Related papers: VisionTS++: Cross-Modal Time Series Foundation Mod…
Multivariate time series forecasting (MTSF) is a fundamental problem in numerous real-world applications. Recently, Transformer has become the de facto solution for MTSF, especially for the long-term cases. However, except for the one…
Traditional fault diagnosis methods using Convolutional Neural Networks (CNNs) often struggle with capturing the temporal dynamics of vibration signals. To overcome this, the application of Transformer-based Vision Transformer (ViT) methods…
Irregularly sampled time series are increasingly prevalent, particularly in medical domains. While various specialized methods have been developed to handle these irregularities, effectively modeling their complex dynamics and pronounced…
While recent advancements in foundation models have significantly impacted machine learning, rigorous tests on the performance of time series foundation models (TSFMs) remain largely underexplored. This paper presents an empirical study…
Forecasting Multivariate Time Series (MTS) involves significant challenges in various application domains. One immediate challenge is modeling temporal patterns with the finite length of the input. These temporal patterns usually involve…
Large language models (LLMs) have been introduced to time series forecasting (TSF) to incorporate contextual knowledge beyond numerical signals. However, existing studies question whether LLMs provide genuine benefits, often reporting…
Vision-Language Foundation Models (VLFMs) have made remarkable progress on various multimodal tasks, such as image captioning, image-text retrieval, visual question answering, and visual grounding. However, most methods rely on training…
Visual Place Recognition (VPR) has evolved from handcrafted descriptors to deep learning approaches, yet significant challenges remain. Current approaches, including Vision Foundation Models (VFMs) and Multimodal Large Language Models…
Time series foundation models (TSFMs) have become increasingly popular for zero-shot forecasting. However, for a new time series domain not fully covered by the pretraining set, performance can suffer. Therefore, when a practitioner cares…
In this paper, we introduce Masked Multi-Step Multivariate Forecasting (MMMF), a novel and general self-supervised learning framework for time series forecasting with known future information. In many real-world forecasting scenarios, some…
This study investigates zero-shot forecasting capabilities of Time Series Foundation Models (TSFMs) for macroeconomic indicators. We apply TSFMs to forecasting economic indicators under univariate conditions, bypassing the need for train…
Vision-Language Models (VLMs) have demonstrated strong capabilities in aligning visual and textual modalities, enabling a wide range of applications in multimodal understanding and generation. While they excel in zero-shot and transfer…
Machine learning methods trained on raw numerical time series data exhibit fundamental limitations such as a high sensitivity to the hyper parameters and even to the initialization of random weights. A combination of a recurrent neural…
Multivariate Time Series Forecasting (MTSF) has long been a key research focus. Traditionally, these studies assume a fixed number of variables, but in real-world applications, Cyber-Physical Systems often expand as new sensors are…
With the success of pre-trained language models (PLMs) in various application fields beyond natural language processing, language models have raised emerging attention in the field of time series forecasting (TSF) and have shown great…
Effective resource allocation in higher education depends on reliable enrolment forecasts, yet institutional planners frequently face data series disrupted by structural shifts. This paper investigates whether zero-shot Time Series…
With abundant, unlabeled real faces, how can we learn robust and transferable facial representations to boost generalization across various face security tasks? We make the first attempt and propose FS-VFM, a scalable self-supervised…
Time series forecasting is a fundamental task with broad applications, yet conventional methods often treat data as discrete sequences, overlooking their origin as noisy samples of continuous processes. Crucially, discrete noisy…
Forecasting the behaviour of complex dynamical systems such as interconnected sensor networks characterized by high-dimensional multivariate time series(MTS) is of paramount importance for making informed decisions and planning for the…
Multivariate time series forecasting (MTSF) seeks to model temporal dynamics among variables to predict future trends. Transformer-based models and large language models (LLMs) have shown promise due to their ability to capture long-range…