Related papers: RoadMamba: A Dual Branch Visual State Space Model …

Mamba-based architectures have shown to be a promising new direction for deep learning models owing to their competitive performance and sub-quadratic deployment speed. However, current Mamba multi-modal large language models (MLLM) are…

As a deep learning model, Visual Mamba (VMamba) has a low computational complexity and a global receptive field, which has been successful applied to image classification and detection. To extend its applications, we apply VMamba to crowd…

Autonomous driving systems face significant challenges in perceiving complex environments and making real-time decisions. Traditional modular approaches, while offering interpretability, suffer from error propagation and coordination…

In recent years, robust matching methods using deep learning-based approaches have been actively studied and improved in computer vision tasks. However, there remains a persistent demand for both robust and fast matching techniques. To…

Remote sensing images are becoming increasingly widespread in military, earth resource exploration. Because of the limitation of a single sensor, we can obtain high spatial resolution grayscale panchromatic (PAN) images and low spatial…

Although Sentinel-2 based land use and land cover (LULC) classification is critical for various environmental monitoring applications, it is a very difficult task due to some key data challenges (e.g., spatial heterogeneity, context…

Multimodal Aspect-based Sentiment Analysis (MABSA) enhances sentiment detection by integrating textual data with complementary modalities, such as images, to provide a more refined and comprehensive understanding of sentiment. However,…

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…

Unsupervised graph-level anomaly detection (UGLAD) is a critical and challenging task across various domains, such as social network analysis, anti-cancer drug discovery, and toxic molecule identification. However, existing methods often…

High-performance semantic segmentation has achieved significant progress in recent years, often driven by increasingly large backbones and higher computational budgets. While effective, such approaches introduce substantial computational…

VADMamba pioneered the introduction of Mamba to Video Anomaly Detection (VAD), achieving high accuracy and fast inference through hybrid proxy tasks. Nevertheless, its heavy reliance on optical flow as auxiliary input and inter-task fusion…

In recent years, visually-rich document understanding has attracted increasing attention. Transformer-based pre-trained models have become the mainstream approach, yielding significant performance gains in this field. However, the…

Semantic segmentation of multi-source remote sensing images is a fundamental task for Earth observation applications. Existing methods often struggle with insufficient multi-scale context modeling and suboptimal cross-modal feature fusion,…

Mamba, a special case of the State Space Model, is gaining popularity as an alternative to template-based deep learning approaches in medical image analysis. While transformers are powerful architectures, they have drawbacks, including…

In the era of large-scale pre-trained models, effectively adapting general knowledge to specific affective computing tasks remains a challenge, particularly regarding computational efficiency and multimodal heterogeneity. While…

Vision state space models inherit the efficiency and long-range modeling ability of Mamba-style selective scans. However, their performance depends critically on the representation of two-dimensional visual features as one-dimensional token…

In the field of multimodal medical data analysis, leveraging diverse types of data and understanding their hidden relationships continues to be a research focus. The main challenges lie in effectively modeling the complex interactions…

The attention mechanism has become a dominant operator in point cloud learning, but its quadratic complexity leads to limited inter-point interactions, hindering long-range dependency modeling between objects. Due to excellent long-range…

Fake artefacts for discriminating between bonafide and fake audio can exist in both short- and long-range segments. Therefore, combining local and global feature information can effectively discriminate between bonafide and fake audio. This…

In recent years, Transformers have become the de-facto architecture for sequence modeling on text and a variety of multi-dimensional data, such as images and video. However, the use of self-attention layers in a Transformer incurs…