Related papers: Axial-Relation Guided Fusion State Space Model for…
Long-range 3D object detection remains challenging because LiDAR observations become highly sparse and fragmented in the far field, making reliable context modeling difficult for existing detectors. To address this issue, recent state space…
Multispectral (MS) and panchromatic (PAN) images describe the same land surface, so these images not only have their own advantages, but also have a lot of similar information. In order to separate these similar information and their…
Reliable 3D object detection is fundamental to autonomous driving, and multimodal fusion algorithms using cameras and LiDAR remain a persistent challenge. Cameras provide dense visual cues but ill posed depth; LiDAR provides a precise 3D…
Skeleton action recognition involves recognizing human action from human skeletons. The use of graph convolutional networks (GCNs) has driven major advances in this recognition task. In real-world scenarios, the captured skeletons are not…
State-space modeling has emerged as a powerful paradigm for sequence analysis in various tasks such as natural language processing, time-series forecasting, and signal processing. In this work, we propose an \emph{Adaptive State-Space…
Semantic Change Detection (SCD) from remote sensing imagery requires models balancing extensive spatial context, computational efficiency, and sensitivity to class-imbalanced land-cover transitions. While Convolutional Neural Networks excel…
By sharing complementary perceptual information, multi-agent collaborative perception fosters a deeper understanding of the environment. Recent studies on collaborative perception mostly utilize CNNs or Transformers to learn feature…
Multi-modal Emotion Recognition in Conversation (MERC) has received considerable attention in various fields, e.g., human-computer interaction and recommendation systems. Most existing works perform feature disentanglement and fusion to…
Multimodal large language models (MLLMs), such as GPT-4o, Gemini, LLaVA, and Flamingo, have made significant progress in integrating visual and textual modalities, excelling in tasks like visual question answering (VQA), image captioning,…
Medical image super-resolution (SR) is essential for enhancing diagnostic accuracy while reducing acquisition cost and scanning time. However, modeling both long-range anatomical structures and fine-grained frequency details with low…
Radar-camera depth estimation must turn an ultra-sparse, all-weather, metric radar signal into a dense per-pixel depth map. Existing methods -- concatenation, confidence-aware gating, sparse supervision, graph-based extraction -- combine…
Recent 2D CNN-based domain adaptation approaches struggle with long-range dependencies due to limited receptive fields, making it difficult to adapt to target domains with significant spatial distribution changes. While transformer-based…
EEG-based emotion recognition struggles with capturing multi-scale spatiotemporal dynamics and ensuring computational efficiency for real-time applications. Existing methods often oversimplify temporal granularity and spatial hierarchies,…
Remote sensing image scene classification remains a challenging task, primarily due to the complex spatial structures and multi-scale characteristics of ground objects. Although CNN-based methods excel at extracting local inductive biases,…
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…
We present the first work demonstrating that a pure Mamba block can achieve efficient Dense Global Fusion, meanwhile guaranteeing top performance for camera-LiDAR multi-modal 3D object detection. Our motivation stems from the observation…
Multi-source remote sensing enables complementary observation of ground objects, while cross-modal fine-grained object retrieval remains challenging, especially under unaligned optical and SAR conditions. Unlike conventional retrieval…
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…
Guided depth super-resolution (GDSR) reconstructs HR depth maps from LR inputs with HR RGB guidance. Existing methods either model each modality independently or rely on computationally expensive attention mechanisms with quadratic…
Achieving both high accuracy and topological continuity in road segmentation from satellite imagery is a critical goal for applications ranging from urban planning to disaster response. State-of-the-art methods often rely on Vision…