相关论文: KARMA: A Multilevel Decomposition Hybrid Mamba Fra…

Despite the remarkable quality of LLM-based text-to-speech systems, their reliance on autoregressive Transformers leads to quadratic computational complexity, which severely limits practical applications. Linear-time alternatives, notably…

This paper presents a framework for universal sound separation and polyphonic audio classification, addressing the challenges of separating and classifying individual sound sources in a multichannel mixture. The proposed framework,…

Optimal adaptive bitrate (ABR) decision depends on a comprehensive characterization of state transitions that involve interrelated modalities over time including environmental observations, returns, and actions. However, state-of-the-art…

Traffic crash detection in long-form surveillance videos is essential for improving emergency response and infrastructure planning, yet remains difficult due to the brief and infrequent nature of crash events. We present…

State space models, such as Mamba, have recently garnered attention in time series forecasting due to their ability to capture sequence patterns. However, in electricity consumption benchmarks, Mamba forecasts exhibit a mean error of…

Recent Mamba-based architectures for video understanding demonstrate promising computational efficiency and competitive performance, yet struggle with overfitting issues that hinder their scalability. To overcome this challenge, we…

Transformer-based methods for 3D human pose estimation face significant computational challenges due to the quadratic growth of self-attention mechanism complexity with sequence length. Recently, the Mamba model has substantially reduced…

In this paper we present CARMA, a language recently defined to support specification and analysis of collective adaptive systems. CARMA is a stochastic process algebra equipped with linguistic constructs specifically developed for modelling…

Convolutional neural networks (CNN) and Transformers have made impressive progress in the field of remote sensing change detection (CD). However, both architectures have inherent shortcomings: CNN are constrained by a limited receptive…

The quadratic complexity of the attention mechanism in Transformer models has motivated the development of alternative architectures with sub-quadratic scaling, such as state-space models. Among these, Mamba has emerged as a leading…

Although learned video compression methods have exhibited outstanding performance, most of them typically follow a hybrid coding paradigm that requires explicit motion estimation and compensation, resulting in a complex solution for video…

Recent advances in video anomaly detection (VAD) mainly focus on ground-based surveillance or unmanned aerial vehicle (UAV) videos with static backgrounds, whereas research on UAV videos with dynamic backgrounds remains limited. Unlike…

The LiDAR 3D object detector that strikes a balance between accuracy and speed is crucial for achieving real-time perception in autonomous driving. However, many existing LiDAR detection models depend on complex feature transformations,…

Large language models (LLMs) struggle with compositional generalisation, limiting their ability to systematically combine learned components to interpret novel inputs. While architectural modifications, fine-tuning, and data augmentation…

Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge with self-improvement…

Numerous CNN-Transformer hybrid models rely on high-complexity global attention mechanisms to capture long-range dependencies, which introduces non-linear computational complexity and leads to significant resource consumption. Although…

Understanding the robustness of deep learning models for multivariate long-term time series forecasting (M-LTSF) remains challenging, as evaluations typically rely on real-world datasets with unknown noise properties. We propose a…

In the field of self-supervised depth estimation, Convolutional Neural Networks (CNNs) and Transformers have traditionally been dominant. However, both architectures struggle with efficiently handling long-range dependencies due to their…

Accurate medical image segmentation remains challenging due to blurred lesion boundaries (LBA), loss of high-frequency details (LHD), and difficulty in modeling long-range anatomical structures (DC-LRSS). Vision Mamba employs…

In this paper we introduce the Kumaraswamy autoregressive moving average models (KARMA), which is a dynamic class of models for time series taking values in the double bounded interval $(a,b)$ following the Kumaraswamy distribution. The…