Related papers: EMMA: Empowering Multi-modal Mamba with Structural…

Accurate detection of cardiac abnormalities from electrocardiogram recordings is regarded as essential for clinical diagnostics and decision support. Traditional deep learning models such as residual networks and transformer architectures…

Spatial-Spectral Mamba (SSM) improves computational efficiency and captures long-range dependencies, addressing Transformer limitations. However, traditional Mamba models overlook rich spectral information in HSIs and struggle with high…

Large language models (LLMs) have advanced significantly due to the attention mechanism, but their quadratic complexity and linear memory demands limit their performance on long-context tasks. Recently, researchers introduced Mamba, an…

Mamba has recently gained widespread attention as a backbone model for point cloud modeling, leveraging a state-space architecture that enables efficient global sequence modeling with linear complexity. However, its lack of local inductive…

Recent advancements in multivariate time series forecasting have been propelled by Linear-based, Transformer-based, and Convolution-based models, with Transformer-based architectures gaining prominence for their efficacy in temporal and…

Recent progress in remote sensing image (RSI) super-resolution (SR) has exhibited remarkable performance using deep neural networks, e.g., Convolutional Neural Networks and Transformers. However, existing SR methods often suffer from either…

Category-level object pose estimation is fundamental for embodied intelligence, yet achieving robust generalization to unseen instances remains challenging. However, existing methods mainly rely on simple feature extraction and aggregation,…

Depression is a prevalent mental health disorder that severely impairs daily functioning and quality of life. While recent deep learning approaches for depression detection have shown promise, most rely on limited feature types, overlook…

We propose EMMA, an efficient and unified architecture for multimodal understanding, generation and editing. Specifically, EMMA primarily consists of 1) An efficient autoencoder with a 32x compression ratio, which significantly reduces the…

Multi-Modal Image Fusion (MMIF) aims to combine images from different modalities to produce fused images, retaining texture details and preserving significant information. Recently, some MMIF methods incorporate frequency domain information…

Multimodal Large Language Models (MLLMs) have showcased impressive skills in tasks related to visual understanding and reasoning. Yet, their widespread application faces obstacles due to the high computational demands during both the…

Monocular depth estimation provides an additional depth dimension to RGB images, making it widely applicable in various fields such as virtual reality, autonomous driving and robotic navigation. However, existing depth estimation algorithms…

We introduce MARL-MambaContour, the first contour-based medical image segmentation framework based on Multi-Agent Reinforcement Learning (MARL). Our approach reframes segmentation as a multi-agent cooperation task focused on generate…

Recent advancements in medical imaging have resulted in more complex and diverse images, with challenges such as high anatomical variability, blurred tissue boundaries, low organ contrast, and noise. Traditional segmentation methods…

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…

Inspired by the recent success of the Mamba architecture in vision and language domains, we introduce a Unified Attention-Mamba (UAM) backbone. Unlike previous hybrid approaches that integrate Attention and Mamba modules in fixed…

Neuron segmentation is the cornerstone of reconstructing comprehensive neuronal connectomes, which is essential for deciphering the functional organization of the brain. The irregular morphology and densely intertwined structures of neurons…

Diffusion models have achieved great success in image generation, with the backbone evolving from U-Net to Vision Transformers. However, the computational cost of Transformers is quadratic to the number of tokens, leading to significant…

An ecosystem of Transformer-based models has been established by building large models with extensive data. Parameter-efficient fine-tuning (PEFT) is a crucial technology for deploying these models to downstream tasks with minimal cost…

The development of Multimodal Large Language Models (MLLMs) has seen significant advancements with increasing demands in various fields (e.g., multimodal agents, embodied intelligence). While model-driven approaches attempt to enhance MLLMs…