相关论文: STaT: Resolving Shape Distortion in Non-Stationary…

Time series data often contain latent temporal structure, transitions between locally stationary regimes, repeated motifs, and bursts of variability, that are rarely leveraged in standard representation learning pipelines. Existing models…

Recently, there has been growing interest in incorporating textual information into foundation models for time series forecasting. However, it remains unclear whether and under what conditions such multimodal integration consistently yields…

While many advances in time series models focus exclusively on numerical data, research on multimodal time series, particularly those involving contextual textual information, remains in its infancy. With recent progress in large language…

Multimodal time series (MTS) anomaly detection is crucial for maintaining the safety and stability of working devices (e.g., water treatment system and spacecraft), whose data are characterized by multivariate time series with diverse…

Spatial transcriptomics (ST) technologies have revolutionized the study of gene expression patterns in tissues by providing multimodality data in transcriptomic, spatial, and morphological, offering opportunities for understanding tissue…

Time series forecasting traditionally relies on unimodal numerical inputs, which often struggle to capture high-level semantic patterns due to their dense and unstructured nature. While recent approaches have explored representing time…

Dynamic Text-Attributed Graphs (DyTAGs) are a novel graph paradigm that captures evolving temporal events (edges) alongside rich textual attributes. Existing studies can be broadly categorized into TGNN-driven and LLM-driven approaches,…

This paper challenges the dominance of stochastic trend models by introducing the Seasonal-Trend-Stationary ARMA (STSA) framework, which represents univariate nonstationary time series as stationary fluctuations around deterministic trend…

A reliable and efficient representation of multivariate time series is crucial in various downstream machine learning tasks. In multivariate time series forecasting, each variable depends on its historical values and there are…

Advances in multi-modal large language models (MLLMs) have inspired time series understanding and reasoning tasks, that enable natural language querying over time series, producing textual analyses of complex temporal dynamics. Recent…

Motion retargeting seeks to faithfully replicate the spatio-temporal motion characteristics of a source character onto a target character with a different body shape. Apart from motion semantics preservation, ensuring geometric plausibility…

While existing multivariate time series forecasting models have advanced significantly in modeling periodicity, they largely neglect the periodic heterogeneity common in real-world data, where variables exhibit distinct and dynamically…

Processing and analyzing time series data\-sets have become a central issue in many domains requiring data management systems to support time series as a native data type. A crucial prerequisite of these systems is time series matching,…

Irregularly sampled time series (ISTS) are widespread in real-world scenarios, exhibiting asynchronous observations on uneven time intervals across variables. Existing ISTS forecasting methods often solely utilize historical observations to…

Deep neural networks, especially transformer-based architectures, have achieved remarkable success in semantic segmentation for environmental perception. However, existing models process video frames independently, thus failing to leverage…

Is the Text to Motion model robust? Recent advancements in Text to Motion models primarily stem from more accurate predictions of specific actions. However, the text modality typically relies solely on pre-trained Contrastive Language-Image…

Incorporating textual information into time-series forecasting holds promise for addressing event-driven non-stationarity; however, a fundamental modality gap hinders effective fusion: textual descriptions express temporal impacts…

Spatio-temporal forecasting is crucial in transportation, logistics, and supply chain management. However, current methods struggle with large, complex datasets. We propose a dynamic, multi-modal approach that integrates the strengths of…

Existing audio-driven visual dubbing methods have achieved great success. Despite this, we observe that the semantic ambiguity between spatial and temporal domains significantly degrades the synthesis stability for the dynamic faces. We…

Multivariate time-series data are frequently observed in critical care settings and are typically characterized by sparsity (missing information) and irregular time intervals. Existing approaches for learning representations in this domain…