Related papers: Selecting and Pruning: A Differentiable Causal Seq…
Correspondence selection aims to correctly select the consistent matches (inliers) from an initial set of putative correspondences. The selection is challenging since putative matches are typically extremely unbalanced, largely dominated by…
Training deep learning models for semantic occupancy prediction is challenging due to factors such as a large number of occupancy cells, severe occlusion, limited visual cues, complicated driving scenarios, etc. Recent methods often adopt…
We introduce VideoMamba, a novel adaptation of the pure Mamba architecture, specifically designed for video recognition. Unlike transformers that rely on self-attention mechanisms leading to high computational costs by quadratic complexity,…
In various domains, Sequential Recommender Systems (SRS) have become essential due to their superior capability to discern intricate user preferences. Typically, SRS utilize transformer-based architectures to forecast the subsequent item…
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…
We identify a routing paradox in hybrid sequence models: content-based routing - deciding which tokens deserve expensive attention - requires pairwise computation, and this requirement is inescapable. Through 20+ controlled experiments…
Although change detection using MODIS time series is critical for environmental monitoring, it is a highly challenging task due to key MODIS difficulties, e.g., mixed pixels, spatial-spectral-temporal information coupling effect, and…
Motion forecasting is a crucial component of autonomous driving systems, enabling the generation of accurate and smooth future trajectories to ensure safe navigation to the destination. In previous methods, potential future trajectories are…
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…
Multivariate time series forecasting is fundamental to numerous domains such as energy, finance, and environmental monitoring, where complex temporal dependencies and cross-variable interactions pose enduring challenges. Existing…
The Transformer architecture has shown a remarkable ability in modeling global relationships. However, it poses a significant computational challenge when processing high-dimensional medical images. This hinders its development and…
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,…
Recent advances in Vision Transformers (ViTs) and State Space Models (SSMs) have challenged the dominance of Convolutional Neural Networks (CNNs) in computer vision. ViTs excel at capturing global context, and SSMs like Mamba offer linear…
Multimodal large language models (MLLMs) have attracted widespread interest and have rich applications. However, the inherent attention mechanism in its Transformer structure requires quadratic complexity and results in expensive…
Underwater images often suffer from severe degradation, such as color distortion, low contrast, and blurred details, due to light absorption and scattering in water. While learning-based methods like CNNs and Transformers have shown…
In recent speech enhancement (SE) research, transformer and its variants have emerged as the predominant methodologies. However, the quadratic complexity of the self-attention mechanism imposes certain limitations on practical deployment.…
Sequential recommendation systems aim to provide personalized recommendations by analyzing dynamic preferences and dependencies within user behavior sequences. Recently, Transformer models can effectively capture user preferences. However,…
Vision Mamba has emerged as a promising and efficient alternative to Vision Transformers, yet its efficiency remains fundamentally constrained by the number of input tokens. Existing token reduction approaches typically adopt token pruning…
Multimodal fusion has made great progress in the field of remote sensing image classification due to its ability to exploit the complementary spatial-spectral information. Deep learning methods such as CNN and Transformer have been widely…
Understanding the inter-relations and interactions between tasks is crucial for multi-task dense prediction. Existing methods predominantly utilize convolutional layers and attention mechanisms to explore task-level interactions. In this…