17 accepted papers
Time series forecasting under distribution shift remains challenging, as existing deep learning models often rely on local statistical normalization (e.g., mean and variance) that fails to capture global distribution shift. Methods like RevIN and its variants attempt to decouple distribution and pat
Bi-temporal satellite imagery supports critical applications such as urbanization monitoring and disaster assessment. Although powerful multimodal large language models~(MLLMs) have been applied in bi-temporal change analysis, previous methods process image pairs through direct concatenation, inadeq…
High-order control barrier functions (HOCBFs) that can achieve strict safety guarantees are widely used in robot safety control. However, robot obstacle avoidance in narrow environments with curved surfaces, as represented by aircraft blade detection, is still a challenge. Considering the narrow spa…
We present Zeus, a unified tuning-free Time Series Foundation Model (TSFM) that delivers superior performance across diverse analysis tasks without any task-specific fine-tuning. Unlike prior studies that primarily focus on zero-shot forecasting but require task-specific tuning for other tasks, Zeus…
Wearable devices record physiological and behavioral signals that can improve health predictions. While foundation models are increasingly used for such predictions, they have been primarily applied to low-level sensor data, despite behavioral data often being more informative due to their alignment…
Transformers have gained attention in atmospheric time series forecasting (ATSF) for their ability to capture global spatial-temporal correlations. However, their complex architectures lead to excessive parameter counts and extended training times, limiting their scalability to large-scale forecasti…
Class Incremental Learning (CIL) aims to enable models to learn new classes sequentially while retaining knowledge of previous ones. Although current methods have alleviated catastrophic forgetting (CF), recent studies highlight that the performance of CIL models is highly sensitive to the order of…
Benefiting from high capacity for capturing complex temporal patterns, deep learning (DL) has significantly advanced time series forecasting (TSF). However, deep models tend to suffer from severe overfitting due to the inherent vulnerability of time series to noise and anomalies. The prevailing DL p…
Complex spatial dependencies in transportation networks make traffic prediction extremely challenging. Much existing work is devoted to learning dynamic graph structures among sensors, and the strategy of mining spatial dependencies from traffic data, known as data-driven, tends to be an intuitive a…
As a fundamental problem in multimodal learning multimodal fusion aims to compensate for the inherent limitations of a single modality. One challenge of multimodal fusion is that the unimodal data in their unique embedding space mostly contains potential noise which leads to corrupted cross-modal in…
This paper studies the problem of continual learning in an open-world scenario, referred to as Open-world Continual Learning (OwCL). OwCL is increasingly rising while it is highly challenging in two-fold: i) learning a sequence of tasks without forgetting knowns in the past, and ii) identifying unkn…
Identifying causal relations from purely observational data typically requires additional assumptions on relations and/or noise. Most current methods restrict their analysis to datasets that are assumed to have pure linear or nonlinear relations, which is often not reflective of real-world datasets…
Detecting small objects in Unmanned Aerial Vehicle (UAV) images is pivotal for a multitude of applications. Given the high-altitude perspective of UAVs, the images they capture often feature intricate backgrounds, pronounced object heterogeneity, and a plethora of sparsely situated small targets. Th…
Recently, the Vision Transformer (ViT) has achieved outstanding performance in various computer vision tasks. Positional encoding is an indispensable component of ViT for handling the inherent structural information of images. However, attaching position encodings manually is a time-consuming proces…
Detecting fraud is an urgent task to avoid transaction risks. Especially when expanding a business to new cities or new countries, developing a totally new model will bring the cost issue and result in forgetting previous knowledge. This study proposes a novel solution based on heterogeneous trade g…
To efficiently process and understand a large amount of incoming visual information from first-person perspective (i.e. egocentric vision), predicting human gaze is important. However, even though people continuously gaze in noisy environments, most existing gaze prediction methods mainly use image…
Absorption, scattering, and color distortion are three major issues in underwater optical imaging. Light rays traveling through water are scattered and absorbed according to their wavelength. Scattering is caused by large suspended particles that degrade optical images captured underwater. Color dis…