Related papers: MambaFlow: A Novel and Flow-guided State Space Mod…

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…

Transformers have become dominant in large-scale deep learning tasks across various domains, including text, 2D and 3D vision. However, the quadratic complexity of their attention mechanism limits their efficiency as the sequence length…

Driven by the rapid development of deep learning technology, the YOLO series has set a new benchmark for real-time object detectors. Additionally, transformer-based structures have emerged as the most powerful solution in the field, greatly…

Point cloud completion aims to generate a complete and high-fidelity point cloud from an initially incomplete and low-quality input. A prevalent strategy involves leveraging Transformer-based models to encode global features and facilitate…

Addressing the dual challenges of local redundancy and global dependencies in video understanding, this work innovatively adapts the Mamba to the video domain. The proposed VideoMamba overcomes the limitations of existing 3D convolution…

Place recognition is the foundation for enabling autonomous systems to achieve independent decision-making and safe operations. It is also crucial in tasks such as loop closure detection and global localization within SLAM. Previous methods…

Recent advances in LiDAR 3D detection have demonstrated the effectiveness of Transformer-based frameworks in capturing the global dependencies from point cloud spaces, which serialize the 3D voxels into the flattened 1D sequence for…

We tackle the task of scene flow estimation from point clouds. Given a source and a target point cloud, the objective is to estimate a translation from each point in the source point cloud to the target, resulting in a 3D motion vector…

Multimodal image fusion aims to integrate information from different imaging techniques to produce a comprehensive, detail-rich single image for downstream vision tasks. Existing methods based on local convolutional neural networks (CNNs)…

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,…

Mamba has garnered widespread attention due to its flexible design and efficient hardware performance to process 1D sequences based on the state space model (SSM). Recent studies have attempted to apply Mamba to the visual domain by…

We introduce a novel motion estimation method, MaskFlow, that is capable of estimating accurate motion fields, even in very challenging cases with small objects, large displacements and drastic appearance changes. In addition to lower-level…

In a real-world traffic scenario, varying-scale objects are usually distributed in a cluttered background, which poses great challenges to accurate detection. Although current Mamba-based methods can efficiently model long-range…

Learned visual compression is an important and active task in multimedia. Existing approaches have explored various CNN- and Transformer-based designs to model content distribution and eliminate redundancy, where balancing efficacy (i.e.,…

State Space Models (SSMs) with selective scan (Mamba) have been adapted into efficient vision models. Mamba, unlike Vision Transformers, achieves linear complexity for token interactions through a recurrent hidden state process. This…

Event cameras capture asynchronous pixel-level brightness changes with microsecond temporal resolution, offering unique advantages for high-speed vision tasks. Existing methods often convert event streams into intermediate representations…

Designing computationally efficient network architectures remains an ongoing necessity in computer vision. In this paper, we adapt Mamba, a state-space language model, into VMamba, a vision backbone with linear time complexity. At the core…

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…

Event camera-based visual tracking has drawn more and more attention in recent years due to the unique imaging principle and advantages of low energy consumption, high dynamic range, and dense temporal resolution. Current event-based…

Occupancy prediction has attracted intensive attention and shown great superiority in the development of autonomous driving systems. The fine-grained environmental representation brought by occupancy prediction in terms of both geometry and…