Related papers: VIFO: Visual Feature Empowered Multivariate Time S…

Some data from multiple sources can be modeled as multimodal time-series events which have different sampling frequencies, data compositions, temporal relations and characteristics. Different types of events have complex nonlinear…

Foundation models for vision and language are the basis of AI applications across numerous sectors of society. The success of these models stems from their ability to mimic human capabilities, namely visual perception in vision models, and…

Transformer-based models have significantly advanced time series forecasting. Recent work, like the Cross-Attention-only Time Series transformer (CATS), shows that removing self-attention can make the model more accurate and efficient.…

Conventionally, spatiotemporal modeling network and its complexity are the two most concentrated research topics in video action recognition. Existing state-of-the-art methods have achieved excellent accuracy regardless of the complexity…

Accurate workload forecasting is critical for efficient resource management in cloud computing systems, enabling effective scheduling and autoscaling. Despite recent advances with transformer-based forecasting models, challenges remain due…

Traffic prediction is a challenging spatio-temporal forecasting problem that involves highly complex spatio-temporal correlations. This paper proposes a Multi-level Multi-view Augmented Spatio-temporal Transformer (LVSTformer) for traffic…

Recent advancements in Video Large Language Models (VideoLLMs) have enabled strong performance across diverse multimodal video tasks. To reduce the high computational cost of processing dense video frames, efficiency-oriented methods such…

Modern Vision-Language Models (VLMs) can solve a wide range of tasks requiring visual reasoning. In real-world scenarios, desirable properties for VLMs include fast inference and controllable generation (e.g., constraining outputs to adhere…

Cross-modal misalignments, such as spatial offsets, resolution discrepancies, and semantic deficiencies, frequently occur in visible-infrared object detection (VI-OD). To mitigate this, existing methods are typically adapted into an…

Multimodal large language models (MLLMs) typically extract visual features from the final layers of a pretrained Vision Transformer (ViT). This widespread deep-layer bias, however, is largely driven by empirical convention rather than…

Multimodal large language models (MLLMs) achieve remarkable progress in cross-modal perception and reasoning, yet a fundamental question remains unresolved: should the vision encoder be fine-tuned or frozen? Despite the success of models…

Long-term time series forecasting (LTSF) is a crucial aspect of modern society, playing a pivotal role in facilitating long-term planning and developing early warning systems. While many Transformer-based models have recently been…

Large Language Models (LLMs) have emerged as a promising paradigm for time series analytics, leveraging their massive parameters and the shared sequential nature of textual and time series data. However, a cross-modality gap exists between…

Multimodal sentiment analysis has a wide range of applications due to its information complementarity in multimodal interactions. Previous works focus more on investigating efficient joint representations, but they rarely consider the…

Although LLMs have demonstrated remarkable capabilities in processing and generating textual data, their pre-trained vocabularies are ill-suited for capturing the nuanced temporal dynamics and patterns inherent in time series. The discrete,…

As the real propagation environment becomes in creasingly complex and dynamic, millimeter wave beam prediction faces huge challenges. However, the powerful cross modal representation capability of vision-language model (VLM) provides a…

Massive multiple-input multiple-output (MIMO) is a key enabler for the high data rates required by the sixth-generation networks, yet its performance hinges on effective beam management with low training overhead. This paper proposes an…

We develop an approach to learning visual representations that embraces multimodal data, driven by a combination of intra- and inter-modal similarity preservation objectives. Unlike existing visual pre-training methods, which solve a proxy…

Satellite image time series (SITS) provide continuous observations of the Earth's surface, making them essential for applications such as environmental management and disaster assessment. However, existing spatiotemporal foundation models…

Visible and infrared image fusion (VIF) has gained significant attention in recent years due to its wide application in tasks such as scene segmentation and object detection. VIF methods can be broadly classified into traditional VIF…