相关论文: MambaRain: Multi-Scale Mamba-Attention Framework f…

Video super-resolution remains a major challenge in low-level vision tasks. To date, CNN- and Transformer-based methods have delivered impressive results. However, CNNs are limited by local receptive fields, while Transformers struggle with…

With extreme weather events becoming more common, the risk posed by surface water flooding is ever increasing. In this work we propose a model, and associated Bayesian inference scheme, for generating probabilistic (high-resolution…

In applications such as e-commerce, online education, and streaming services, sequential recommendation systems play a critical role. Despite the excellent performance of self-attention-based sequential recommendation models in capturing…

Leveraging its robust linear global modeling capability, Mamba has notably excelled in computer vision. Despite its success, existing Mamba-based vision models have overlooked the nuances of event-driven tasks, especially in video…

Meteorological agencies around the world rely on real-time flood guidance to issue life-saving advisories and warnings. For decades traditional numerical weather prediction (NWP) models have been state-of-the-art for precipitation…

In this paper, we consider the design of Model Predictive Control (MPC) algorithms based on Mamba neural networks. Mamba is a neural network architecture capable of sub-quadratic computational scaling in sequence length with…

Transformer-based methods have demonstrated remarkable capabilities in 3D semantic segmentation through their powerful attention mechanisms, but the quadratic complexity limits their modeling of long-range dependencies in large-scale point…

Recently, a novel visual state space (VSS) model, referred to as Mamba, has demonstrated significant progress in modeling long sequences with linear complexity, comparable to Transformer models, thereby enhancing its adaptability for…

Mamba is an efficient sequence model that rivals Transformers and demonstrates significant potential as a foundational architecture for various tasks. Quantization is commonly used in neural networks to reduce model size and computational…

Transformer-based methods have achieved remarkable performance in event-based object detection, owing to the global modeling ability. However, they neglect the influence of non-event and noisy regions and process them uniformly, leading to…

Multi-task dense scene understanding, which trains a model for multiple dense prediction tasks, has a wide range of application scenarios. Capturing long-range dependency and enhancing cross-task interactions are crucial to multi-task dense…

Multi-view depth estimation has achieved impressive performance over various benchmarks. However, almost all current multi-view systems rely on given ideal camera poses, which are unavailable in many real-world scenarios, such as autonomous…

Human engagement estimation in conversational scenarios is essential for applications such as adaptive tutoring, remote healthcare assessment, and socially aware human--computer interaction. Engagement is a dynamic, multimodal signal…

Deep learning-based time series forecasting has dominated the short-term precipitation forecasting field with the help of its ability to estimate motion flow in high-resolution datasets. The growing interest in precipitation nowcasting…

Multivariate time series classification (TSC) is critical for various applications in fields such as healthcare and finance. While various approaches for TSC have been explored, important properties of time series, such as shift…

Precipitation nowcasting based on radar echoes plays a crucial role in monitoring extreme weather and supporting disaster prevention. Although deep learning approaches have achieved significant progress, they still face notable limitations.…

This work tackles the problem of Online detection of Take and Release (OTR) of an object in untrimmed egocentric videos. This task is challenging due to severe label imbalance, with temporally sparse positive annotations, and the need for…

State Space Models (SSMs) show significant potential for long-sequence modeling, but their reliance on input order conflicts with the irregular nature of point clouds. Existing approaches often rely on predefined serialization schemes whose…

While recent Transformer and Mamba architectures have advanced point cloud representation learning, they are typically developed for single-task or single-domain settings. Directly applying them to multi-task domain generalization (DG)…

While the Mamba architecture demonstrates superior inference efficiency and competitive performance on short-context natural language processing (NLP) tasks, empirical evidence suggests its capacity to comprehend long contexts is limited…