Time-VLM：探索多模态视觉-语言模型用于增强时间序列预测
Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting
AI总结：
Time-VLM提出一种多模态框架，融合预训练视觉-语言模型，通过检索、视觉和文本增强学习器协同工作，提升时间序列预测性能，尤其在少样本和零样本场景下表现优异。
摘要：
近期时间序列预测的进展探索了通过文本或视觉模态增强模型以提高准确性。虽然文本提供了上下文理解，但往往缺乏细粒度的时间细节。相反，视觉捕捉复杂的时间模式，但缺乏语义上下文，限制了这些模态的互补潜力。为解决这一问题，我们提出Time-VLM，一种新颖的多模态框架，利用预训练的视觉-语言模型（VLMs）桥接时间、视觉和文本模态以增强预测。我们的框架包含三个关键组件：（1）检索增强学习器，通过记忆库交互提取丰富的时间特征；（2）视觉增强学习器，将时间序列编码为信息丰富的图像；（3）文本增强学习器，生成上下文相关的文本描述。这些组件与冻结的预训练VLMs协作生成多模态嵌入，然后与时间特征融合以进行最终预测。大量实验表明，Time-VLM在少样本和零样本场景中尤其表现出卓越性能，从而为多模态时间序列预测开辟了新方向。代码可在https://github.com/CityMind-Lab/ICML25-TimeVLM获取。
英文摘要：
Recent advancements in time series forecasting have explored augmenting models with text or vision modalities to improve accuracy. While text provides contextual understanding, it often lacks fine-grained temporal details. Conversely, vision captures intricate temporal patterns but lacks semantic context, limiting the complementary potential of these modalities. To address this, we propose \method, a novel multimodal framework that leverages pre-trained Vision-Language Models (VLMs) to bridge temporal, visual, and textual modalities for enhanced forecasting. Our framework comprises three key components: (1) a Retrieval-Augmented Learner, which extracts enriched temporal features through memory bank interactions; (2) a Vision-Augmented Learner, which encodes time series as informative images; and (3) a Text-Augmented Learner, which generates contextual textual descriptions. These components collaborate with frozen pre-trained VLMs to produce multimodal embeddings, which are then fused with temporal features for final prediction. Extensive experiments demonstrate that Time-VLM achieves superior performance, particularly in few-shot and zero-shot scenarios, thereby establishing a new direction for multimodal time series forecasting. Code is available at https://github.com/CityMind-Lab/ICML25-TimeVLM.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
