the following characteristics: (1) irregularity encoders for multi-source samples that can leverage all available information and accelerate the convergence of the model; (2) parallelised neural networks to enable flexibility and avoid information overwhelming; and (3) attention mechanism that highlights different information and gives high importance to the most related data. Through extensive experiments on real-world data sets related to COVID-19, we show that the proposed architecture is able to effectively model heterogeneous temporal data and outperforms other state-of-the-art approaches in the prediction task.

The usage of smartphone-collected respiratory sound, trained with deep learning models, for detecting and classifying COVID-19 becomes popular recently. It removes the need for in-person testing procedures especially for rural regions where related medical supplies, experienced workers, and equipment are limited. However, existing sound-based diagnostic approaches are trained in a fully-supervised manner, which requires large scale well-labelled data. It is critical to discover new methods to leverage unlabelled respiratory data, which can be obtained more easily. In this paper, we propose a novel self-supervised learning enabled framework for COVID-19 cough classification. A contrastive pre-training phase is introduced to train a Transformer-based feature encoder with unlabelled data. Specifically, we design a random masking mechanism to learn robust representations of respiratory sounds. The pre-trained feature encoder is then fine-tuned in the downstream phase to perform cough classification. In addition, different ensembles with varied random masking rates are also explored in the downstream phase. Through extensive evaluations, we demonstrate that the proposed contrastive pre-training, the random masking mechanism, and the ensemble architecture contribute to improving cough classification performance.

Human mobility prediction is a core functionality in many location-based services and applications. However, due to the sparsity of mobility data, it is not an easy task to predict future POIs (place-of-interests) that are going to be visited. In this paper, we propose MobTCast, a Transformer-based context-aware network for mobility prediction. Specifically, we explore the influence of four types of context in mobility prediction: temporal, semantic, social, and geographical contexts. We first design a base mobility feature extractor using the Transformer architecture, which takes both the history POI sequence and the semantic information as input. It handles both the temporal and semantic contexts. Based on the base extractor and the social connections of a user, we employ a self-attention module to model the influence of the social context. Furthermore, unlike existing methods, we introduce a location prediction branch in MobTCast as an auxiliary task to model the geographical context and predict the next location. Intuitively, the geographical distance between the location of the predicted POI and the predicted location from the auxiliary branch should be as close as possible. To reflect this relation, we design a consistency loss to further improve the POI prediction performance. In our experimental results, MobTCast outperforms other state-of-the-art next POI prediction methods. Our approach illustrates the value of including different types of context in next POI prediction.

Change Point Detection (CPD) methods identify the times associated with changes in the trends and properties of time series data in order to describe the underlying behaviour of the system. For instance, detecting the changes and anomalies associated with web service usage, application usage or human behaviour can provide valuable insights for downstream modelling tasks. We propose a novel approach for self-supervised Time Series Change Point detection method based on Contrastive Predictive coding (TS − CP2). TS − CP2 is the first approach to employ a contrastive learning strategy for CPD by learning an embedded representation that separates pairs of embeddings of time adjacent intervals from pairs of interval embeddings separated across time. Through extensive experiments on three diverse, widely used time series datasets, we demonstrate that our method outperforms five state-of-the-art CPD methods, which include unsupervised and semi-supervised approaches. TS − CP2 is shown to improve the performance of methods that use either handcrafted statistical or temporal features by 79.4% and deep learning-based methods by 17.0% with respect to the F1-score averaged across the three datasets.

Pedestrian path prediction is a very challenging problem because scenes are often crowded or contain obstacles. Existing state-of-the-art long short-term memory (LSTM)-based prediction methods have been mainly focused on analyzing the influence of other people in the neighborhood of each pedestrian while neglecting the role of potential destinations in determining a walking path. In this article, we propose classifying pedestrian trajectories into a number of route classes (RCs) and using them to describe the pedestrian movement patterns. Based on the RCs obtained from trajectory clustering, our algorithm, which we name the prediction of pedestrian paths by LSTM (PoPPL), predicts the destination regions through a bidirectional LSTM classification network in the first stage and then generates trajectories corresponding to the predicted destination regions through one of the three proposed LSTM-based architectures in the second stage. Our algorithm also outputs probabilities of multiple predicted trajectories that head toward the destination regions. We have evaluated PoPPL against other state-of-the-art methods on two public data sets. The results show that our algorithm outperforms other methods and incorporating potential destination prediction improves the trajectory prediction accuracy.

The prediction of the surrounding pedestrians' walking paths is a vital part for autonomous driving systems in the aspect of traffic safety. In this paper, we propose a pipeline which tracks pedestrians captured by a stereo camera system onboard a mobile vehicle, composes the pedestrian tracklets, clusters the tracklets to form trajectories, and matches the trajectories. The output 3D pedestrian trajectories can be used for further applications such as pedestrian trajectory prediction for driverless vehicles. Our algorithm has been compared with various state-of-art pedestrian tracking methods. Our experimental results show that the visual temporal features computed by our algorithm are effective for trajectory representation and that, by incorporating tracklet clustering into the pipeline, the pedestrian tracking performance is improved.

Pedestrian path forecasting is crucial in applications such as smart video surveillance. It is a challenging task because of the complex crowd movement patterns in the scenes. Most of existing state-of-the-art LSTM based prediction methods require rich context like labelled static obstacles, labelled entrance/exit regions and even the background scene. Furthermore, incorporating contextual information into trajectory prediction increases the computational overhead and decreases the generalization of the prediction models across different scenes. In this paper, we propose a joint Location-Velocity Attention LSTM based method to predict trajectories. Specifically, a module is designed to tweak the LSTM network and an attention mechanism is trained to learn to optimally combine the location and the velocity information of pedestrians in the prediction process. We have evaluated our approach against other baselines and state-of-the-art methods on several publicly available datasets. The results show that it not only outperforms other prediction methods but it also has a good generalization ability.

Pedestrian trajectory prediction is an extremely challenging problem because of the crowdedness and clutter of the scenes. Previous deep learning LSTM-based approaches focus on the neighbourhood influence of pedestrians but ignore the scene layouts in pedestrian trajectory prediction. In this paper, a novel hierarchical LSTM-based network is proposed to consider both the influence of social neighbourhood and scene layouts. Our SS-LSTM, which stands for Social-Scene-LSTM, uses three different LSTMs to capture person, social and scene scale information. We also use a circular shape neighbourhood setting instead of the traditional rectangular shape neighbourhood in the social scale. We evaluate our proposed method against two baseline methods and a state-of-art technique on three public datasets. The results show that our method outperforms other methods and that using circular shape neighbourhood improves the prediction accuracy.

With the development of the economic and the popularity of smartphones, location-based service is receiving more and more attention. It can be used inside a building where GPS signals are often unavailable. Because of its low deployment cost, vision-based indoor localization is becoming popular in the complicated indoor environment. However, in order to increase the accuracy of indoor localization, the database should be as large as possible. But in online phase, the query image retrieving would be more time-consuming. Therefore, we propose a fast cluster-based GIST (C- GIST) image retrieval method to reduce the time overhead of image retrieval. Compared with the existing indoor localization system, the proposed method utilizing video data could reduce the computational complexity evidently, which is much more convenient. The experiment results show that the proposed method is applicable in the complicated indoor environment, whose localization error less than 2 meters is nearly 70%. The error performance of the proposed method is slightly worse than the traditional method. Nevertheless, the proposed method decreases the computational complexity of image retrieval significantly.

Visual-based indoor localization have become a favored research area in recent years. It can be used inside a building where GPS signals are often not available. And due to its low deployment cost, visual-based indoor localization has been implemented in the complicated indoor environment. However, in order to increase the accuracy of indoor localization, the scale of image database should be as large as possible. The process of building a database that can be used for indoor localization is laborious. Thus, we propose a fast visual map building method for visual-based indoor localization, which takes fully use of convenience of video stream. Compared with existing image-based indoor localization system, the proposed system utilize video data is much more convenient. The experimental results show that the proposed method is applicable in the complicated indoor environment. The possibility of localization error less than 2 meters is nearly 70%. The error performance of the proposed method is slightly worse than the traditional method. Nevertheless, the proposed method can dramatically decrease the complexity of building a visual map.