Related papers: EventMamba: Enhancing Spatio-Temporal Locality wit…
Transformers have demonstrated impressive results for 3D point cloud semantic segmentation. However, the quadratic complexity of transformer makes computation costs high, limiting the number of points that can be processed simultaneously…
Long-term time series forecasting (LTSF) provides longer insights into future trends and patterns. Over the past few years, deep learning models especially Transformers have achieved advanced performance in LTSF tasks. However, LTSF faces…
EEG-based emotion recognition holds significant potential in the field of brain-computer interfaces. A key challenge lies in extracting discriminative spatiotemporal features from electroencephalogram (EEG) signals. Existing studies often…
Volume Electron Microscopy (VEM) is crucial for 3D tissue imaging but often produces anisotropic data with poor axial resolution, hindering visualization and downstream analysis. Existing methods for isotropic reconstruction often suffer…
Multi-modal image fusion integrates complementary information from different modalities to produce enhanced and informative images. Although State-Space Models, such as Mamba, are proficient in long-range modeling with linear complexity,…
Visual Geometry Grounded Transformers (VGGT) have set new benchmarks in high-fidelity 3D scene reconstruction. However, as the sequence length increases, these models suffer from catastrophic geometric forgetting and accumulation drift,…
Recent deep learning approaches for river discharge forecasting have improved the accuracy and efficiency in flood forecasting, enabling more reliable early warning systems for risk management. Nevertheless, existing deep learning…
Recent advances in deep learning structured state space models, especially the Mamba architecture, have demonstrated remarkable performance improvements while maintaining linear complexity. In this study, we introduce functional…
Physics-informed machine learning (PIML) has emerged as a promising alternative to classical methods for predicting dynamical systems, offering faster and more generalizable solutions. However, existing models, including recurrent neural…
Convolutional neural networks have primarily led 3D medical image segmentation but may be limited by small receptive fields. Transformer models excel in capturing global relationships through self-attention but are challenged by high…
Recently, Mamba-based methods have become popular in medical image segmentation due to their lightweight design and long-range dependency modeling capabilities. However, current segmentation methods frequently encounter challenges in fetal…
Recent years have seen significant advancements in image restoration, largely attributed to the development of modern deep neural networks, such as CNNs and Transformers. However, existing restoration backbones often face the dilemma…
Human trajectory forecasting is crucial for safe navigation in crowded environments, requiring models that balance accuracy with computational efficiency. Efficiently modeling social interactions is key to performance in dense crowds. Yet,…
We introduce a novel state-space architecture for diffusion models, effectively harnessing spatial and frequency information to enhance the inductive bias towards local features in input images for image generation tasks. While state-space…
In scene text detection, Transformer-based methods have addressed the global feature extraction limitations inherent in traditional convolution neural network-based methods. However, most directly rely on native Transformer attention layers…
Recent advancements in sRGB-to-RAW de-rendering have increasingly emphasized metadata-driven approaches to reconstruct RAW data from sRGB images, supplemented by partial RAW information. In image-based de-rendering, metadata is commonly…
Deep learning models like Convolutional Neural Networks and transformers have shown impressive capabilities in speech verification, gaining considerable attention in the research community. However, CNN-based approaches struggle with…
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…
Recently the state space models (SSMs) with efficient hardware-aware designs, i.e., the Mamba deep learning model, have shown great potential for long sequence modeling. Meanwhile building efficient and generic vision backbones purely upon…
State Space Models (SSMs) have emerged as powerful alternatives to attention-based Transformers, with Mamba demonstrating impressive efficiency and scalability. As these models grow increasingly larger, the need for Parameter-Efficient…