Related papers: GRAM-MAMBA: Holistic Feature Alignment for Wireles…

Task failures in prior fine-grained robotic manipulation methods often stem from suboptimal initial grasping, which is critical for subsequent manipulation and reducing the requirement for complex pose adjustments. To address this, we…

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…

Cross-modal alignment is crucial for multimodal representation fusion due to the inherent heterogeneity between modalities. While Transformer-based methods have shown promising results in modeling inter-modal relationships, their quadratic…

U-shaped architectures have long dominated the field of medical image segmentation, while Transformers are widely employed for modeling long-range dependencies. The former typically handles scale variations implicitly by aggregating…

Collaborative perception integrates multi-agent perspectives to enhance the sensing range and overcome occlusion issues. While existing multimodal approaches leverage complementary sensors to improve performance, they are highly prone to…

Sequential recommendation systems aim to predict users' next preferences based on their interaction histories, but existing approaches face critical limitations in efficiency and multi-scale pattern recognition. While Transformer-based…

Cross-modality fusing complementary information from different modalities effectively improves object detection performance, making it more useful and robust for a wider range of applications. Existing fusion strategies combine different…

Accurate traffic forecasting is crucial for intelligent transportation systems, supporting effective traffic management, congestion reduction, and informed urban planning. However, traditional models often fail to adequately capture the…

With the rise of Visual and Language Pretraining (VLP), an increasing number of downstream tasks are adopting the paradigm of pretraining followed by fine-tuning. Although this paradigm has demonstrated potential in various multimodal…

Micro-gesture recognition (MGR) targets the identification of subtle and fine-grained human motions and requires accurate modeling of both long-range and local spatiotemporal dependencies. While CNNs are effective at capturing local…

Multi-modal MRI offers valuable complementary information for diagnosis and treatment; however, its utility is limited by prolonged scanning times. To accelerate the acquisition process, a practical approach is to reconstruct images of the…

Multimodal learning seeks to utilize data from multiple sources to improve the overall performance of downstream tasks. It is desirable for redundancies in the data to make multimodal systems robust to missing or corrupted observations in…

Multi-modal fusion holds great promise for integrating information from different modalities. However, due to a lack of consideration for modal consistency, existing multi-modal fusion methods in the field of remote sensing still face…

Video understanding is a complex challenge that requires effective modeling of spatial-temporal dynamics. With the success of image foundation models (IFMs) in image understanding, recent approaches have explored parameter-efficient…

Multimodal semantic segmentation integrates complementary information from diverse sensors for remote sensing Earth observation. However, practical systems often encounter missing modalities due to sensor failures or incomplete coverage,…

Human activity recognition (HAR) from inertial sensors is essential for ubiquitous computing, mobile health, and ambient intelligence. Conventional deep models such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs),…

Human-human interaction generation has garnered significant attention in motion synthesis due to its vital role in understanding humans as social beings. However, existing methods typically rely on transformer-based architectures, which…

Magnetic Resonance Fingerprinting (MRF) enables fast quantitative imaging by matching signal evolutions to a predefined dictionary. However, conventional dictionary matching suffers from exponential growth in computational cost and memory…

Self-supervised pretraining is promising for large-scale neuroimaging, yet the impact of region-aware masking and hybrid sequence modeling remains underexplored. In this work, we introduce Rhamba, a region-aware pretraining framework that…

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…