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

Existing RGBT tracking methods often design various interaction models to perform cross-modal fusion of each layer, but can not execute the feature interactions among all layers, which plays a critical role in robust multimodal…

Multi-modal object tracking has attracted considerable attention by integrating multiple complementary inputs (e.g., thermal, depth, and event data) to achieve outstanding performance. Although current general-purpose multi-modal trackers…

In this paper, we reveal that most current efficient multimodal fine-tuning methods are hindered by a key limitation: they are directly borrowed from LLMs, often neglecting the intrinsic differences of multimodal scenarios and even…

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…

Missing modalities present a fundamental challenge in multimodal models, often causing catastrophic performance degradation. Our observations suggest that this fragility stems from an imbalanced learning process, where the model develops an…

Remote sensing change detection (CD) has made significant advancements with the adoption of Convolutional Neural Networks (CNNs) and Transformers. While CNNs offer powerful feature extraction, they are constrained by receptive field…

Multimodal Sentiment Analysis (MSA) with missing modalities has attracted increasing attention recently. While current Transformer-based methods leverage dense text information to maintain model robustness, their quadratic complexity…

Recent Mamba-based architectures for video understanding demonstrate promising computational efficiency and competitive performance, yet struggle with overfitting issues that hinder their scalability. To overcome this challenge, we…

Accurate building segmentation and height estimation from single-view RGB satellite imagery are fundamental for urban analytics, yet remain ill-posed due to structural variability and the high computational cost of global context modeling.…

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…

Multimodal sensors provide complementary information to develop accurate machine-learning methods for human activity recognition (HAR), but introduce significantly higher computational load, which reduces efficiency. This paper proposes an…

Leveraging the complementary characteristics of visible (RGB) and infrared (IR) imagery offers significant potential for improving object detection. In this paper, we propose WaveMamba, a cross-modality fusion method that efficiently…

Radar-based Human Activity Recognition (HAR) is an attractive alternative to wearables and cameras because it preserves privacy, and is contactless and robust to occlusions. However, dominant Convolutional Neural Network (CNN)- and…

Recent learned image compression (LIC) leverages Mamba-style state-space models (SSMs) for global receptive fields with linear complexity. However, the standard Mamba adopts content-agnostic, predefined raster (or multi-directional) scans…

Infrared Image Super-Resolution (IRSR) is challenged by the low contrast and sparse textures of infrared data, requiring robust long-range modeling to maintain global coherence. While State-Space Models like Mamba offer proficiency in…

Recent advances in multi-modal detection have significantly improved detection accuracy in challenging environments (e.g., low light, overexposure). By integrating RGB with modalities such as thermal and depth, multi-modal fusion increases…

Training urban spatio-temporal foundation models that generalize well across diverse regions and cities is critical for deploying urban services in unseen or data-scarce regions. Recent studies have typically focused on fusing cross-domain…

Mimicking the real interaction trajectory in the inference of the world model has been shown to improve the sample efficiency of model-based reinforcement learning (MBRL) algorithms. Many methods directly use known state sequences for…

While integrating multiple modalities has the potential to improve environmental monitoring, current approaches struggle to combine data sources with heterogeneous formats or contents. A central difficulty arises when combining continuous…

Multimodal learning typically relies on the assumption that all modalities are fully available during both the training and inference phases. However, in real-world scenarios, consistently acquiring complete multimodal data presents…