Related papers: MambaMap: Online Vectorized HD Map Construction us…
Video semantic segmentation (VSS) plays a vital role in understanding the temporal evolution of scenes. Traditional methods often segment videos frame-by-frame or in a short temporal window, leading to limited temporal context, redundant…
Remote sensing images are frequently obscured by cloud cover, posing significant challenges to data integrity and reliability. Effective cloud detection requires addressing both short-range spatial redundancies and long-range atmospheric…
Traffic crash detection in long-form surveillance videos is essential for improving emergency response and infrastructure planning, yet remains difficult due to the brief and infrequent nature of crash events. We present…
Human motion generation stands as a significant pursuit in generative computer vision, while achieving long-sequence and efficient motion generation remains challenging. Recent advancements in state space models (SSMs), notably Mamba, have…
This paper proposes MambaST, a plug-and-play cross-spectral spatial-temporal fusion pipeline for efficient pedestrian detection. Several challenges exist for pedestrian detection in autonomous driving applications. First, it is difficult to…
Mamba is emerging as a novel approach to overcome the challenges faced by Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) in computer vision. While CNNs excel at extracting local features, they often struggle to capture…
Temporal information plays a pivotal role in Bird's-Eye-View (BEV) driving scene understanding, which can alleviate the visual information sparsity. However, the indiscriminate temporal fusion method will cause the barrier of feature…
Self-supervised video hashing (SSVH) is a practical task in video indexing and retrieval. Although Transformers are predominant in SSVH for their impressive temporal modeling capabilities, they often suffer from computational and memory…
Existing Transformer-based models for point cloud analysis suffer from quadratic complexity, leading to compromised point cloud resolution and information loss. In contrast, the newly proposed Mamba model, based on state space models (SSM),…
Time series data plays a pivotal role in a wide variety of fields but faces challenges related to privacy concerns. Recently, synthesizing data via diffusion models is viewed as a promising solution. However, existing methods still struggle…
Establishing semantic correspondences between images is a fundamental yet challenging task in computer vision. Traditional feature-metric methods enhance visual features but may miss complex inter-correlation relationships, while recent…
The rapid growth of long-duration, high-definition videos has made efficient video quality assessment (VQA) a critical challenge. Existing research typically tackles this problem through two main strategies: reducing model parameters and…
Recent deep learning approaches for river discharge forecasting have improved the accuracy and efficiency in flood forecasting, enabling more reliable early warning systems for risk management. Nevertheless, existing deep learning…
Autonomous driving requires an understanding of the static environment from sensor data. Learned Bird's-Eye View (BEV) encoders are commonly used to fuse multiple inputs, and a vector decoder predicts a vectorized map representation from…
Dynamic graphs exhibit intertwined spatio-temporal evolutionary patterns, widely existing in the real world. Nevertheless, the structure incompleteness, noise, and redundancy result in poor robustness for Dynamic Graph Neural Networks…
Online High-Definition (HD) maps have emerged as the preferred option for autonomous driving, overshadowing the counterpart offline HD maps due to flexible update capability and lower maintenance costs. However, contemporary online HD map…
Autonomous driving systems face significant challenges in perceiving complex environments and making real-time decisions. Traditional modular approaches, while offering interpretability, suffer from error propagation and coordination…
State-space models (SSMs), exemplified by S4, have introduced a novel context modeling method by integrating state-space techniques into deep learning. However, they struggle with global context modeling due to their data-independent…
Accurate detection of cardiac abnormalities from electrocardiogram recordings is regarded as essential for clinical diagnostics and decision support. Traditional deep learning models such as residual networks and transformer architectures…
Accurate and efficient multivariate time series (MTS) analysis is increasingly critical for a wide range of intelligent applications. Within this realm, Transformers have emerged as the predominant architecture due to their strong ability…