Related papers: MambaMap: Online Vectorized HD Map Construction us…
High-definition (HD) maps provide environmental information for autonomous driving systems and are essential for safe planning. While existing methods with single-frame input achieve impressive performance for online vectorized HD map…
High-definition (HD) maps are crucial to autonomous driving, providing structured representations of road elements to support navigation and planning. However, existing query-based methods often employ random query initialization and depend…
Deep image hashing aims to enable effective large-scale image retrieval by mapping the input images into simple binary hash codes through deep neural networks. More recently, Vision Mamba with linear time complexity has attracted extensive…
Modeling high-resolution spatiotemporal representations, including both global dynamic contexts (e.g., holistic human motion tendencies) and local motion details (e.g., high-frequency changes of keypoints), is essential for video-based…
High-Definition (HD) maps are essential for the safety of autonomous driving systems. While existing techniques employ camera images and onboard sensors to generate vectorized high-precision maps, they are constrained by their reliance on…
Dynamic outdoor environments with high temporal variation (HTV) pose significant challenges for 3D single object tracking in LiDAR point clouds. Existing memory-based trackers often suffer from quadratic computational complexity, temporal…
Temporal information is crucial for detecting occluded instances. Existing temporal representations have progressed from BEV or PV features to more compact query features. Compared to these aforementioned features, predictions offer the…
Accurate traffic prediction plays a vital role in intelligent transportation systems by enabling efficient routing, congestion mitigation, and proactive traffic control. However, forecasting is challenging due to the combined effects of…
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…
Existing RGB-T tracking algorithms have made remarkable progress by leveraging the global interaction capability and extensive pre-trained models of the Transformer architecture. Nonetheless, these methods mainly adopt imagepair appearance…
To reduce the reliance on high-definition (HD) maps, a growing trend in autonomous driving is leveraging onboard sensors to generate vectorized maps online. However, current methods are mostly constrained by processing only single-frame…
Online High-Definition (HD) map construction is pivotal for autonomous driving. While recent approaches leverage historical temporal fusion to improve performance, we identify a critical safety flaw in this paradigm: it is inherently…
Accurate 3D object detection in autonomous driving relies on Bird's Eye View (BEV) perception and effective temporal fusion. However, existing fusion strategies based on convolutional layers or deformable self-attention struggle to model…
Multivariate Time series forecasting is crucial in domains such as transportation, meteorology, and finance, especially for predicting extreme weather events. State-of-the-art methods predominantly rely on Transformer architectures, which…
Video anomaly detection (VAD) methods are mostly CNN-based or Transformer-based, achieving impressive results, but the focus on detection accuracy often comes at the expense of inference speed. The emergence of state space models in…
Video super-resolution (VSR) faces critical challenges in effectively modeling non-local dependencies across misaligned frames while preserving computational efficiency. Existing VSR methods typically rely on optical flow strategies or…
Recent advancements in state space models, notably Mamba, have demonstrated significant progress in modeling long sequences for tasks like language understanding. Yet, their application in vision tasks has not markedly surpassed the…
Recent advancements in anomaly detection have seen the efficacy of CNN- and transformer-based approaches. However, CNNs struggle with long-range dependencies, while transformers are burdened by quadratic computational complexity.…
In recent years, Transformers have become the de-facto architecture for sequence modeling on text and a variety of multi-dimensional data, such as images and video. However, the use of self-attention layers in a Transformer incurs…
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…